Computer‐Assisted Performance‐Based Assessment for Mental Health: A Scoping Review

Abstract

Adolescent mental health is foundational to personal development, yet it faces escalating challenges globally. While traditional assessment methods lack objectivity and ecological validity, integrating computer‐assisted technology (CAT) into performance‐based assessments (PBAs) offers a promising pathway. This review, following the PRISMA‐ScR reporting standard, analyzed 89 articles (2015–2025) to map the assessed components, CAT applications, and scenario diversity in mental health PBAs. Analysis revealed a research emphasis on mental disorders, with critical domains for adolescent development remaining significantly understudied. CATs significantly enhanced PBAs through data analysis, data acquisition, scenario creation, and tool digitization. PBA scenarios are diverse, demonstrating the adaptability of PBAs for multidimensional mental health assessment. Prioritizing the design of PBAs for social–emotional and adaptive assessment is critical for the early identification of adolescent mental health issues. Furthermore, advancing predictive analytics and leveraging large language models for feedback generation are promising ways to unlock CAT's potential in enhancing PBAs. Importantly, integrating and adapting scenarios from validated scales by CATs into PBAs could further enhance assessment typicality and reliability.

Introduction

Mental health is a critical foundation of youth development, supporting independence, academic achievement, and the formation of lifelong relationships (Patton et al. 2016). Recent data highlight the growing prevalence of mental health challenges among adolescents, with 15% of adolescents aged 10–19 years worldwide experiencing mental disorders in 2021 (IHME 2021). In the United States, 40% of high school students reported persistent sadness or helplessness in 2023 (Centers for Disease Control and Prevention 2024). These widespread issues not only profoundly impact individuals but also place significant burdens on health care and education systems, indicating an urgent need for more effective mental assessments and intervention strategies.

Effective assessment begins with a clear and comprehensive conceptualization. Mental health definitions range from the absence of diagnosable disorders to an emphasis on general well‐being (Wren‐Lewis and Alexandrova 2021). Different perspectives directly shape the scope and focus of mental health assessments, thus influencing the constructs measured. Traditional methods, such as self‐reports and clinical checklists, are favored for their convenience and cost‐effectiveness. However, social desirability bias and inaccurate self‐perception limit their insights (Feldon et al. 2015). They also lack ecological validity, failing to capture real‐world behaviors and unconscious psychological states. This limitation is particularly problematic in measuring adolescent mental health, which is unstable (Patel et al. 2023).

Performance‐based assessment (PBA) offers a promising alternative to traditional methods by evaluating observable behaviors in realistic or simulated scenarios. It effectively detects subtle impairments frequently overlooked by traditional methods, such as cognitive deficits and social skills (Angers et al. 2024; Keleman et al. 2024). Tasks such as the Multiple Errands Test (MET) (Shallice and Burgess 1991) and the UCSD Performance‐Based Skills Assessment (UPSA) (Patterson et al. 2001) show strong ecological validity, linking assessments with real‐life challenges (Dawson et al. 2009; Green et al. 2015). Moreover, embedding assessments in interactive scenarios enhances their accuracy and participant engagement (Aubrey 2011; Suastra and Menggo 2020). For example, the Shape School task (Espy 1997) is an accessible and enjoyable assessment for preschoolers (O'Meagher et al. 2019; Power et al. 2023).

The integration of computer‐assisted technology (CAT), such as virtual reality (VR) and machine learning (ML), further expands the potential of PBA (Al‐Ansi et al. 2023; Fazil et al. 2024). CATs enable scalable, objective, and ecologically valid mental health assessments by simulating naturalistic scenarios and processing complex data (Cerasuolo et al. 2024). Despite significant advancements, the state of computer‐assisted mental health PBA remains insufficiently understood, leaving key questions unanswered. Specifically, what mental health components are measured through computer‐assisted PBAs? What PBA scenarios are employed? What techniques are applied, and how do they facilitate mental health PBAs? To address these gaps, this study systematically synthesizes existing research on computer‐assisted mental health PBAs, focusing on their conceptual frameworks of mental health, the diversity of assessment scenarios, and the role of CAT in measuring various mental health dimensions. Through a comprehensive and structured analysis, this research not only deepens the understanding of computer‐assisted mental health PBAs but also offers actionable recommendations to advance the precision and applicability of mental health assessments.

Divergent Understandings of Mental Health

Mental health is a complex and multidimensional construct that varies across cultures and contexts. Traditionally, it has been narrowly defined as the absence of diagnosable mental disorders, as reflected in psychiatric frameworks such as the DSM‐5, which classifies over 300 conditions (APA 2013). While this framework aids in clinical diagnosis and treatment, it has been criticized for privileging pathology and overlooking broader dimensions of mental health as a dynamic and positive construct (Li et al. 2024; Murphy 2017).

In contrast, holistic perspectives—often grounded in positive psychology—define mental health as the ability to adapt and self‐manage under stress, emphasizing psychological capacities necessary for thriving, such as emotional stability, meaning, resilience, and positive relationships (Huber et al. 2011; Huppert and So 2013; Seligman and Csikszentmihalyi 2000). It aligns with definitions of the American Psychological Association (APA 2018) and the World Health Organization (WHO 2022), which frame mental health as well‐being. However, the overlap between terms such as mental health, well‐being, and mental well‐being remains contested (Keyes 2013). While positive mental health can contribute to flourishing, conflating it with general well‐being risks imposing unrealistic standards and oppressive expectations (Keller 2020; Wren‐Lewis and Alexandrova 2021).

These divergent understandings have shaped the development of varied mental health measurement tools, each corresponding to specific definitions and components. Clarifying the conceptual foundations is thus essential for developing precise and effective assessments, particularly for adolescents whose mental health is shaped by complex developmental factors. This need underpins our effort to investigate the components commonly assessed by PBAs and the tools employed across different dimensions.

CATs In Mental Health Assessment

CATs have enhanced the efficiency and flexibility of mental health assessment by digitizing traditional PBA tools and creating assessment scenarios. For example, Moore et al. (2015) developed a mobile version of the UPSA that achieved 87% accuracy in identifying schizophrenia patients. Unlike traditional PBAs, which rely on resource‐intensive in‐person observations (Greenwood et al. 2016), CATs like VR can create controlled and immersive environments that allow researchers to elicit cognitive and behavioral responses with greater precision (Bell et al. 2020). For example, the VR adaptation of the MET automates data collection in a virtual supermarket, reducing implementation costs while increasing task complexity and flexibility (Rand et al. 2009).

Beyond convenience, CATs enable the collection of multidimensional data that goes far beyond traditional item responses. Process data such as keystrokes, eye‐tracking patterns, and action sequences offer deeper insights into psychological states (Jiao et al. 2021). When combined with physiological and behavioral measures, VR paradigms have been shown to be particularly valuable in assessing some mental disorders (Wiebe et al. 2023). These high‐dimensional datasets also facilitate advanced analytic methods, such as clustering or word embedding, to extract meaningful insights (Qorich and El Ouazzani 2024).

Furthermore, CATs enhance objectivity by mitigating biases in human observation and scoring. Modern computer systems can detect subtle behavioral and emotional cues, such as microexpressions, thereby improving the reliability of assessments (Eileen Brown 2017). ML and large language models (LLMs) further extend this capacity, offering advanced pattern recognition and predictive accuracy (Hodges 2021). For example, Lau et al. (2023) demonstrated the effectiveness of fine‐tuned LLMs in detecting depression through parameter‐efficient tuning techniques.

Despite these advances, insufficient interdisciplinary collaboration, technical challenges in implementation, and the lack of validation hinder the broader adoption of CATs in mental health PBAs. To date, applications of CATs in PBAs across diverse mental health dimensions have not been comprehensively mapped. Bridging these gaps is essential to fully realizing the potential of CATs in advancing mental health research and assessment practices.

Definition of Key Concepts

Mental Health

As discussed above, existing definitions of mental health range from a pathology‐centered view that equates it with the absence of disorders to a more idealized notion overlapping with general well‐being. This study adopts a pragmatic and balanced definition: mental health is the capacity for psychological stability and adaptability when facing life challenges. It is a fluid condition influenced by individual and environmental factors (WHO and UNICEF 2024).

Informed by major mental health frameworks (APA, 2013; Keyes 2002; Ryff and Keyes 1995; WHO 2022), maintaining this balance requires (a) the absence of severe mental disorders, (b) basic cognitive and social skills integral to daily life (Moritz et al. 1995), (c) effective emotional regulation (Brandão et al. 2023), (d) adaptability to unpredictable events (Klanker et al. 2013), and (e) appropriate self‐cognition (Henriksen et al. 2017; Koban et al. 2021). Crucially, societal barriers must be distinguished from individual limitations because they may impede functioning without signifying poor mental health (Herrman 2016). This working perspective provides a robust framework for assessing and fostering mental health, particularly in adolescents, by equipping them with the necessary abilities and skills to navigate the challenges in their developmental journey.

Performance‐Based Assessment

In education, PBAs involve structured tasks that simulate authentic challenges, allowing individuals to demonstrate their learning processes while generating tangible outcomes (Adri et al. 2022). They not only measure cognitive mastery but also provide feedback on practice (Suastra and Menggo 2020). In the context of mental health, PBAs refer to the use of simulated or real‐world tasks to evaluate individuals' mental states. This method provides an effective framework for mental health measurement and feedback, linking abstract mental concepts with tangible performance.

Computer‐Assisted Technology

In the field of psychometrics, CATs broadly refer to a range of computerized tools and systems used throughout the assessment process, including hardware (e.g., input/output devices, sensors, and VR/AR devices), software platforms (e.g., test administration and data management platforms), and algorithmic approaches (e.g., ML, natural language processing, and LLMs). The core purpose of CATs is to assist assessment delivery, response capture, scoring, data processing, and result interpretation through automation, standardization, and enhanced interactivity (AERA et al. 2014; Bauer 2017).

Performance‐Based Assessment Scenario

In the context of computer‐assisted PBA, a scenario refers to a temporal sequence of contextual elements in which actions and events unfold and can be systematically observed (Ulbrich et al. 2015). Scenarios may involve structured experimental tasks or naturally occurring behaviors, provided they elicit measurable performance that reflects underlying psychological constructs. By embedding assessment tasks in structured scenarios, PBAs provide ecologically valid conditions that allow for direct or indirect observation and multimodal data capture.

Previous Reviews

Several reviews have examined advanced technologies and PBAs in mental health, focusing on cognitive functions, specific populations, and technological innovations (see Table 1). For example, Raimo et al. (2024) conducted a meta‐analysis showing that visuospatial and language abilities are strongly correlated with daily living activities, particularly when evaluated with PBAs. Similarly, Gawęda et al. (2024) demonstrated that PBAs are effective in identifying cognitive biases in schizophrenia spectrum psychoses. Iceta et al. (2021) reviewed neurocognitive function PBAs in individuals with binge eating disorder or food addiction. Population‐specific research further underscores the versatility of PBAs. For example, Su et al. (2023) highlighted the adaptability of PBA tools for preschool‐aged children across different cultural and developmental contexts. Collectively, these studies demonstrate the ability of PBAs to detect subtle impairments and address diverse clinical needs.

Other reviews have explored the integration of specific technologies in mental health assessment. Wongkoblap et al. (2017) synthesized work on social media data–based prediction of mental disorders, noting the dominance of text‐based approaches. Cerasuolo et al. (2024) highlighted the potential of VR in diagnosing autism spectrum disorder (ASD) by creating objective, ecological, and engaging scenarios. Building on this, Su et al. (2020) demonstrated the potential of deep learning (DL) for developing disease risk prediction models, while Kusuma et al. (2022) showed that ML approaches can outperform traditional models in predicting longitudinal suicide‐related outcomes, offering both scalability and predictive power.

Previous reviews have offered valuable insights into the application of CATs and PBAs in mental health assessment, but their scope has been fragmented. Most focus either on specific mental health or on particular technologies, which limits a comprehensive understanding of how CATs and PBAs map into the multidimensional nature of mental health. Moreover, little attention has been given to PBA scenarios, which are important to ensure that PBAs align with the constructs they aim to measure (Mutweleli et al. 2024). To address these gaps, the present scoping review systematically examines the interplay between CATs, the mental health constructs they assess, and the scenarios in which PBAs are implemented.

Research Rationale, Aims, and Questions of the Current Review

The current review differs from previous reviews in three aspects. First, unlike previous reviews that focused on isolated mental health constructs, this study adopts a multidimensional perspective, providing a comprehensive review of the research on and application of computer‐assisted mental health PBAs across cognitive, emotional, social, and other dimensions. Second, rather than emphasizing specific technologies, this review explores how CATs broadly enhance mental health PBAs. Third, this review examines different scenarios employed in PBAs, identifies how they align with different dimensions of mental health, and highlights the role of CATs in tailoring assessments to these scenarios. By integrating these considerations, this study seeks to develop a robust framework for understanding the application of CATs and PBAs in mental health assessment. Specifically, it aims to clarify which PBA scenarios are frequently used to assess specific mental health dimensions and how CATs can optimize assessments.

To achieve these objectives, this review poses the following research questions: What mental health components are typically measured via computer‐assisted PBAs? What roles do CATs play in enhancing mental health PBAs? What scenarios are used in computer‐assisted PBAs for mental health?

Method

This study presents a scoping review of the use of CATs in evaluating mental health through PBAs. The approach taken for this scoping review was informed by the Preferred Reporting Items for Systematic reviews and Meta‐Analyses extension for Scoping Reviews (PRISMA‐ScR; Tricco et al. 2018).

Search Strategy

A comprehensive literature search was conducted across five databases: Web of Science, EI Engineering Village, Scopus, APA PsycINFO, and PubMed. Studies were searched from 2015 onward as this period marks the development of CATs and their integration into psychological assessment research. The first search was performed on September 13, 2024, using structured keyword combinations related to computer‐assisted mental health assessment. The terms were organized into three conceptual domains and combined with Boolean operators (see Table 2). To ensure sensitivity and coverage, the search strings were piloted and refined in several iterations until they consistently retrieved key benchmark studies. There were no age limits for participants so that the mapping of computer‐assisted PBAs for mental health could be as complete as possible, as this is a new and limited study topic. A second search was conducted on December 31, 2025, following the same process. The complete search strategies are provided in Appendix A.

Inclusion and Exclusion Criteria

The titles and abstracts of the articles retrieved with the specified search terms (see Table 2) were screened according to the inclusion criteria. Only English‐language articles were considered. Further inclusion criteria are provided in Table 3; exclusion criteria are the inverse.

Screening and Data Management

Search results from all databases were imported into reference management software, where duplicates were identified through standardized bibliographic information and removed. Study selection proceeded in two stages: (a) titles and abstracts were screened against the inclusion criteria, and (b) full texts of potentially eligible studies were reviewed for confirmation. Two reviewers conducted independent duplicate screenings of the title, abstract, and full text, achieving significant inter‐rater agreement (Cohen's κ = 0.83). We developed a standardized data tool to extract information on studies, including populations, assessment domains, applied CATs, and PBA scenarios. Two reviewers independently extracted data and resolved discrepancies through consensus. Appendix B provides the detailed information.

Results

Search Results

A total of 14,104 articles were retrieved across all databases. After the removal of duplicates (n = 2617), 11,487 articles were screened by title and abstract. The full texts of the remaining 762 articles were assessed, leaving 89 articles to be included in the review (see Appendix B, Figure 1 for screening flow).

FIGURE 1 Flow diagram depicting the article screening process. (Figure not reproduced here; see the original article.)

The included studies were conducted across multiple countries, with the largest number of publications originating from the United States (26, 29%), China (13, 15%), and India (8, 9%). Validation studies accounted for most of the literature (57, 64%), followed by case–control studies (15, 17%), whereas longitudinal (4, 4%) and intervention‐based studies (2, 2%) were relatively rare. Publication volume showed an upward trend over time, particularly after 2017 (see Figure 2). Most studies focused on adult populations (48, 54%); only 17 articles examined children or adolescents exclusively. Sample sizes were generally modest, with over half of the studies involving fewer than 100 participants (51, 57%), whereas 19 studies included samples exceeding 200 participants.

FIGURE 2 Distribution of screened articles by sample age group from 2015 to 2025. (Figure not reproduced here; see the original article.)

Mental Health Components

In line with the established definition of mental health, this review categorized the measured variables into five main categories: mental disorders, cognitive functions, emotional and social competence, coping and adaptation, and self‐cognition. Figure 3 presents the components included in these five categories and the number of articles measuring them. Mental disorder was the most frequently measured category (49 articles, including 41 exclusively focused on this domain). Self‐cognition was rarely assessed, with only four articles. Although most studies targeted a single category, 12 combined two or more domains—most often mental disorders with coping and adaptability.

FIGURE 3 Network diagram of mental health components assessed in the reviewed articles. Node size reflects the number of studies assessing each category or component; gray line thickness represents the number of studies jointly measuring the two categories. (Figure not reproduced here; see the original article.)

Mental Disorders

The reviewed studies assessed a range of mental disorders, such as depression, anxiety, schizophrenia, and bipolar disorder, with 8 studies focusing on adolescent populations. Overall, 26 studies investigated depression and 16 assessed anxiety, with 13 addressing both conditions concurrently. Other mental health issues were also represented, albeit to a lesser extent. Schizophrenia was assessed in nine articles, typically using patient‐control comparisons. Disorders with higher prevalence in specific age groups, such as attention‐deficit/hyperactivity disorder (ADHD) and ASD, were evaluated in only nine articles. Suicidality was explicitly assessed in three articles, including Liu, Zhong, et al. (2022) and Liu, Lu, et al. (2022), which recruited participants via a project's website and classified them into suicide risk classes based on preassessment interviews.

Cognitive Functions

Cognitive functions, such as memory, attention, and decision‐making, enable individuals to acquire knowledge and carry out tasks. Cognitive impairments often coexist with mental disorders and can adversely affect daily functioning (McIntyre et al. 2013). This review identified 14 articles measuring cognitive functions through PBAs. The most articles, nine in total, focused on executive functions, with 4 evaluating memory and attention simultaneously. For example, Tezer et al. (2025) assessed the degree of cognitive impairment in children and adolescents with Juvenile Idiopathic Arthritis in terms of executive function, composite memory, working memory, complex attention, and 6 additional domains. Hoffmeister et al. (2025) assessed the elderly's memory, attention, executive functioning, and processing speed to detect early Alzheimer's disease.

Emotion and Sociability

Emotion and sociability refer to individuals' abilities to recognize, regulate, and express emotions, as well as to initiate and maintain social relationships. This dimension captures factors essential for emotional stability and social functioning in both stressful and routine contexts. A total of 19 articles measured emotion and sociability, with 5 focusing on adolescent populations. For example, two articles evaluated adolescents' social perspective‐taking (Fantozzi et al. 2024; Pile et al. 2017), a core component of empathy that enables understanding others' thoughts and feelings.

In adults, emotion regulation was a key focus. Broch‐Due et al. (2018) compared emotion regulation skills between individuals with bipolar disorder and healthy controls, reporting significant differences. Emotion regulation is closely linked to emotion recognition (Rosenthal et al. 2011), which Myruski et al. (2019) assessed through facial morphing tasks. Regarding social anxiety, two studies examined it by requiring participants to deliver speeches in socially stressful settings (Harshit et al. 2024; Nowakowski et al. 2015).

Coping and Adaptation

Coping and adaptation refer to the behavioral and cognitive strategies that individuals employ to manage stress, endure adversity, and adjust to life's challenges (Aspinwall 2004). Unlike emotion and sociability, which emphasize ongoing affective and interpersonal processes, coping and adaptation are situational responses to specific external challenges that emphasize goal‐directed strategies tailored to immediate demands (Marroquín et al. 2017).

Seventeen studies evaluated coping mechanisms and adaptation, including 10 that examined stress states across different populations. For example, Schoch‐Ruppen et al. (2018) assessed prenatal stress in pregnant women, emphasizing implications for both maternal well‐being and neonatal development, while Singh and Singh (2022) assessed stress in a broader cohort of 2500 Indian online users. Four studies focused on resilience and distress tolerance, such as Iasonidou et al. (2023), who examined women at varying risks of eating disorders under physical and cognitive stressors. Coping mechanisms were also linked to behavioral outcomes: Purwandari et al. (2020), for example, explored internet addiction in undergraduate students. Together, these findings underscore the importance of assessing coping strategies and their effectiveness in mitigating stress, enhancing resilience, and preventing maladaptive outcomes.

Self‐Cognition

Self‐cognition refers to individuals' awareness and understanding of themselves, including their beliefs, perceptions, and assessments. It is conceptually and functionally distinct from cognitive functions, as impairments in these domains can be dissociated (Rutherford and Rogers 2003). Although studies examining self‐cognition represent a smaller subset of this review, they provide valuable insights. Ali et al. (2022) investigated unrealistic beliefs, that is, deviations from reality, that may shape negative self‐schemas, which are basic to one's self‐concept and can impact various aspects of mental health and behavior. McArthur et al. (2019) explored self‐schemas among adolescents, a developmentally sensitive group experiencing various changes.

Computer‐Assisted Approaches

Based on the evidence‐centered design framework (Mislevy et al. 2003), this review classifies the implementation of CAT in PBAs into four types according to their roles in evidence generation and representation: tool digitization, scenario creation, data acquisition, and data analysis. Tool digitization converts traditional instruments into digital formats, enhancing standardization and procedural control through automated presentation and scoring. CATs like VR and AR strengthen assessments' ability to accurately elicit the targeted psychological processes by creating more immersive, realistic, and ecologically valid scenarios. Data acquisition broadens the range of observable evidence by collecting behavioral and physiological responses. Finally, data analysis, using statistical learning, ML, and DL models to extract and analyze evidence from multimodal data, improves predictive accuracy. Figure 4 shows their distribution across five mental health dimensions. Data analysis was the most prevalent application (60 articles), followed by tool digitization and scenario creation. Scenario creation was mainly used to assess cognitive function, emotion and sociability, while data acquisition and analysis were more often used for mental disorder PBAs. Tool digitization exhibited a more even distribution across cognitive function, emotion and sociability, and mental disorder domains.

FIGURE 4 Applications of CATs across five mental health dimensions. (Figure not reproduced here; see the original article.)

Data Analysis

Data analysis refers to using computational techniques to extract meaningful patterns from behavioral, textual, and physiological data. These methods fall broadly into four paradigms: feature engineering, architecture engineering, objective engineering, and prompt engineering (Liu et al. 2023).

Within our review, feature engineering was the most prevalent, applied in 57 articles. Grounded in domain expertise, it involves extracting key features (e.g., language use, facial expressions, and physiological reactions) to improve predictive accuracy and interpretability. For example, Purwandari et al. (2020) analyzed web browsing histories and selected five specific features to develop a classification model for internet addiction. Textual feature extraction methods such as LIWC (Pennebaker et al. 2007) and TF‐IDF (Salton and Buckley 1988) were frequently applied to social media posts or personal narratives. Schoch‐Ruppen et al. (2018) applied LIWC to analyze pregnant women's written texts, finding associations between prenatal stress and frequent use of negative‐emotion words.

Architecture engineering involves designing and selecting DL models. Roy et al. (2020) employed neural networks to create a binary model that detected suicidal ideation from tweets. Five articles combined feature and architecture engineering. Liu, Zhong, et al. (2022) and Liu, Lu, et al. (2022) compared the predictive performance of these two in text analysis for assessing mental state. Objective and prompt engineering were less frequently applied in mental health PBAs. Ding et al. (2025) extracted 159 audio features from speech tasks, developed a TCN‐MTA multi‐task model with personality‐assisted auxiliary tasks, and then refined it using a joint loss function to aid in early diagnosis of depression. Only one study employed prompt engineering, with Shin et al. (2024) applying fine‐tuned LLMs to detect depression through users' diaries. LLMs were also used as foundational models in the architecture engineering approach. Jiang et al. (2024) applied models such as DinoV2, WavLM, and LLAMA‐65B to multimodal interview data (audio, video, and transcripts). After encoding signals into high‐dimensional embeddings, multimodal fusion was employed to identify depression and anxiety.

Physiological and Behavioral Data Acquisition

Physiological and behavioral data acquisition involves the use of CATs, such as the Internet of Things (IoT), eye‐tracking systems, and neuroimaging technologies, to capture real‐time and high‐resolution indicators of mental states. These technologies allow for precise measurement of neural activity, visual attention, and movement patterns, offering an objective basis for mental health PBAs.

In this review, 18 studies employed CATs to enhance data acquisition. IoT sensors, employed in six studies, enabled real‐time collection of physiological and behavioral data, capturing physiological states and movement patterns. Eye‐tracking technologies, reported in five studies, were used to assess visual attention and cognitive processing. By monitoring eye movements and fixations, researchers gained insights into information processing (Kim et al. 2022), attention allocation (Fantozzi et al. 2024), and emotional responses to visual stimuli (Broch‐Due et al. 2018; Jyotsna et al. 2023; Xiang et al. 2024). Electroencephalography (EEG) was used in five studies to capture electrical brain activity, allowing researchers to examine brain changes linked to ADHD (Öztoprak et al. 2017), anxiety (Yadawad et al. 2024), stress (Rajendran et al. 2024), depression (Stone et al. 2025), and emotional state (Raina 2025).

Scenario Creation

Scenario creation involves designing immersive and interactive PBA scenarios that simulate real‐world or imaginary situations. These scenarios, often powered by VR and interactive game design, enable researchers to observe participants' behaviors and responses in ecologically valid contexts while maintaining experimental control.

In this review, 22 studies applied CATs to develop scenarios. Seven created VR scenarios, with settings ranging from imaginative (e.g., a spaceship; Marín‐Morales et al. 2021) to everyday environments, such as a supermarket (Tsai et al. 2021), kiosk (Kim et al. 2022), orchard (Danousis and Goumopoulos 2023), social scenarios (Kjærstad et al. 2022), and classrooms (Neguț et al. 2017; Parsons and Carlew 2016). These examples illustrate VR's versatility in constructing dynamic and context‐specific scenarios tailored to diverse research objectives.

Beyond VR, three studies adapted classic cognitive tests and incorporated them into video games. For example, Ibrahim et al. (2023) adapted five classic tests into a puzzle adventure game set in a village, where participants need to complete tasks like house renovation to evaluate their multiple cognitive functions. Additionally, the director task was used in two studies to simulate social communication under asymmetric information, assessing participants' capacities to infer others' mental states. Similarly, the Movie for Assessment of Social Cognition (MASC), adopted in two studies, immersed participants in a film‐based scenario where they answered questions about characters' mental states (Corsi et al. 2021; Poznyak et al. 2019). These methods combine narrative richness with standardized assessment, offering unique insights into social cognition.

Digital Assessment Tools

In this review, 40 articles employed multiple computerized PBA instruments across various mental health dimensions. Several classic paradigms have been digitized. The stop‐signal task (SST), traditionally used to assess inhibition control (Morein‐Zamir and Sahakian 2010), was employed by Leontyev et al. (2019), who compared the predictive power of its standard and ML‐enhanced versions. The latter, which integrated mouse‐tracking data, demonstrated higher accuracy in assessing ADHD symptoms. Similarly, the Stroop task (ST), designed to measure conflicting information processing (Stroop 1935), appeared in nine studies targeting mental disorders, cognitive functions, and adaptation. Badr et al. (2023) used the ST to induce and evaluate stress, while Lu et al. (2021) employed a word‐face version to assess emotional conflict resolution skills.

PBA Scenarios

The PBAs reviewed encompass various scenarios, classified inductively according to their response‐elicitation mechanism, including laboratory‐based, social interaction, game, and emotion‐stimulating scenarios. Laboratory‐based scenarios were the most prevalent (39 studies), followed by social interaction scenarios (38 articles). Emotion‐stimulating scenarios appeared in 10 articles, while game scenarios were the least common (eight studies). As shown in Figure 5, laboratory‐based scenarios were employed across all mental health categories. Social interaction scenarios mainly focused on assessing mental disorders, with 27 articles enhancing data analysis through CATs. Game scenarios were applied primarily to measure cognitive functions, whereas emotion‐stimulating scenarios were commonly used to evaluate coping and adaptive abilities.

FIGURE 5 PBA scenarios assessing mental health under different CAT applications. (Figure not reproduced here; see the original article.)

Laboratory‐Based Scenarios

Laboratory‐based scenarios are highly controlled and standardized, designed to elicit specific psychological or behavioral responses using abstract or symbolic stimuli and tasks. Among these articles, 22 focused on mental disorders. Digitalized assessment tools were the most common CAT application in these scenarios, appearing in 26 articles.

Task accuracy and response time were widely used indicators, reported in 24 articles. Accuracy directly reflects task execution precision, while response time indicates information processing efficiency. Beyond these structured responses, several studies have expanded data acquisition by including multimodal features such as audio, video, and behavioral recordings to evaluate mental disorders. For example, reading tasks and the verbal fluency tasks facilitated audio‐based analysis (Bruno et al. 2023; Huang et al. 2023; Luo et al. 2024). Stark et al. (2022) quantified walking and balance performance using IoT, illustrating how behavioral data can enhance laboratory‐based PBAs.

Social Interaction Scenarios

Social interaction scenarios rely on individuals' interaction with real people or virtual agents in socially meaningful contexts, such as role play, public speaking, teamwork, interviews, and social media engagement, to assess mental health through dynamic interpersonal behaviors. These scenarios were widely applied to measure mental disorders and emotion and sociability, with CATs typically enhancing data analysis.

Within these studies, social media analysis was especially prominent. Platforms like Facebook, Twitter, and Weibo provided data for assessing mental disorders, with features extracted from posts using CATs like LIWC and TF‐IDF. Researchers also analyzed additional parameters, such as browsing histories (Purwandari et al. 2020), comment threads (Hemtanon et al. 2020), follower counts, and posting time (Sivak and Smirnov 2020). Nguyen et al. (2018) conducted a longitudinal survey to predict depression and anxiety based on images that participants posted on social media platforms.

Interviews were another common method, reported in 10 articles. To predict suicidal ideation, Liu, Zhong, et al. (2022) and Liu, Lu, et al. (2022) analyzed eye contact in video data, while Wright‐Berryman et al. (2023) transcribed audio recordings for textual analysis. Simulated social pressure tasks, such as public speaking, mock job interviews, and simulated auditions, allowed researchers to observe stress‐related behaviors (Nowakowski et al. 2015; Oesten et al. 2023; Harshit et al. 2024; Yadawad et al. 2024; Kho et al. 2025). In addition, more naturalistic settings, such as teamwork projects in real workshops, were used to assess coping and adaptive abilities (Zeulner et al. 2024). Together, these approaches demonstrate the versatility of social interaction scenarios in capturing complex psychological processes across both structured and naturalistic contexts.

Game Scenarios

Game scenarios embed PBA tasks within gamified and immersive environments, incorporating structured rules, goals, role assignments, rewards, and penalties. These scenarios all focus on evaluating cognitive functions, with CATs facilitating scenario creation and data analysis. Eight articles employed game scenarios, using performance metrics such as completion time, in‐game achievements, and behavioral responses as indicators of mental health states. VR games were designed to simulate real‐world environments, such as supermarkets and kiosks, to evaluate mild cognitive impairments and cognitive load (Kim et al. 2022; Tsai et al. 2021). Through CAT, eye‐tracking and sensor‐based data were frequently used to capture detailed behavioral responses. For example, Danousis and Goumopoulos (2023) employed sensors to capture the body positions and gestures of elderly participants in a VR fruit‐harvesting game, gaining insights into physical and cognitive engagement. Puzzle adventure games focus on structured narratives and still improve the immersion of the assessment without VR technologies (Ibrahim et al. 2023).

Emotion‐Stimulating Scenarios

Emotion‐stimulating scenarios rely on affective cues to induce affective perturbation—shifting the individual from a neutral state to specific emotional arousal levels through passive or active induction. In reviewed articles, these scenarios are primarily used to examine coping and adaptation under emotion influence. CATs were predominantly applied in these studies for data acquisition and tool digitalization.

A total of 10 studies employed emotion‐stimulating scenarios, with five measuring coping and adaptive competencies. For example, frustration‐inducing tasks, such as the mirror tracing persistence task and paced auditory serial addition task, evaluated participants' tolerance for frustration through task performance and time‐to‐quit measures (Iasonidou et al. 2023; Seymour et al. 2016; Veilleux et al. 2019). Studies also measured mental disorders through mood induction tasks, such as the bubble task, snake task, and speech task, to assess internalizing disorders in children (McGinnis et al. 2021). Multimedia tools, including affective pictures and movie clips, were used to induce targeted emotions like nervousness and fear. For example, Xiang et al. (2024) analyzed pupillary responses to combat scenes to assess resilience, offering nuanced insights into adaptive functioning.

Discussion

PBA'S Role in Empowering Adolescent Mental Health Assessment

Adolescence is a formative period with substantial physical, cognitive, and socioemotional changes (Patton et al. 2016; Sawyer et al. 2012). These shifts increase vulnerability to emotional fluctuations, self‐concept instability, and social stress, potentially resulting in mental subhealth—a reversible but potentially worsening state if not promptly handled (Dong and Dong 2001; Wu et al. 2021). Reliable assessment during this stage is challenging, as adolescents' self‐awareness is still developing and their self‐reported answers are often influenced by social desirability (De Los Reyes et al. 2015). PBAs offer an alternative by capturing observable mental and behavioral responses in real time rather than relying on introspective judgments. Through performance indicators, PBAs can reveal impairments and mental state changes often missed by self‐reports (Connor and Maeir 2011; Nielsen et al. 2016; Regev and Josman 2020). This sensitivity is particularly valuable for adolescents, who may perform within normal ranges on self‐report scales but exhibit mild mental issues under PBA (Kiss et al. 2024).

In reviewed articles, most CAT‐enhanced PBAs focused on the evaluation of mental disorders, while dimensions such as emotion and sociability, as well as coping and adaptation, have received relatively little attention. This disparity is noteworthy, as these dimensions are crucial to adolescents' psychological development (Knapp 2021; Martinsone et al. 2022; Perzow et al. 2021). Social–emotional and adaptive competencies empower adolescents to manage increasing responsibilities, academic stress, and shifting interpersonal relationships (Collie 2020; Moksnes et al. 2010; Ronen 2021), which are intrinsically dynamic, manifesting through interactions and contextual demands (Folkman 2013; Kuppens and Verduyn 2017). Traditional self‐reports, though useful for assessing internalized and stable traits, are inadequate for capturing these context‐sensitive processes in real time (Anderson et al. 2017). Thus, PBAs that simulate real‐world scenarios and elicit contextual responses may offer a more ecologically grounded means of assessing these competencies (Lievens and De Soete 2012).

PBAs are contextualized, embedding assessment in scenarios that closely mirror adolescents' daily experiences. Such scenario fidelity improves assessment ecological validity by eliciting authentic responses under simulated real‐life stressors or emotionally stimulated scenarios (Stanton and Franz 2015; Fiebig et al. 2020). Beyond static reporting, PBAs are inherently interactive, requiring individuals to respond to evolving demands in continuous scenarios (Andrews‐Todd et al. 2021). These interactive settings foster embodied engagement, enabling the capture of social–emotional and adaptive processes through bodily states like facial expressions, gestures, or physiological arousal (Barsalou 2008; D'Mello et al. 2018). Collectively, these features offer PBAs distinct benefits in assessing adolescents' emotion and sociability, as well as coping and adaptation in ecologically grounded ways.

With growing concerns about social–emotional, adaptive, and other issues of adolescent mental health, the demand for accurate and timely assessment tools has increased (WHO and UNICEF 2024). Future research should focus on designing PBAs for emotion and sociability, as well as coping and adaptation, that correspond with adolescents' developmental characteristics and daily experiences. With familiar scenarios and interactive tasks, such PBAs could accurately measure and timely identify adolescents' social–emotional and adaptive conditions, thus helping them navigate adolescence smoothly and develop healthily.

CAT'S Value and Current Landscape Within Mental Health PBAs

A synthesis of the reviewed articles indicates that CATs have advanced mental health PBAs by transforming the design, capture, and interpretation of psychological evidence. CATs serve four primary functions: tool digitization, scenario creation, data acquisition, and data analysis. These improve the precision, scenario fidelity, evidence complexity, and inferential depth of mental health PBAs, pertaining to different stages of the evidence‐generation process.

Tool digitization and scenario creation are two CAT applications to solve measurement issues of PBA and enhance its design (de Klerk et al. 2016). Tool digitization facilitates precise control of stimulus presentation and response timing, improving PBA's standardization, precision, and reliability (Bauer et al. 2012; de Klerk et al. 2016). It also lowers costs and enables large‐scale, flexible, and efficient assessments, overcoming typical challenges like small sample sizes, uncontrolled conditions, and site dependency (Alfalahi et al. 2022; De Angel et al. 2022; Shute and Rahimi 2017). Scenario creation, particularly when implemented by VR or AR, improves scenario fidelity and ecological validity of PBA, eliciting targeted and authentic responses (Andrews‐Todd et al. 2021; Pieri et al. 2023; Spytska 2024). It should be noted that immersive PBA scenarios require careful design to minimize extraneous processing and maintain coherence, thereby avoiding additional cognitive load (Mayer and Fiorella 2014).

CATs also broaden the scope and depth of psychological evidence within PBAs. CATs facilitate the collection of physiological and behavioral data produced by participants. This capability enables PBAs to be more interactive and embodied, thereby generating more complex and ecologically valid evidence (Barsalou 2008; Niedenthal 2007). The real‐time monitoring of these signals could provide a more detailed picture of underlying mental states (Ates et al. 2024; Bateni and Sigal 2022). After data collection, accurate analysis is essential for deriving meaningful psychological inferences. CATs could combine multimodal data streams, offering complementary insights beyond single modalities (Dai et al. 2023). In mental health PBAs, feature engineering remains the primary analytic paradigm, as it aligns with psychological theory by offering interpretable indicators that connect behavioral features to mental states. Empirical studies demonstrate that ML algorithms outperform traditional linear models in predicting constructs like well‐being and personality (Oparina et al. 2025; Stachl et al. 2020). DL models are relatively less used compared to other fields (Devlin et al. 2019). Although they can automatically learn hierarchical representations for detection, classification, and prediction (LeCun et al. 2015), this often sacrifices interpretability, hence their being known as “black box” models (Ribeiro et al. 2016).

A key challenge in analyzing psychological data with CATs lies in balancing interpretability with predictive precision. Transparent “white‐box” models like linear regression (Weisberg 2005) and decision‐tree algorithms (Safavian and Landgrebe 1991) offer explainable results but lack the predictive power of complex “black‐box” models. Overemphasizing interpretability constrains the psychometric utility of CATs. Some researchers, therefore, argue that prioritizing predictive performance over explanatory power may offer new insights into the dynamics of mental states (Yarkoni and Westfall 2017). In practice, DL approaches have demonstrated promising potential in identifying latent patterns and predicting mental health trajectories. For example, a fine‐tuned BERT model (Devlin et al. 2018) achieved an F1 score of 91.3% in identifying suicide risk on social media (Tanaka and Fukazawa 2024). Furthermore, methodological innovations, such as hidden state analysis in DeBERTa models (Ormerod 2022) and univariate histogram projections for SVMs (Cherkassky and Dhar 2015), exemplify possible pathways to reconcile predictive accuracy with transparency.

CATs also hold promise for delivering personalized and actionable feedback that supports psychological stability and adaptability. Although PBAs move beyond self‐report formats, their results are still expressed in terminology that participants may find difficult to understand. Particularly, adolescents tend to describe mental experiences using everyday language like sadness, loneliness, or anger (JHU and UNICEF 2022), highlighting the need for feedback that resonates with lived experience. Advances in LLMs may address this gap by generating data‐driven, accessible, individualized, and supportive feedback, which may transform PBA from a diagnostic process into a meaningful progress that helps individuals understand and regulate their own mental health.

Collectively, these applications demonstrate the increasing potential of CATs to enhance the applicability, ecological validity, embodiment, and accuracy of mental health PBAs. Future research should focus on developing integrative analysis and feedback frameworks that comprehensively utilize these potentials to improve participants' mental health.

Limitations and Improvements in PBA Scenario Design

The design of scenarios is pivotal to the quality of PBAs for mental health. This is acutely evident in adolescents, who often exhibit mental concerns in some scenarios but not others (De Los Reyes et al. 2015), highlighting the importance of PBA scenario fidelity. Our review finds that current CAT‐enhanced mental health PBAs employ diverse scenarios, including laboratory, social interaction, game, and emotion‐stimulation. Laboratory‐based and social scenarios cover every dimension of mental health, while emotion‐stimulating scenarios primarily target coping and adaptation. VR‐powered game scenarios are particularly common for measuring cognitive functions. Although they can offer safe and controlled conditions for interactions (Riva 2005; Lumsden et al. 2016), these immersive scenarios often introduce excessive stimuli that disrupt attention and impose heavy cognitive loads, reducing measurement precision (Mayer and Fiorella 2014; Neguţ et al. 2016; Lobato‐Camacho et al. 2024). Moreover, overly standardized or culturally neutral scenarios risk reducing participants' emotional resonance (Fang et al. 2022). These limitations reveal the challenge of attaining both high reliability and ecological validity in mental health PBAs (Fletcher and Miciak 2023). Therefore, enhancing the theoretical and cultural relevance, as well as the narrative coherence of scenarios, is essential for improving PBA accuracy and reliability.

Drawing from these challenges, established psychometric instruments, such as self‐report scales, offer valuable insights for PBA scenario design. The scenarios embedded in scale items are typically derived from a rigorous and theory‐driven development process that includes theoretical construction, expert review, and iterative empirical validation (Nunnally and Bernstein 1994; DeVellis and Thorpe 2021). Such procedures ensure that assessment scenarios are theoretically grounded, psychometrically sound, and culturally relevant. For example, emotional ability measures like the Situational Test of Emotional Understanding (MacCann and Roberts 2008) and the Social Emotional Competence Questionnaire (Zhou and Ee 2012) use validated scenarios that simulate interpersonal and emotional challenges in real life. Incorporating such scenarios into PBA design could balance ecological validity with measurement reliability, bridging the methodological rigor of traditional psychometrics with the contextual and interactive advantages of PBAs.

However, scenarios embedded in traditional scales are discrete and static, disrupting narrative flow and immersive engagement. Such fragmentation also heightens participants' cognitive burden, as they need to reconstruct situational meaning (Sweller 2011; Männiste et al. 2019). CATs, especially LLMs, offer promising solutions to these challenges by transforming standardized scale items into storytelling and interactive PBA scenarios (Yang et al. 2024). In doing so, they can enhance interactivity, coherence, and contextual richness while maintaining theoretical grounding. Researchers must carefully manage scenario complexity and participant familiarity while minimizing unnecessary elements (Mayer and Fiorella 2014) to ensure that technologies strengthen the ecological validity, reliability, and contextual fidelity without increasing cognitive load or cultural biases in PBAs.

Future research could use validated psychometric instruments for reference to develop PBA scenarios with stronger theoretical grounding and contextual typicality. CATs can help refine and localize these scenarios to improve storyline coherence and experience fit. Ultimately, such CAT‐enhanced PBAs could enable more effective and engaging assessments of adolescents, facilitating early identification and personalized intervention for mental health issues.

Conclusion and Limitations

This review systematically mapped the landscape of CAT‐enhanced PBAs for mental health. Through a rigorous multistage screening process across five major databases, we identified 89 articles covering various CAT‐enhanced PBAs that assess mental disorders, cognitive functions, emotion and sociability, coping and adaptation, and self‐cognition. Several critical domains for adolescents are insufficiently explored, like emotion, sociability, coping, and adaptation, which are inappropriately assessed by self‐reports, necessitating developing contextualized and interactive PBAs. CATs strengthen PBAs through data analysis, physiological and behavioral data collection, scenario creation, and tool digitization, enhancing PBA design, evidence diversity, and analytical ability. However, their potential for generating predictive analytics and using LLMs for PBA feedback remains untapped. PBA scenarios are diverse, spanning laboratory, social interaction, game, and emotion‐stimulating contexts. To mitigate potential issues such as poor reliability, excessive cognitive burden, and insufficient typicality in PBA, LLMs can be employed to adapt validated scales and generate coherent, ecologically valid, and theoretically grounded PBA scenarios. With CAT‐enhanced PBAs, improve the effectiveness and accuracy in identifying mental health issues, thus designing more targeted intervention strategies to foster the growth and development of adolescents.

This review underscores the value of CAT‐enhanced PBAs in addressing the limitations of traditional assessment methods, offering a framework for integrating specific technologies into diverse mental health dimensions. Expanding CAT applications and incorporating context‐sensitive scenarios could enhance early identification of mental health concerns, fostering evaluations that support psychological stability and adaptability. Meanwhile, this review reveals an important gap in the literature regarding the limited research focused on teenagers. Future research should adapt validated computer‐assisted PBA paradigms developed for adults to adolescents, refining scenario, task, and feedback designs to suit developmental traits.

Despite these contributions, this review has limitations. First, it overlooks the role of group‐level psychological constructs, such as collective emotion, cohesion, and shared beliefs, which are essential for understanding societal mental health outcomes (Abrutyn 2023; Goldenberg 2024; McIntyre et al. 2018). Future research should adopt multilevel frameworks that integrate individual and collective variables to inform interventions addressing personal and community mental health. Second, this review synthesizes evidence descriptively due to the methodological heterogeneity of included studies, without performing a risk‐of‐bias evaluation or a quantitative evaluation of PBA efficacy and reliability. As such, the findings should be interpreted as a mapping of the field rather than an appraisal of evidence strength. Future meta‐analyses are needed to generate statistically robust insights into PBA efficacy, identify methodological strengths and weaknesses, and guide the development of more reliable and effective mental health PBAs (Gurevitch et al. 2018). Finally, although we did not pre‐register a review protocol, we sought to maintain methodological rigor by adhering to the PRISMA‐ScR reporting guidelines and providing full details of the search strategy, screening, and data extraction. This approach enhances transparency and allows readers to appraise the review process and reproducibility.

Funding

This work was supported by National Key Research and Development Program of China (2021YFC3340800).

Conflicts of Interest

The authors declare no conflicts of interest.

Acknowledgements

AcknowledgementsThis work was supported by the National Key Research and Development Program of China (2021YFC3340800). An AI‐assisted tool (Grammarly) was used for language polishing. All scientific decisions and interpretations were made by the authors.

References

1. Abrutyn, S. 2023. “The Roots of Social Trauma: Collective, Cultural Pain and Its Consequences.” Society and Mental Health 14: 240–256. 10.1177/21568693231213088. doi:10.1177/21568693231213088
2. Adri, J. , Refdinal , Ambiyar , and A. S. Abdullah . 2022. “Critical Thinking Skills in Performance‐Based Assessment: Instrument Development and Validation.” Journal of Technical Education and Training 14, no. 1: 90–99. 10.30880/jtet.2022.14.01.008. doi:10.30880/jtet.2022.14.01.008
3. AERA, APA, & NCME . 2014. Standards for Educational and Psychological Testing. American Educational Research Association.
4. Al‐Ansi, A. M. , M. Jaboob , A. Garad , and A. Al‐Ansi . 2023. “Analyzing Augmented Reality (AR) and Virtual Reality (VR) Recent Development in Education.” Social Sciences & Humanities Open 8, no. 1: 100532. 10.1016/j.ssaho.2023.100532. doi:10.1016/j.ssaho.2023.100532
5. Alfalahi, H. , A. H. Khandoker , N. Chowdhury , et al. 2022. “Diagnostic Accuracy of Keystroke Dynamics as Digital Biomarkers for Fine Motor Decline in Neuropsychiatric Disorders: A Systematic Review and Meta‐Analysis.” Scientific Reports 12: 7690. 10.1038/s41598-022-11865-7.35546606 PMC9095860 doi:10.1038/s41598-022-11865-7 PubMed
6. Ali, M. , A. Baqir , H. Husnain Raza Sherazi , A. Hussain , A. Hassan Alshehri , and M. Ali Imran . 2022. “Machine Learning Based Psychotic Behaviors Prediction From Facebook Status Updates.” Computers, Materials & Continua 72, no. 2: 2411–2427. 10.32604/cmc.2022.024704. doi:10.32604/cmc.2022.024704
7. American Psychiatric Association . 2013. Diagnostic and Statistical Manual of Mental Disorders. 5th ed. American Psychiatric Association. 10.1176/appi.books.9780890425596. doi:10.1176/appi.books.9780890425596
8. American Psychological Association . 2018. “APA Dictionary of Psychology.” https://dictionary.apa.org/.
9. Anderson, R. , M. Thier , and C. Pitts . 2017. “Interpersonal and Intrapersonal Skill Assessment Alternatives: Self‐Reports, Situational‐Judgment Tests, and Discrete‐Choice Experiments.” Learning and Individual Differences 53: 47–60. 10.1016/j.lindif.2016.10.017. doi:10.1016/j.lindif.2016.10.017
10. Andrews‐Todd, J. , R. J. Mislevy , M. LaMar , and S. de Klerk . 2021. “Virtual Performance‐Based Assessments.” In Computational Psychometrics: New Methodologies for a New Generation of Digital Learning and Assessment: With Examples in R and Python, edited by A. A. von Davier , R. J. Mislevy , and J. Hao , 45–60. Springer International Publishing. 10.1007/978-3-030-74394-9_4. doi:10.1007/978-3-030-74394-9_4
11. Andrikopoulos, D. , G. Vassiliou , P. Fatouros , C. Tsirmpas , A. Pehlivanidis , and C. Papageorgiou . 2024. “Machine Learning‐Enabled Detection of Attention‐Deficit/Hyperactivity Disorder With Multimodal Physiological Data: A Case‐Control Study.” BMC Psychiatry 24: 547. 10.1186/s12888-024-05987-7.39103819 PMC11302198 doi:10.1186/s12888-024-05987-7 PubMed
12. Angers, K. , P. Gu , C. A. Lasagna , et al. 2024. “The Relationship of Neurocognitive and Social Cognitive Performance to Social Competence and Appropriateness on a Performance‐Based Social Skills Assessment in Individuals With Psychosis and Unaffected Controls.” Journal of Psychiatric Research 179: 15–20. 10.1016/j.jpsychires.2024.08.042.39222550 doi:10.1016/j.jpsychires.2024.08.042 PubMed
13. Aspinwall, L. G. 2004. “Dealing With Adversity: Self‐Regulation, Coping, Adaptation, and Health.” In Applied Social Psychology, 3–27. Blackwell Publishing.
14. Ates, H. C. , C. Ates , and C. Dincer . 2024. “Stress Monitoring With Wearable Technology and AI.” Nature Electronics 7, no. 2: 98–99. 10.1038/s41928-024-01128-w. doi:10.1038/s41928-024-01128-w
15. Aubrey, S. 2011. “Facilitating Interaction in East Asian EFL Classrooms: Increasing studentsʼ Willingness to Communicate.” Language Education in Asia 2, no. 2: 237–245.
16. Badr, Y. , F. Al‐Shargie , U. Tariq , F. Babiloni , F. Al‐Mughairbi , and H. Al‐Nashash . 2023. “Mental Stress Detection and Mitigation Using Machine Learning and Binaural Beat Stimulation.” In 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 1–5. IEEE. 10.1109/EMBC40787.2023.10340673.38083737 doi:10.1109/EMBC40787.2023.10340673 PubMed
17. Barsalou, L. W. 2008. “Grounded Cognition.” Annual Review of Psychology 59: 617–645. 10.1146/annurev.psych.59.103006.093639.17705682 doi:10.1146/annurev.psych.59.103006.093639 PubMed
18. Bateni, P. , and L. Sigal . 2022. “Real‐Time Monitoring of User Stress, Heart Rate and Heart Rate Variability on Mobile Devices.” arXiv. 10.48550/arXiv.2210.01791. doi:10.48550/arXiv.2210.01791
19. Bauer, R. M. 2017. “Computer‐Assisted Assessment.” In The SAGE Encyclopedia of Abnormal and Clinical Psychology, vol. 7, edited by A. Wenzel , 806–806. SAGE Publications, Inc. 10.4135/9781483365817.n309. doi:10.4135/9781483365817.n309
20. Bauer, R. M. , G. L. Iverson , A. N. Cernich , L. M. Binder , R. M. Ruff , and R. I. Naugle . 2012. “Computerized Neuropsychological Assessment Devices: Joint Position Paper of the American Academy of Clinical Neuropsychology and the National Academy of Neuropsychology.” Archives of Clinical Neuropsychology 27, no. 3: 362–373. 10.1093/arclin/acs027.22382386 PMC3499090 doi:10.1093/arclin/acs027 PubMed
21. Bell, I. H. , J. Nicholas , M. Alvarez‐Jimenez , A. Thompson , and L. Valmaggia . 2020. “Virtual Reality as a Clinical Tool in Mental Health Research and Practice.” Dialogues in Clinical Neuroscience 22, no. 2: 169–177. 10.31887/DCNS.2020.22.2/lvalmaggia.32699517 PMC7366939 doi:10.31887/DCNS.2020.22.2/lvalmaggia PubMed
22. Birnbaum, M. L. , P. Kulkarni , A. V. Meter , et al. 2020. “Utilizing Machine Learning on Internet Search Activity to Support the Diagnostic Process and Relapse Detection in Young Individuals With Early Psychosis: Feasibility Study.” JMIR Mental Health 7, no. 9: e19348. 10.2196/19348.32870161 PMC7492982 doi:10.2196/19348 PubMed
23. Brandão, T. , R. Brites , J. Hipólito , and O. Nunes . 2023. “Emotion Goals, Emotion Regulation, and Mental Health: A Mediational Hypothesis.” Clinical Psychologist 27, no. 3: 290–301. 10.1080/13284207.2023.2214312. doi:10.1080/13284207.2023.2214312
24. Broch‐Due, I. , H. L. Kjærstad , L. V. Kessing , and K. Miskowiak . 2018. “Subtle Behavioural Responses During Negative Emotion Reactivity and Down‐Regulation in Bipolar Disorder: A Facial Expression and Eye‐Tracking Study.” Psychiatry Research 266: 152–159. 10.1016/j.psychres.2018.04.054.29864615 doi:10.1016/j.psychres.2018.04.054 PubMed
25. Brown, E. 2017. “Can Computers Detect Emotion and Predict How People Will React?” https://www.zdnet.com/article/can‐computers‐detect‐emotions‐and‐determine‐whether‐people‐believe‐what‐they‐say/#google_vignette.
26. Bruno, E. , E. Martz , L. Weiner , A. Greco , and N. Vanello . 2023. “Speech Signal Analysis as an Aid to Clinical Diagnosis and Assessment of Mental Health Disorders.” Biomedical Signal Processing and Control 85: 104854. 10.1016/j.bspc.2023.104854. doi:10.1016/j.bspc.2023.104854
27. Campbell, L. E. , K. L. McCabe , J. L. Melville , P. A. Strutt , and U. Schall . 2015. “Social Cognition Dysfunction in Adolescents With 22q11.2 Deletion Syndrome (Velo‐Cardio‐Facial Syndrome): Relationship With Executive Functioning and Social Competence/Functioning.” Journal of Intellectual Disability Research 59, no. 9: 845–859. 10.1111/jir.12183.25726953 doi:10.1111/jir.12183 PubMed
28. Centers for Disease Control and Prevention . 2024. “Youth Risk Behavior Survey Data Summary & Trends Report: 2013–2023.”
29. Cerasuolo, M. , S. De Marco , R. Nappo , R. Simeoli , and A. Rega . 2024. “The Potential of Virtual Reality to Improve Diagnostic Assessment by Boosting Autism Spectrum Disorder Traits: A Systematic Review.” Advances in Neurodevelopmental Disorders 9: 1–22. 10.1007/s41252-024-00413-1. doi:10.1007/s41252-024-00413-1
30. Chandra Guntuku, S. , A. Buffone , K. Jaidka , J. C. Eichstaedt , and L. H. Ungar . 2019. “Understanding and Measuring Psychological Stress Using Social Media.” In Proceedings of the International AAAI Conference on Web and Social Media, vol. 13, 214–225. Association for the Advancement of Artificial Intelligence (AAAI). 10.1609/icwsm.v13i01.3223. doi:10.1609/icwsm.v13i01.3223
31. Chen, D. , P. Wang , X. Zhang , et al. 2025. “Comparative Efficacy of MultiModal AI Methods in Screening for Major Depressive Disorder: Machine Learning Model Development Predictive Pilot Study.” JMIR Formative Research 9: e56057. 10.2196/56057.40446148 PMC12143584 doi:10.2196/56057 PubMed
32. Cherkassky, V. , and S. Dhar . 2015. “Interpretation of Black‐Box Predictive Models.” In Measures of Complexity: Festschrift for Alexey Chervonenkis, edited by V. Vovk , H. Papadopoulos , and A. Gammerman , 267–286. Springer International Publishing. 10.1007/978-3-319-21852-6_19. doi:10.1007/978-3-319-21852-6_19
33. Collie, R. J. 2020. “Social and Emotional Competence: Advancing Understanding of What, for Whom, and When.” Educational Psychology 40, no. 6: 663–665. 10.1080/01443410.2020.1775936. doi:10.1080/01443410.2020.1775936
34. Compton, M. T. , A. Lunden , S. D. Cleary , et al. 2018. “The Aprosody of Schizophrenia: Computationally Derived Acoustic Phonetic Underpinnings of Monotone Speech.” Schizophrenia Research 197: 392–399. 10.1016/j.schres.2018.01.007.29449060 PMC6087691 doi:10.1016/j.schres.2018.01.007 PubMed
35. Connor, L. T. , and A. Maeir . 2011. “Putting Executive Performance in a Theoretical Context.” OTJR: Occupational Therapy Journal of Research 31, no. 1_suppl: S3–S7. 10.3928/15394492-20101108-02.24650261 doi:10.3928/15394492-20101108-02 PubMed
36. Corsi, E. , V. Cardi , S. Sowden , et al. 2021. “Socio‐Cognitive Processing in People With Eating Disorders: Computerized Tests of Mentalizing, Empathy and Imitation Skills.” International Journal of Eating Disorders 54, no. 8: 1509–1518. 10.1002/eat.23556.34056730 PMC8453969 doi:10.1002/eat.23556 PubMed
37. Dai, Y. , Z. Yan , J. Cheng , X. Duan , and G. Wang . 2023. “Analysis of Multimodal Data Fusion From an Information Theory Perspective.” Information Sciences 623: 164–183. 10.1016/j.ins.2022.12.014. doi:10.1016/j.ins.2022.12.014
38. Danousis, M. , and C. Goumopoulos . 2023. “A Machine‐Learning‐Based Motor and Cognitive Assessment Tool Using in‐Game Data From the GAME2AWE Platform.” Informatics 10, no. 3: 3. 10.3390/informatics10030059. doi:10.3390/informatics10030059
39. Dawson, D. R. , N. D. Anderson , P. Burgess , E. Cooper , K. M. Krpan , and D. T. Stuss . 2009. “Further Development of the Multiple Errands Test: Standardized Scoring, Reliability, and Ecological Validity for the Baycrest Version.” Archives of Physical Medicine and Rehabilitation 90, no. 11 Suppl: S41–S51. 10.1016/j.apmr.2009.07.012.19892074 doi:10.1016/j.apmr.2009.07.012 PubMed
40. De Angel, V. , S. Lewis , K. White , et al. 2022. “Digital Health Tools for the Passive Monitoring of Depression: A Systematic Review of Methods.” npj Digital Medicine 5, no. 1: 3. 10.1038/s41746-021-00548-8.35017634 PMC8752685 doi:10.1038/s41746-021-00548-8 PubMed
41. de Klerk, S. , T. J. H. M. Eggen , and B. P. Veldkamp . 2016. “A Methodology for Applying Students' Interactive Task Performance Scores From a Multimedia‐Based Performance Assessment in a Bayesian Network.” Computers in Human Behavior 60: 264–279. 10.1016/j.chb.2016.02.071. doi:10.1016/j.chb.2016.02.071
42. De Los Reyes, A. , T. M. Augenstein , M. Wang , et al. 2015. “The Validity of the Multi‐Informant Approach to Assessing Child and Adolescent Mental Health.” Psychological Bulletin 141, no. 4: 858–900. 10.1037/a0038498.25915035 PMC4486608 doi:10.1037/a0038498 PubMed
43. Deb, K. , H. De , S. S. Chatterjee , and A. Pal . 2022. “Studying Borderline Personality Disorder Using Machine Learning.” In 2022 16th International Conference on Ubiquitous Information Management and Communication (IMCOM), 1–6. IEEE. 10.1109/IMCOM53663.2022.9721800. doi:10.1109/IMCOM53663.2022.9721800
44. DesRuisseaux, L. A. , M. Gereau Mora , and Y. Suchy . 2025. “Computerized Assessment of Executive Functioning: Validation of the CNS Vital Signs Executive Functioning Scores in a Sample of Community‐Dwelling Older Adults.” Clinical Neuropsychologist 39, no. 1: 159–181. 10.1080/13854046.2024.2354953.38763890 doi:10.1080/13854046.2024.2354953 PubMed
45. DeVellis, R. F. , and C. T. Thorpe . 2021. Scale Development: Theory and Applications. Sage publications.
46. Devlin, J. , M.‐W. Chang , K. Lee , and K. Toutanova . 2018. “BERT: Pre‐Training of Deep Bidirectional Transformers for Language Understanding.” (No. arXiv:1810.04805; Version 1) arXiv 10.48550/arXiv.1810.04805. doi:10.48550/arXiv.1810.04805
47. Devlin, J. , M.‐W. Chang , K. Lee , and K. Toutanova . 2019. “BERT: Pre‐Training of Deep Bidirectional Transformers for Language Understanding.” In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), edited by J. Burstein , C. Doran , and T. Solorio , 4171–4186. Association for Computational Linguistics. 10.18653/v1/N19-1423. doi:10.18653/v1/N19-1423
48. Ding, Z. , J. Chen , B.‐L. Zhong , C.‐L. Liu , and Z.‐T. Liu . 2025. “Emotional Stimulated Speech‐Based Assisted Early Diagnosis of Depressive Disorders Using Personality‐Enhanced Deep Learning.” Journal of Affective Disorders 376: 177–188. 10.1016/j.jad.2025.01.136.39914753 doi:10.1016/j.jad.2025.01.136 PubMed
49. D'Mello, S. , A. Kappas , and J. Gratch . 2018. “The Affective Computing Approach to Affect Measurement.” Emotion Review 10, no. 2: 174–183. 10.1177/1754073917696583. doi:10.1177/1754073917696583
50. Dong, L. , and Y. Dong . 2001. “The Performance,Reasons and Countermeasures of Sub‐Health.” Medicine and Philosophy 12: 54–55.
51. Espy, K. A. 1997. “The Shape School: Assessing Executive Function in Preschool Children.” Developmental Neuropsychology 13, no. 4: 495–499. 10.1080/87565649709540690. doi:10.1080/87565649709540690
52. Fang, X. , M. Rychlowska , and J. Lange . 2022. “Cross‐Cultural and Inter‐Group Research on Emotion Perception.” Journal of Cultural Cognitive Science 6: 1–7. 10.1007/s41809-022-00102-2. doi:10.1007/s41809-022-00102-2
53. Fantozzi, P. , L. Billeci , P. Muratori , et al. 2024. “Autistic Traits and Perspective Taking in Youths With Anorexia Nervosa: An Exploratory Clinical and Eye Tracking Study.” Journal of Eating Disorders 12: 116. 10.1186/s40337-024-01075-z.39143647 PMC11325632 doi:10.1186/s40337-024-01075-z PubMed
54. Farhoumandi, N. , S. Mollaey , S. Heysieattalab , M. Zarean , and R. Eyvazpour . 2021. “Facial Emotion Recognition Predicts Alexithymia Using Machine Learning.” Computational Intelligence and Neuroscience 2021: 2053795. 10.1155/2021/2053795.34621306 PMC8492233 doi:10.1155/2021/2053795 PubMed
55. Fazil, M. , A. Rísquez , and C. Halpin . 2024. “A Novel Deep Learning Model for Student Performance Prediction Using Engagement Data.” Journal of Learning Analytics 11, no. 2: 2. 10.18608/jla.2024.7985. doi:10.18608/jla.2024.7985
56. Feldon, D. F. , M. A. Maher , M. Hurst , and B. Timmerman . 2015. “Faculty Mentors', Graduate Students', and Performance‐Based Assessments of Students' Research Skill Development.” American Educational Research Journal 52, no. 2: 334–370.
57. Fiebig, A. , P. Jordan , and C. C. Moshona . 2020. “Assessments of Acoustic Environments by Emotions – The Application of Emotion Theory in Soundscape.” Frontiers in Psychology 11: 573041. 10.3389/fpsyg.2020.573041.33329214 PMC7718000 doi:10.3389/fpsyg.2020.573041 PubMed
58. Finze, N. , D. Jechle , S. Faußer , and H. Gewald . 2024. “How Are we Doing Today? Using Natural Speech Analysis to Assess Older Adults' Subjective Well‐Being.” Business & Information Systems Engineering 66, no. 3: 321–334. 10.1007/s12599-024-00877-4. doi:10.1007/s12599-024-00877-4
59. Fitts, W. , L. Massimo , N. Lim , M. Grossman , and N. Dahodwala . 2016. “Computerized Assessment of Goal‐Directed Behavior in Parkinson's Disease.” Journal of Clinical and Experimental Neuropsychology 38, no. 9: 1015–1025. 10.1080/13803395.2016.1184232.27270271 PMC4979569 doi:10.1080/13803395.2016.1184232 PubMed
60. Fletcher, J. M. , and J. Miciak . 2023. “Assessment of Specific Learning Disabilities and Intellectual Disabilities.” Assessment 31, no. 1: 53–74. 10.1177/10731911231194992.37671726 PMC10795803 doi:10.1177/10731911231194992 PubMed
61. Folkman, S. 2013. “Stress: Appraisal and Coping.” In Encyclopedia of Behavioral Medicine, 1913–1915. Springer. 10.1007/978-1-4419-1005-9_215. doi:10.1007/978-1-4419-1005-9_215
62. Gawęda, Ł. , J. Kowalski , A. Aleksandrowicz , P. Bagrowska , M. Dąbkowska , and R. Pionke‐Ubych . 2024. “A Systematic Review of Performance‐Based Assessment Studies on Cognitive Biases in Schizophrenia Spectrum Psychoses and Clinical High‐Risk States: A Summary of 40 Years of Research.” Clinical Psychology Review 108: 102391. 10.1016/j.cpr.2024.102391.38301343 doi:10.1016/j.cpr.2024.102391 PubMed
63. Goldenberg, A. 2024. “What Makes Groups Emotional?” Perspectives on Psychological Science 19, no. 2: 489–502. 10.1177/17456916231179154.37493141 doi:10.1177/17456916231179154 PubMed
64. Green, M. F. , K. Llerena , and R. S. Kern . 2015. “The “Right Stuff” Revisited: What Have we Learned About the Determinants of Daily Functioning in Schizophrenia?” Schizophrenia Bulletin 41, no. 4: 781–785. 10.1093/schbul/sbv018.25750248 PMC4466185 doi:10.1093/schbul/sbv018 PubMed
65. Greenwood, K. E. , R. Morris , V. Smith , A.‐M. Jones , D. Pearman , and T. Wykes . 2016. “Virtual Shopping: A Viable Alternative to Direct Assessment of Real Life Function?” Schizophrenia Research 172, no. 1: 206–210. 10.1016/j.schres.2016.02.029.26961185 doi:10.1016/j.schres.2016.02.029 PubMed
66. Gurevitch, J. , J. Koricheva , S. Nakagawa , and G. Stewart . 2018. “Meta‐Analysis and the Science of Research Synthesis.” Nature 555, no. 7695: 175–182. 10.1038/nature25753.29517004 doi:10.1038/nature25753 PubMed
67. Harshit, N. S. , N. K. Sahu , and H. R. Lone . 2024. “Eyes Speak Louder: Harnessing Deep Features From Low‐Cost Camera Video for Anxiety Detection.” In Proceedings of the Workshop on Body‐Centric Computing Systems, 23–28. ACM. 10.1145/3662009.3662021. doi:10.1145/3662009.3662021
68. Hemtanon, S. , S. Aekwarangkoon , and N. Kittphattanabawon . 2020. “Behavior Features for Automatic Detection of Depression From Facebook Users.” In Frontiers in Artificial Intelligence and Applications, edited by A. J. Tallón‐Ballesteros and C.‐H. Chen , 12–20. IOS Press. 10.3233/FAIA200761. doi:10.3233/FAIA200761
69. Henriksen, I. O. , I. Ranøyen , M. S. Indredavik , and F. Stenseng . 2017. “The Role of Self‐Esteem in the Development of Psychiatric Problems: A Three‐Year Prospective Study in a Clinical Sample of Adolescents.” Child and Adolescent Psychiatry and Mental Health 11: 68. 10.1186/s13034-017-0207-y.29299058 PMC5747942 doi:10.1186/s13034-017-0207-y PubMed
70. Herrman, H. 2016. “Improving the Mental Health of Women and Girls: Psychiatrists as Partners for Change.” World Psychiatry 15, no. 2: 190–191. 10.1002/wps.20316.27265719 PMC4911763 doi:10.1002/wps.20316 PubMed
71. Hodges, B. D. 2021. “Performance‐Based Assessment in the 21st Century: When the Examiner Is a Machine.” Perspectives on Medical Education 10, no. 1: 3–5. 10.1007/s40037-020-00647-4.33428164 PMC7809079 doi:10.1007/s40037-020-00647-4 PubMed
72. Hoffmeister, J. R. , B. R. Robison , C. T. Copeland , C. I. Prodan , J. G. Scott , and J. M. Glenn . 2025. “Detecting Early Stages of Alzheimer's Disease Using a Web‐Based Cognitive Battery.” GeroScience 47, no. 3: 5355–5363. 10.1007/s11357-024-01496-3.39739256 PMC12181539 doi:10.1007/s11357-024-01496-3 PubMed
73. Huang, J. , Y. Zhao , Z. Tian , et al. 2023. “Evaluating the Clinical Utility of Speech Analysis and Machine Learning in Schizophrenia: A Pilot Study.” Computers in Biology and Medicine 164: 107359. 10.1016/j.compbiomed.2023.107359.37591160 doi:10.1016/j.compbiomed.2023.107359 PubMed
74. Huang, Y.‐P. , A. Singh , S. Chen , F.‐J. Sun , C.‐R. Huang , and S.‐I. Liu . 2019. “Validity of a Novel Touch Screen Tablet‐Based Assessment for Mild Cognitive Impairment and Probable AD in Older Adults.” Assessment 26, no. 8: 1540–1553. 10.1177/1073191117748395.29251514 doi:10.1177/1073191117748395 PubMed
75. Huber, M. , J. A. Knottnerus , L. Green , et al. 2011. “How Should We Define Health?” British Medical Journal 343: d4163. 10.1136/bmj.d4163.21791490 doi:10.1136/bmj.d4163 PubMed
76. Huppert, F. A. , and T. T. C. So . 2013. “Flourishing Across Europe: Application of a New Conceptual Framework for Defining Well‐Being.” Social Indicators Research 110, no. 3: 837–861. 10.1007/s11205-011-9966-7.23329863 PMC3545194 doi:10.1007/s11205-011-9966-7 PubMed
77. Iasonidou, E. , E. Constantinou , N. Ferreira , and M. Koushiou . 2023. “Emotional Responding and Distress Tolerance in Women at High vs. Low Risk for Eating Disorders in Response to Physical and Cognitive Stress. Mediterranean.” Journal of Clinical Psychology 11, no. 3: 3. 10.13129/2282-1619/mjcp-3796. doi:10.13129/2282-1619/mjcp-3796
78. Ibrahim, N. , F. ElOraby , M. Gamal , A. Elmougy , and S. Abdennadher . 2023. “The Gamification of Psychological Tests for the Detection of Cognitive Dysfunction in Young Adults.” In 2023 IEEE 11th International Conference on Serious Games and Applications for Health (SeGAH), 1–8. IEEE. 10.1109/SeGAH57547.2023.10253812. doi:10.1109/SeGAH57547.2023.10253812
79. Iceta, S. , C. Rodrigue , M. Legendre , et al. 2021. “Cognitive Function in Binge Eating Disorder and Food Addiction: A Systematic Review and Three‐Level Meta‐Analysis.” Progress in Neuro‐Psychopharmacology and Biological Psychiatry 111: 110400. 10.1016/j.pnpbp.2021.110400.34256024 doi:10.1016/j.pnpbp.2021.110400 PubMed
80. Institute for Health Metrics and Evaluation (IHME) . 2021. “GBD Results Institute for Health Metrics and Evaluation.” https://vizhub.healthdata.org/gbd‐results.
81. Islam, M. R. , M. A. Kabir , A. Ahmed , A. R. M. Kamal , H. Wang , and A. Ulhaq . 2018. “Depression Detection From Social Network Data Using Machine Learning Techniques.” Health Information Science and Systems 6: 8. 10.1007/s13755-018-0046-0.30186594 PMC6111060 doi:10.1007/s13755-018-0046-0 PubMed
82. Jiang, Z. , S. Seyedi , E. Griner , et al. 2024. “Multimodal Mental Health Digital Biomarker Analysis From Remote Interviews Using Facial, Vocal, Linguistic, and Cardiovascular Patterns.” IEEE Journal of Biomedical and Health Informatics 28, no. 3: 1680–1691. 10.1109/JBHI.2024.3352075.38198249 PMC10986761 doi:10.1109/JBHI.2024.3352075 PubMed
83. Jiao, H. , Q. He , and B. P. Veldkamp . 2021. “Process Data in Educational and Psychological Measurement.” Frontiers in Psychology 12: 793399. 10.3389/fpsyg.2021.793399.34925194 PMC8677654 doi:10.3389/fpsyg.2021.793399 PubMed
84. Jing, C. , X. Liu , N. Zhao , and T. Zhu . 2019. “Different Performances of Speech and Natural Gait in Identifying Anxiety and Depression.” In Human Centered Computing, edited by D. Milošević , Y. Tang , and Q. Zu , vol. 11956, 200–210. Springer International Publishing. 10.1007/978-3-030-37429-7_20. doi:10.1007/978-3-030-37429-7_20
85. Johns Hopkins Bloomberg School of Public Health & United Nations Children's Fund . 2022. “On My Mind: How Adolescents Experience and Perceive Mental Health Around the World.”
86. Jyotsna, C. , J. Amudha , A. Ram , and G. Nollo . 2023. “IntelEye: An Intelligent Tool for the Detection of Stressful State based on Eye Gaze Data While Watching Video.” Procedia Computer Science 218: 1270–1279. 10.1016/j.procs.2023.01.105. doi:10.1016/j.procs.2023.01.105
87. Keleman, A. A. , R. M. Bollinger , J. Rodakowski , et al. 2024. “Exploring the Remote Administration of a Performance‐Based Functional Assessment.” Journal of Applied Gerontology 44: 981–993. 10.1177/07334648241292968.39449317 PMC12018588 doi:10.1177/07334648241292968 PubMed
88. Keller, S. 2020. “What Does Mental Health Have to Do With Well‐Being?” Bioethics 34, no. 3: 228–234. 10.1111/bioe.12702.31782815 doi:10.1111/bioe.12702 PubMed
89. Kelley, S. W. , C. N. Mhaonaigh , L. Burke , R. Whelan , and C. M. Gillan . 2022. “Machine Learning of Language Use on Twitter Reveals Weak and Non‐Specific Predictions.” npj Digital Medicine 5, no. 1: 35. 10.1038/s41746-022-00576-y.35338248 PMC8956571 doi:10.1038/s41746-022-00576-y PubMed
90. Keyes, C. L. M. 2002. “The Mental Health Continuum: From Languishing to Flourishing in Life.” Journal of Health and Social Behavior 43, no. 2: 207. 10.2307/3090197.12096700 doi:10.2307/3090197 PubMed
91. Keyes, C. L. M. 2013. Mental Well‐Being: International Contributions to the Study of Positive Mental Health. Springer Netherlands. 10.1007/978-94-007-5195-8. doi:10.1007/978-94-007-5195-8
92. Kho, J. J. , S. Song , S. M. X. Tan , et al. 2025. “Leveraging Computational Linguistics and Machine Learning for Detection of Ultra‐High Risk of Mental Health Disorders in Youths.” Schizophrenia 11: 98. 10.1038/s41537-025-00649-3.40664678 PMC12264269 doi:10.1038/s41537-025-00649-3 PubMed
93. Kim, S. Y. , H. Park , H. Kim , J. Kim , and K. Seo . 2022. “Technostress Causes Cognitive Overload in High‐Stress People: Eye Tracking Analysis in a Virtual Kiosk Test.” Information Processing & Management 59, no. 6: 103093. 10.1016/j.ipm.2022.103093.36119755 PMC9464304 doi:10.1016/j.ipm.2022.103093 PubMed
94. Kiss, E. , O. R. de Oliveira , E. Wittmann , Z. Herczegh , and K. Kapornai . 2024. “The Effect of Psychological and Behavioral Problems on the Quality of Life of Children and Adolescents Based on Self‐Reports and Proxy Reports.” Health and Quality of Life Outcomes 22: 84. 10.1186/s12955-024-02299-y.39379992 PMC11463092 doi:10.1186/s12955-024-02299-y PubMed
95. Kjærstad, H. L. , K. S. Hellum , N. H. Haslum , et al. 2022. “Assessment of the Validity and Feasibility of a Novel Virtual Reality Test of Emotion Regulation in Patients With Bipolar Disorder and Their Unaffected Relatives.” Journal of Affective Disorders 318: 217–223. 10.1016/j.jad.2022.09.004.36089075 doi:10.1016/j.jad.2022.09.004 PubMed
96. Klanker, M. , M. Feenstra , and D. Denys . 2013. “Dopaminergic Control of Cognitive Flexibility in Humans and Animals.” Frontiers in Neuroscience 7: 201. 10.3389/fnins.2013.00201.24204329 PMC3817373 doi:10.3389/fnins.2013.00201 PubMed
97. Knapp, P. 2021. “Iterative and Comprehensive Mental Health Assessment and Treatment Planning: The Mental Health Dashboard.” Pediatric Medicine 4: 24. 10.21037/pm-20-72. doi:10.21037/pm-20-72
98. Koban, L. , P. J. Gianaros , H. Kober , and T. D. Wager . 2021. “The Self in Context: Brain Systems Linking Mental and Physical Health.” Nature Reviews. Neuroscience 22, no. 5: 309–322. 10.1038/s41583-021-00446-8.33790441 PMC8447265 doi:10.1038/s41583-021-00446-8 PubMed
99. König, A. , N. Linz , R. Zeghari , et al. 2019. “Detecting Apathy in Older Adults With Cognitive Disorders Using Automatic Speech Analysis.” Journal of Alzheimer's Disease 69, no. 4: 1183–1193. 10.3233/JAD-181033.31127764 doi:10.3233/JAD-181033 PubMed
100. Kuppens, P. , and P. Verduyn . 2017. “Emotion Dynamics.” Current Opinion in Psychology 17: 22–26. 10.1016/j.copsyc.2017.06.004.28950968 doi:10.1016/j.copsyc.2017.06.004 PubMed
101. Kusuma, K. , M. Larsen , J. C. Quiroz , et al. 2022. “The Performance of Machine Learning Models in Predicting Suicidal Ideation, Attempts, and Deaths: A Meta‐Analysis and Systematic Review.” Journal of Psychiatric Research 155: 579–588. 10.1016/j.jpsychires.2022.09.050.36206602 doi:10.1016/j.jpsychires.2022.09.050 PubMed
102. Lau, C. , X. Zhu , and W.‐Y. Chan . 2023. “Automatic Depression Severity Assessment With Deep Learning Using Parameter‐Efficient Tuning.” Frontiers in Psychiatry 14: 1160291. 10.3389/fpsyt.2023.1160291.37398577 PMC10308283 doi:10.3389/fpsyt.2023.1160291 PubMed
103. LeCun, Y. , Y. Bengio , and G. Hinton . 2015. “Deep Learning.” Nature 521, no. 7553: 436–444. 10.1038/nature14539.26017442 doi:10.1038/nature14539 PubMed
104. Lenehan, M. E. , M. J. Summers , N. L. Saunders , J. J. Summers , and J. C. Vickers . 2016. “Does the Cambridge Automated Neuropsychological Test Battery (CANTAB) Distinguish Between Cognitive Domains in Healthy Older Adults?” Assessment 23, no. 2: 163–172. 10.1177/1073191115581474.25882162 doi:10.1177/1073191115581474 PubMed
105. Leontyev, A. , T. Yamauchi , and M. Razavi . 2019. “Machine Learning Stop Signal Test (ML‐SST): ML‐Based Mouse Tracking Enhances Adult ADHD Diagnosis.” In 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), 1–5. Cambridge. 10.1109/ACIIW.2019.8925073. doi:10.1109/ACIIW.2019.8925073
106. Li, J. , S. Cai , Y. Liu , et al. 2024. “Mapping Adolescent Mental Well‐Being—30 PLADs, China, 2019.” China CDC Weekly 6, no. 29: 703–707. 10.46234/ccdcw2024.159.39050017 PMC11264050 doi:10.46234/ccdcw2024.159 PubMed
107. Lievens, F. , and B. De Soete . 2012. “Simulations.” In The Oxford Handbook of Personnel Assessment and Selection, edited by N. Schmitt , 383–410. Oxford University Press. 10.1093/oxfordhb/9780199732579.013.0017. doi:10.1093/oxfordhb/9780199732579.013.0017
108. Lin, G.‐H. , C.‐T. Wu , Y.‐J. Huang , et al. 2018. “A Reliable and Valid Assessment of Sustained Attention for Patients With Schizophrenia: The Computerized Digit Vigilance Test.” Archives of Clinical Neuropsychology 33, no. 2: 227–237. 10.1093/arclin/acx064.28981615 doi:10.1093/arclin/acx064 PubMed
109. Liu, I. , Q. Zhong , F. Liu , et al. 2022. “Assessing Mental Health During COVID‐19 Lockdown: A Smartphone‐Based Multimodal Emotion Recognition Approach.” In Proceedings of the Tenth International Symposium of Chinese CHI, 262–269. ACM. 10.1145/3565698.3565795. doi:10.1145/3565698.3565795
110. Liu, P. , W. Yuan , J. Fu , Z. Jiang , H. Hayashi , and G. Neubig . 2023. “Pre‐Train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing.” ACM Computing Surveys 55, no. 9: 195. 10.1145/3560815. doi:10.1145/3560815
111. Liu, S. , C. Lu , S. Alghowinem , L. Gotoh , C. Breazeal , and H. W. Park . 2022. “Explainable AI for Suicide Risk Assessment Using Eye Activities and Head Gestures.” In Artificial Intelligence in HCI, edited by H. Degen and S. Ntoa , 161–178. Springer International Publishing. 10.1007/978-3-031-05643-7_11. doi:10.1007/978-3-031-05643-7_11
112. Llanes, R. G. , and R. Reyes . 2022. “Stress Detection in Video Feed: Utilizing Facial Action Units as Indicators in Various Machine Learning Algorithms.” In 2022 IEEE 4th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS), 236–240. IEEE. 10.1109/ECBIOS54627.2022.9945040. doi:10.1109/ECBIOS54627.2022.9945040
113. Lobato‐Camacho, F. J. , J. C. López , and J. P. Vargas . 2024. “Virtual Reality Evaluation of the Spatial Learning Strategies in Gamers.” Multimedia Tools and Applications 83, no. 13: 38127–38144. 10.1007/s11042-023-17177-w. doi:10.1007/s11042-023-17177-w
114. Lu, S. , X. Shi , M. Li , et al. 2021. “Semi‐Supervised Random Forest Regression Model Based on Co‐Training and Grouping With Information Entropy for Evaluation of Depression Symptoms Severity.” Mathematical Biosciences and Engineering 18, no. 4: mbe‐18‐04‐233. 10.3934/mbe.2021233.34198455 doi:10.3934/mbe.2021233 PubMed
115. Lumsden, J. , E. A. Edwards , N. S. Lawrence , D. Coyle , and M. R. Munafò . 2016. “Gamification of Cognitive Assessment and Cognitive Training: A Systematic Review of Applications and Efficacy.” JMIR Serious Games 4, no. 2: e11. 10.2196/games.5888.27421244 PMC4967181 doi:10.2196/games.5888 PubMed
116. Luo, J. , Y. Wu , M. Liu , et al. 2024. “Differentiation Between Depression and Bipolar Disorder in Child and Adolescents by Voice Features.” Child and Adolescent Psychiatry and Mental Health 18: 19. 10.1186/s13034-024-00708-0.38287442 PMC10826007 doi:10.1186/s13034-024-00708-0 PubMed
117. MacCann, C. , and R. D. Roberts . 2008. “New Paradigms for Assessing Emotional Intelligence: Theory and Data.” Emotion 8, no. 4: 540–551. 10.1037/a0012746.18729584 doi:10.1037/a0012746 PubMed
118. Männiste, T. , M. Pedaste , and R. Schimanski . 2019. “Situational Judgment Test for Measuring Military Tactical Decision‐Making Skills.” Military Psychology 31, no. 6: 462–473. 10.1080/08995605.2019.1664366. doi:10.1080/08995605.2019.1664366
119. Marín‐Morales, J. , L. A. Carrasco‐Ribelles , M. Alcañiz , and I. A. C. Giglioli . 2021. “Applying Machine Learning to a Virtual Serious Game for Neuropsychological Assessment.” In 2021 IEEE Global Engineering Education Conference (EDUCON), 946–949. IEEE. 10.1109/EDUCON46332.2021.9454138. doi:10.1109/EDUCON46332.2021.9454138
120. Marroquín, B. , H. Tennen , and A. L. Stanton . 2017. “Coping, Emotion Regulation, and Well‐Being: Intrapersonal and Interpersonal Processes.” In The Happy Mind: Cognitive Contributions to Well‐Being, edited by M. D. Robinson and M. Eid , 253–274. Springer International Publishing. 10.1007/978-3-319-58763-9_14. doi:10.1007/978-3-319-58763-9_14
121. Martinsone, B. , I. Stokenberga , I. Damberga , et al. 2022. “Adolescent Social Emotional Skills, Resilience and Behavioral Problems During the COVID‐19 Pandemic: A Longitudinal Study in Three European Countries.” Frontiers in Psychiatry 13: 942692. 10.3389/fpsyt.2022.942692.35978848 PMC9376252 doi:10.3389/fpsyt.2022.942692 PubMed
122. Mayer, R. E. , and L. Fiorella . 2014. “Principles for Reducing Extraneous Processing in Multimedia Learning: Coherence, Signaling, Redundancy, Spatial Contiguity, and Temporal Contiguity Principles.” In The Cambridge Handbook of Multimedia Learning, edited by R. E. Mayer , 2nd ed., 279–315. Cambridge University Press. 10.1017/CBO9781139547369.015. doi:10.1017/CBO9781139547369.015
123. McArthur, B. A. , T. A. Burke , S. L. Connolly , et al. 2019. “A Longitudinal Investigation of Cognitive Self‐Schemas Across Adolescent Development.” Journal of Youth and Adolescence 48, no. 3: 635. 10.1007/s10964-018-00981-1.30612293 PMC6391197 doi:10.1007/s10964-018-00981-1 PubMed
124. McGinnis, E. W. , J. Scism , J. Hruschak , et al. 2021. “Digital Phenotype for Childhood Internalizing Disorders: Less Positive Play and Promise for a Brief Assessment Battery.” IEEE Journal of Biomedical and Health Informatics 25, no. 8: 3176–3184. 10.1109/JBHI.2021.3053846.33481724 PMC8384142 doi:10.1109/JBHI.2021.3053846 PubMed
125. McIntyre, J. C. , S. Wickham , B. Barr , and R. P. Bentall . 2018. “Social Identity and Psychosis: Associations and Psychological Mechanisms.” Schizophrenia Bulletin 44, no. 3: 681–690. 10.1093/schbul/sbx110.28981888 PMC5890464 doi:10.1093/schbul/sbx110 PubMed
126. McIntyre, R. S. , D. S. Cha , J. K. Soczynska , et al. 2013. “Cognitive Deficits and Functional Outcomes in Major Depressive Disorder: Determinants, Substrates, and Treatment Interventions.” Depression and Anxiety 30, no. 6: 515–527. 10.1002/da.22063.23468126 doi:10.1002/da.22063 PubMed
127. Mejía, C. , A. Herrera‐Marmolejo , M. Rosero‐Pérez , J. Quimbaya , and J. F. Cardona . 2025. “Design of a Video Game for Assessment of Executive Functions in Deaf and Hearing Children.” Applied Neuropsychology: Child 14, no. 3: 350–357. 10.1080/21622965.2024.2311096.38359416 doi:10.1080/21622965.2024.2311096 PubMed
128. Mislevy, R. J. , L. S. Steinberg , and R. G. Almond . 2003. “On the Structure of Educational Assessments.” Measurement: Interdisciplinary Research and Perspectives 1, no. 1: 3–62. 10.1207/S15366359MEA0101_02. doi:10.1207/S15366359MEA0101_02
129. Moksnes, U. K. , D. G. Byrne , J. Mazanov , and G. A. Espnes . 2010. “Adolescent Stress: Evaluation of the Factor Structure of the Adolescent Stress Questionnaire (ASQ‐N).” Scandinavian Journal of Psychology 51, no. 3: 203–209. 10.1111/j.1467-9450.2009.00803.x.20149144 doi:10.1111/j.1467-9450.2009.00803.x PubMed
130. Moore, R. C. , P. L. Fazeli , T. L. Patterson , et al. 2015. “UPSA‐M: Feasibility and Initial Validity of a Mobile Application of the UCSD Performance‐Based Skills Assessment.” Schizophrenia Research 164, no. 1‐3: 187–192. 10.1016/j.schres.2015.02.014.25790903 PMC4409538 doi:10.1016/j.schres.2015.02.014 PubMed
131. Morein‐Zamir, S. , and B. J. Sahakian . 2010. “Stop‐Signal Task.” In Encyclopedia of Psychopharmacology, edited by I. P. Stolerman , 1285–1285. Springer. 10.1007/978-3-540-68706-1_1120. doi:10.1007/978-3-540-68706-1_1120
132. Moritz, D. J. , S. V. Kasl , and L. F. Berkman . 1995. “Cognitive Functioning and the Incidence of Limitations in Activities of Daily Living in an Elderly Community Sample.” American Journal of Epidemiology 141, no. 1: 41–49. 10.1093/oxfordjournals.aje.a117344.7801965 doi:10.1093/oxfordjournals.aje.a117344 PubMed
133. Murphy, D. 2017. “Philosophy of Psychiatry.” In The Stanford Encyclopedia of Philosophy (Spring 2017), edited by E. N. Zalta . Metaphysics Research Lab, Stanford University. https://plato.stanford.edu/archives/spr2017/entries/psychiatry/.
134. Muszynski, M. , J. Zelazny , J. M. Girard , and L.‐P. Morency . 2020. “Depression Severity Assessment for Adolescents at High Risk of Mental Disorders.” In Proceedings of the … ACM International Conference on Multimodal Interaction, vol. 2020, 70–78. ICMI (Conference). 10.1145/3382507.3418859.33782675 PMC8005296 doi:10.1145/3382507.3418859 PubMed
135. Mutersbaugh, J. , W.‐C. Su , A. Bhat , and A. Gandjbakhche . 2025. “Deep Learning Approaches for Classifying Children With and Without Autism Spectrum Disorder Using Inertial Measurement Unit Hand Tracking Data: Comparative Study.” JMIR Medical Informatics 13: e73440. 10.2196/73440.41428363 PMC12721220 doi:10.2196/73440 PubMed
136. Mutweleli, S. , G. Mwathe , and S. Mundi . 2024. “Scenario‐Based Assessments: Experience From East Africa.” In The Contextualisation of 21st Century Skills, edited by E. Care , M. Giacomazzi , and J. Kabutha Mugo , vol. 11, 135–149. Springer International Publishing. 10.1007/978-3-031-51490-6_9. doi:10.1007/978-3-031-51490-6_9
137. Myruski, S. , J. M. Quintero , S. Denefrio , and T. A. Dennis‐Tiwary . 2019. “Through a Screen Darkly: Use of Computer‐Mediated Communication Predicts Emotional Functioning.” Psychological Reports 123: 2305–2332. 10.1177/0033294119859779.31264919 doi:10.1177/0033294119859779 PubMed
138. Neguţ, A. , S.‐A. Matu , F. A. Sava , and D. David . 2016. “Task Difficulty of Virtual Reality‐Based Assessment Tools Compared to Classical Paper‐And‐Pencil or Computerized Measures: A Meta‐Analytic Approach.” Computers in Human Behavior 54: 414–424. 10.1016/j.chb.2015.08.029. doi:10.1016/j.chb.2015.08.029
139. Neguț, A. , A. M. Jurma , and D. David . 2017. “Virtual‐Reality‐Based Attention Assessment of ADHD: ClinicaVR: Classroom‐CPT Versus a Traditional Continuous Performance Test.” Child Neuropsychology 23, no. 6: 692–712. 10.1080/09297049.2016.1186617.27258210 doi:10.1080/09297049.2016.1186617 PubMed
140. Nguyen, H. , V. Nguyen , T. Nguyen , et al. 2018. “Jointly Predicting Affective and Mental Health Scores Using Deep Neural Networks of Visual Cues on the Web.” In Lecture Notes in Computer Science, vol. 11234, edited by H. Hacid , W. Cellary , H. Wang , H. Y. Paik , and R. Zhou , 100–110. Springer. 10.1007/978-3-030-02925-8_7. doi:10.1007/978-3-030-02925-8_7
141. Niedenthal, P. M. 2007. “Embodying Emotion.” Science 316, no. 5827: 1002–1005. 10.1126/science.1136930.17510358 doi:10.1126/science.1136930 PubMed
142. Nielsen, L. M. , H. Kirkegaard , L. G. Østergaard , K. Bovbjerg , K. Breinholt , and T. Maribo . 2016. “Comparison of Self‐Reported and Performance‐Based Measures of Functional Ability in Elderly Patients in an Emergency Department: Implications for Selection of Clinical Outcome Measures.” BMC Geriatrics 16: 199. 10.1186/s12877-016-0376-1.27899065 PMC5129645 doi:10.1186/s12877-016-0376-1 PubMed
143. Nowakowski, M. E. , M. M. Antony , and N. Koerner . 2015. “Modifying Interpretation Biases: Effects on Symptomatology, Behavior, and Physiological Reactivity in Social Anxiety.” Journal of Behavior Therapy and Experimental Psychiatry 49: 44–52. 10.1016/j.jbtep.2015.04.004.25936655 doi:10.1016/j.jbtep.2015.04.004 PubMed
144. Nunnally, J. C. , and I. H. Bernstein . 1994. Psychometric Theory. 3rd ed. McGraw‐Hill.
145. Oesten, M. , R. Richer , L. Abel , N. Rohleder , and B. M. Eskofier . 2023. “VoStress – Voice‐based Detection of Acute Psychosocial Stress.” In 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), 1–4. IEEE. 10.1109/BHI58575.2023.10313458. doi:10.1109/BHI58575.2023.10313458
146. Olah, J. , W. L. E. Wong , A. R. R. Chaudhry , O. Mena , and S. X. Tang . 2025. “Detecting Schizophrenia, Bipolar Disorder, Psychosis Vulnerability and Major Depressive Disorder From 5 Minutes of Online‐Collected Speech.” Translational Psychiatry 15: 241. 10.1038/s41398-025-03433-0.40651952 PMC12255794 doi:10.1038/s41398-025-03433-0 PubMed
147. O'Meagher, S. , K. Norris , N. Kemp , and P. Anderson . 2019. “Examining the Relationship Between Performance‐Based and Questionnaire Assessments of Executive Function in Young Preterm Children: Implications for Clinical Practice.” Child Neuropsychology 25, no. 7: 899–913. 10.1080/09297049.2018.1531981.30301415 doi:10.1080/09297049.2018.1531981 PubMed
148. Oparina, E. , C. Kaiser , N. Gentile , et al. 2025. “Machine Learning in the Prediction of Human Wellbeing.” Scientific Reports 15: 1632. 10.1038/s41598-024-84137-1.39794488 PMC11723942 doi:10.1038/s41598-024-84137-1 PubMed
149. Ormerod, C. M. 2022. “Mapping Between Hidden States and Features to Validate Automated Essay Scoring Using DeBERTa Models.” Psychological Test and Assessment Modeling 64, no. 4: 495–526.
150. Ortuño‐Miró, S. , S. Molina‐Rodríguez , C. Belmonte , and J. Ibañez‐Ballesteros . 2023. “Identifying ADHD Boys by Very‐Low Frequency Prefrontal fNIRS Fluctuations During a Rhythmic Mental Arithmetic Task.” Journal of Neural Engineering 20, no. 3: 036018. 10.1088/1741-2552/acad2b.37218310 doi:10.1088/1741-2552/acad2b PubMed
151. Öztoprak, H. , M. Toycan , Y. K. Alp , O. Arıkan , E. Doğutepe , and S. Karakaş . 2017. “Machine‐Based Classification of ADHD and nonADHD Participants Using Time/Frequency Features of Event‐Related Neuroelectric Activity.” Clinical Neurophysiology 128, no. 12: 2400–2410. 10.1016/j.clinph.2017.09.105.29096213 doi:10.1016/j.clinph.2017.09.105 PubMed
152. Parsons, T. D. , and A. R. Carlew . 2016. “Bimodal Virtual Reality Stroop for Assessing Distractor Inhibition in Autism Spectrum Disorders.” Journal of Autism and Developmental Disorders 46, no. 4: 1255–1267. 10.1007/s10803-015-2663-7.26614084 doi:10.1007/s10803-015-2663-7 PubMed
153. Patel, V. , S. Saxena , C. Lund , et al. 2023. “Transforming Mental Health Systems Globally: Principles and Policy Recommendations.” Lancet 402, no. 10402: 656–666. 10.1016/S0140-6736(23)00918-2.37597892 doi:10.1016/S0140-6736(23)00918-2 PubMed
154. Patterson, T. L. , S. Goldman , C. L. McKibbin , T. Hughs , and D. V. Jeste . 2001. “UCSD Performance‐Based Skills Assessment: Development of a New Measure of Everyday Functioning for Severely Mentally Ill Adults.” Schizophrenia Bulletin 27, no. 2: 235–245. 10.1093/oxfordjournals.schbul.a006870.11354591 doi:10.1093/oxfordjournals.schbul.a006870 PubMed
155. Patton, G. C. , S. M. Sawyer , J. S. Santelli , et al. 2016. “Our Future: A Lancet Commission on Adolescent Health and Wellbeing.” Lancet 387, no. 10036: 2423–2478. 10.1016/S0140-6736(16)00579-1.27174304 PMC5832967 doi:10.1016/S0140-6736(16)00579-1 PubMed
156. Pennebaker, J. W. , R. J. Booth , and M. E. Francis . 2007. “Linguistic Inquiry and Word Count: LIWC2007.” LIWC.net.
157. Perzow, S. E. D. , B. C. Bray , M. E. Wadsworth , J. F. Young , and B. L. Hankin . 2021. “Individual Differences in Adolescent Coping: Comparing a Community Sample and a Low‐SES Sample to Understand Coping in Context.” Journal of Youth and Adolescence 50, no. 4: 693–710. 10.1007/s10964-021-01398-z.33495968 PMC8074358 doi:10.1007/s10964-021-01398-z PubMed
158. Pieri, L. , G. Tosi , and D. Romano . 2023. “Virtual Reality Technology in Neuropsychological Testing: A Systematic Review.” Journal of Neuropsychology 17, no. 2: 382–399. 10.1111/jnp.12304.36624041 doi:10.1111/jnp.12304 PubMed
159. Pile, V. , S. P. W. Haller , C. F. Hiu , and J. Y. F. Lau . 2017. “Young People With Higher Social Anxiety Are Less Likely to Adopt the Perspective of Another: Data From the Director Task.” Journal of Behavior Therapy and Experimental Psychiatry 55: 41–48. 10.1016/j.jbtep.2016.11.002.27888749 doi:10.1016/j.jbtep.2016.11.002 PubMed
160. Pless, S. , T. Woelfle , J. Lorscheider , et al. 2025. “CoGames: Development of an Adaptive Smartphone‐Based and Gamified Monitoring Tool for Cognitive Function in Multiple Sclerosis.” Journal of Neurology 272, no. 2: 119. 10.1007/s00415-024-12818-y.39812703 PMC11735570 doi:10.1007/s00415-024-12818-y PubMed
161. Power, J. , S. Watson , W. Chen , A. Lewis , M. van IJzendoorn , and M. Galbally . 2023. “The Trajectory of Maternal Perinatal Depressive Symptoms Predicts Executive Function in Early Childhood.” Psychological Medicine 53, no. 16: 7953–7963. 10.1017/S0033291723002118.37781906 PMC10755237 doi:10.1017/S0033291723002118 PubMed
162. Poznyak, E. , L. Morosan , N. Perroud , M. Speranza , D. Badoud , and M. Debbané . 2019. “Roles of Age, Gender and Psychological Difficulties in Adolescent Mentalizing.” Journal of Adolescence 74: 120–129. 10.1016/j.adolescence.2019.06.007.31202040 doi:10.1016/j.adolescence.2019.06.007 PubMed
163. Purwandari, B. , W. S. Wibawa , N. Fitriah , M. Christia , and D. R. Bintari . 2020. “Internet Addiction and Mental Health Prediction Using Ensemble Learning Based on Web Browsing History.” In Proceedings of the 3rd International Conference on Software Engineering and Information Management, 155–159. ACM. 10.1145/3378936.3378947. doi:10.1145/3378936.3378947
164. Qorich, M. , and R. El Ouazzani . 2024. “Advanced Deep Learning and Large Language Models for Suicide Ideation Detection on Social Media.” Progress in Artificial Intelligence 13, no. 2: 135–147. 10.1007/s13748-024-00326-z. doi:10.1007/s13748-024-00326-z
165. Raimo, S. , G. Maggi , C. R. Ilardi , et al. 2024. “The Relation Between Cognitive Functioning and Activities of Daily Living in Normal Aging, Mild Cognitive Impairment, and Dementia: A Meta‐Analysis.” Neurological Sciences 45, no. 6: 2427–2443. 10.1007/s10072-024-07366-2.38347298 doi:10.1007/s10072-024-07366-2 PubMed
166. Raina, A. 2025. “Leveraging Machine Learning and Feature Extraction From Physiological Signals for Multimodal Emotion Detection and Mental Health Support.” Princeton Journal of Interdisciplinary Research 1, no. 2: 215–220.
167. Rajendran, V. G. , S. Jayalalitha , K. Adalarasu , and R. Mathi . 2024. “Machine Learning Based Human Mental State Classification Using Wavelet Packet Decomposition‐An EEG Study.” Multimedia Tools and Applications 83, no. 35: 83093–83112. 10.1007/s11042-024-18725-8. doi:10.1007/s11042-024-18725-8
168. Rand, D. , S. Basha‐Abu Rukan , P. L. T. Weiss , and N. Katz . 2009. “Validation of the Virtual MET as an Assessment Tool for Executive Functions.” Neuropsychological Rehabilitation 19, no. 4: 583–602. 10.1080/09602010802469074.19058093 doi:10.1080/09602010802469074 PubMed
169. Regev, S. , and N. Josman . 2020. “Evaluation of Executive Functions and Everyday Life for People With Severe Mental Illness: A Systematic Review.” Schizophrenia Research: Cognition 21: 100178. 10.1016/j.scog.2020.100178.32477891 PMC7248676 doi:10.1016/j.scog.2020.100178 PubMed
170. Ribeiro, M. T. , S. Singh , and C. Guestrin . 2016. “‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier.” In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135–1144. ACM. 10.1145/2939672.2939778. doi:10.1145/2939672.2939778
171. Riva, G. 2005. “Virtual Reality in Psychotherapy: Review.” Cyberpsychology & Behavior 8, no. 3: 220–230. 10.1089/cpb.2005.8.220.15971972 doi:10.1089/cpb.2005.8.220 PubMed
172. Rochotte, J. , A. Sanap , V. Silenzio , and V. K. Singh . 2024. “Predicting Anxiety Using Google and Youtube Digital Traces.” Emerging Trends in Drugs, Addictions, and Health 4: 100145. 10.1016/j.etdah.2024.100145. doi:10.1016/j.etdah.2024.100145
173. Ronen, T. 2021. “The Role of Coping Skills for Developing Resilience Among Children and Adolescents.” In The Palgrave Handbook of Positive Education, edited by M. L. Kern and M. L. Wehmeyer , 345–368. Springer International Publishing. 10.1007/978-3-030-64537-3_14. doi:10.1007/978-3-030-64537-3_14
174. Rosenthal, M. Z. , K. Kim , N. R. Herr , et al. 2011. “Speed and Accuracy of Facial Expression Classification in Avoidant Personality Disorder: A Preliminary Study.” Personality Disorders, Theory, Research, and Treatment 2, no. 4: 327–334. 10.1037/a0023672.22448805 doi:10.1037/a0023672 PubMed
175. Roy, A. , K. Nikolitch , R. McGinn , S. Jinah , W. Klement , and Z. A. Kaminsky . 2020. “A Machine Learning Approach Predicts Future Risk to Suicidal Ideation From Social Media Data.” npj Digital Medicine 3: 78. 10.1038/s41746-020-0287-6.32509975 PMC7250902 doi:10.1038/s41746-020-0287-6 PubMed
176. Rutherford, M. D. , and S. J. Rogers . 2003. “Cognitive Underpinnings of Pretend Play in Autism.” Journal of Autism and Developmental Disorders 33, no. 3: 289–302. 10.1023/A:1024406601334.12908832 doi:10.1023/A:1024406601334 PubMed
177. Ryff, C. D. , and C. L. M. Keyes . 1995. “The Structure of Psychological Well‐Being Revisited.” Journal of Personality and Social Psychology 69, no. 4: 719–727. 10.1037/0022-3514.69.4.719.7473027 doi:10.1037/0022-3514.69.4.719 PubMed
178. Safavian, S. R. , and D. Landgrebe . 1991. “A Survey of Decision Tree Classifier Methodology.” IEEE Transactions on Systems, Man, and Cybernetics 21, no. 3: 660–674. 10.1109/21.97458. doi:10.1109/21.97458
179. Salton, G. , and C. Buckley . 1988. “Term‐Weighting Approaches in Automatic Text Retrieval.” Information Processing & Management 24, no. 5: 513–523. 10.1016/0306-4573(88)90021-0. doi:10.1016/0306-4573(88)90021-0
180. Sawyer, S. M. , R. A. Afifi , L. H. Bearinger , et al. 2012. “Adolescence: A Foundation for Future Health.” Lancet 379, no. 9826: 1630–1640. 10.1016/S0140-6736(12)60072-5.22538178 doi:10.1016/S0140-6736(12)60072-5 PubMed
181. Schoch‐Ruppen, J. , U. Ehlert , F. Uggowitzer , N. Weymerskirch , and P. L. Marca‐Ghaemmaghami . 2018. “Women's Word Use in Pregnancy: Associations With Maternal Characteristics, Prenatal Stress, and Neonatal Birth Outcome.” Frontiers in Psychology 9: 1234. 10.3389/fpsyg.2018.01234.30087634 PMC6066569 doi:10.3389/fpsyg.2018.01234 PubMed
182. Seligman, M. E. , and M. Csikszentmihalyi . 2000. Positive Psychology: An Introduction. Vol. 55. American Psychological Association.10.1037//0003-066x.55.1.511392865 doi:10.1037//0003-066x.55.1.5 PubMed
183. Settanni, M. , and D. Marengo . 2015. “Sharing Feelings Online: Studying Emotional Well‐Being via Automated Text Analysis of Facebook Posts.” Frontiers in Psychology 6: 1045. 10.3389/fpsyg.2015.01045.26257692 PMC4512028 doi:10.3389/fpsyg.2015.01045 PubMed
184. Seymour, K. E. , R. Macatee , and A. Chronis‐Tuscano . 2016. “Frustration Tolerance in Youth With ADHD.” Journal of Attention Disorders 23, no. 11: 1229. 10.1177/1087054716653216.27282378 PMC6541529 doi:10.1177/1087054716653216 PubMed
185. Shallice, T. , and P. W. Burgess . 1991. “Deficits in Strategy Application Following Frontal Lobe Damage in Man.” Brain 114, no. 2: 727–741. 10.1093/brain/114.2.727.2043945 doi:10.1093/brain/114.2.727 PubMed
186. Sheoran, H. , and P. Srivastava . 2022. “Self‐Reported Depression Is Associated With Aberration in Emotional Reactivity and Emotional Concept Coding.” Frontiers in Psychology 13: 814234. 10.3389/fpsyg.2022.814234.35814123 PMC9267768 doi:10.3389/fpsyg.2022.814234 PubMed
187. Shin, D. , H. Kim , S. Lee , Y. Cho , and W. Jung . 2024. “Using Large Language Models to Detect Depression From User‐Generated Diary Text Data as a Novel Approach in Digital Mental Health Screening: Instrument Validation Study.” Journal of Medical Internet Research 26: e54617. 10.2196/54617.39292502 PMC11447422 doi:10.2196/54617 PubMed
188. Shute, V. J. , and S. Rahimi . 2017. “Review of Computer‐Based Assessment for Learning in Elementary and Secondary Education.” Journal of Computer Assisted Learning 33, no. 1: 1–19. 10.1111/jcal.12172. doi:10.1111/jcal.12172
189. Singh, A. , and J. Singh . 2022. “Synthesis of Affective Expressions and Artificial Intelligence to Discover Mental Distress in Online Community.” International Journal of Mental Health and Addiction 22: 1921–1946. 10.1007/s11469-022-00966-z.PMC976536736570376 doi:10.1007/s11469-022-00966-z PubMed
190. Sivak, E. , and I. Smirnov . 2020. “Measuring Adolescents' Well‐Being: Correspondence of Naïve Digital Traces to Survey Data.” In Social Informatics, edited by S. Aref , K. Bontcheva , M. Braghieri , et al., 352–363. Springer International Publishing. 10.1007/978-3-030-60975-7_26. doi:10.1007/978-3-030-60975-7_26
191. Spytska, L. 2024. “The Use of Virtual Reality in the Treatment of Mental Disorders Such as Phobias and Post‐Traumatic Stress Disorder.” SSM—Mental Health 6: 100351. 10.1016/j.ssmmh.2024.100351. doi:10.1016/j.ssmmh.2024.100351
192. Stachl, C. , Q. Au , R. Schoedel , et al. 2020. “Predicting Personality From Patterns of Behavior Collected With Smartphones.” Proceedings of the National Academy of Sciences 117, no. 30: 17680–17687. 10.1073/pnas.1920484117.PMC739545832665436 doi:10.1073/pnas.1920484117 PubMed
193. Stanton, A. L. , and R. Franz . 2015. Focusing on Emotion. Vol. 1. Oxford University Press. 10.1093/med:psych/9780195119343.003.0005. doi:10.1093/med:psych/9780195119343.003.0005
194. Stark, M. , H. Huang , L.‐F. Yu , et al. 2022. “Identifying Individuals Who Currently Report Feelings of Anxiety Using Walking Gait and Quiet Balance: An Exploratory Study Using Machine Learning.” Sensors 22, no. 9: 3163. 10.3390/s22093163.35590853 PMC9105708 doi:10.3390/s22093163 PubMed
195. Stone, B. T. , P. C. Desrochers , M. Nateghi , et al. 2025. “Decoding Depression: Event Related Potential Dynamics and Predictive Neural Signatures of Depression Severity.” Journal of Affective Disorders 391: 119893. 10.1016/j.jad.2025.119893.40659067 doi:10.1016/j.jad.2025.119893 PubMed
196. Stroop, J. R. 1935. “Studies of Interference in Serial Verbal Reactions.” Journal of Experimental Psychology 18, no. 6: 643–662. 10.1037/h0054651. doi:10.1037/h0054651
197. Su, C. , Z. Xu , J. Pathak , and F. Wang . 2020. “Deep Learning in Mental Health Outcome Research: A Scoping Review.” Translational Psychiatry 10, no. 1: 116. 10.1038/s41398-020-0780-3.32532967 PMC7293215 doi:10.1038/s41398-020-0780-3 PubMed
198. Su, R. , M. Chen , W. Qi , G. Wang , F. Jiang , and X. Sun . 2023. “Performance‐Based Neuropsychological Assessment Tools for Executive Function Among Preschoolers in China: A Systematic Review.” Clinical Neuropsychologist 37, no. 5: 959–1004. 10.1080/13854046.2023.2216923.37260022 doi:10.1080/13854046.2023.2216923 PubMed
199. Suastra, I. , and S. Menggo . 2020. “Empowering Students' Writing Skill Through Performance Assessment.” International Journal of Language Education 4, no. 3: 432–441.
200. Sweller, J. 2011. “Cognitive Load Theory.” In Psychology of Learning and Motivation, vol. 55, 37–76. Elsevier. 10.1016/B978-0-12-387691-1.00002-8. doi:10.1016/B978-0-12-387691-1.00002-8
201. Tanaka, R. , and Y. Fukazawa . 2024. “Integrating Supervised Extractive and Generative Language Models for Suicide Risk Evidence Summarization.” In Proceedings of the 9th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2024), edited by A. Yates , B. Desmet , E. Prud'hommeaux , et al. 270–277. Association for Computational Linguistics. https://aclanthology.org/2024.clpsych‐1.27.
202. Tezer, D. , B. K. Başay , Ö. Başay , G. O. Yener , and S. Yüksel . 2025. “Cognitive Performance, Psychiatric Comorbidities, and Quality of Life in Pediatric Patients With Juvenile Idiopathic Arthritis: A Comparative Analysis With Healthy Controls.” Child Neuropsychology 31, no. 5: 692–710. 10.1080/09297049.2024.2426272.39569588 doi:10.1080/09297049.2024.2426272 PubMed
203. Tricco, A. C. , E. Lillie , W. Zarin , et al. 2018. “PRISMA Extension for Scoping Reviews (PRISMA‐ScR): Checklist and Explanation.” Annals of Internal Medicine 169, no. 7: 467–473. 10.7326/M18-0850.30178033 doi:10.7326/M18-0850 PubMed
204. Tsai, C.‐F. , C.‐C. Chen , E. H.‐K. Wu , et al. 2021. “A Machine‐Learning‐Based Assessment Method for Early‐Stage Neurocognitive Impairment by an Immersive Virtual Supermarket.” IEEE Transactions on Neural Systems and Rehabilitation Engineering 29: 2124–2132. 10.1109/TNSRE.2021.3118918.34623270 doi:10.1109/TNSRE.2021.3118918 PubMed
205. Ulbrich, S. , T. Menzel , A. Reschka , F. Schuldt , and M. Maurer . 2015. “Defining and Substantiating the Terms Scene, Situation, and Scenario for Automated Driving.” In 2015 IEEE 18th International Conference on Intelligent Transportation Systems, 982–988. IEEE. 10.1109/ITSC.2015.164. doi:10.1109/ITSC.2015.164
206. Veilleux, J. C. , G. A. Pollert , M. J. Zielinski , J. A. Shaver , and M. A. Hill . 2019. “Behavioral Assessment of the Negative Emotion Aspect of Distress Tolerance: Tolerance to Emotional Images.” Assessment 26, no. 3: 386–403. 10.1177/1073191116689819.28135808 doi:10.1177/1073191116689819 PubMed
207. Villa‐Pérez, M. E. , L. A. Trejo , M. B. Moin , and E. Stroulia . 2023. “Extracting Mental Health Indicators From English and Spanish Social Media: A Machine Learning Approach.” IEEE Access 11: 128135–128152. 10.1109/ACCESS.2023.3332289. doi:10.1109/ACCESS.2023.3332289
208. Voleti, R. , S. M. Woolridge , J. M. Liss , et al. 2023. “Language Analytics for Assessment of Mental Health Status and Functional Competency.” Schizophrenia Bulletin 49, no. Suppl 2: S183. 10.1093/schbul/sbac176.36946533 PMC10031731 doi:10.1093/schbul/sbac176 PubMed
209. Walia, T. , S. Agashe , D. L. Tikka , D. Ram , B. Das , and S. K. Tikka . 2022. “Irony Comprehension in Schizophrenia: Development, Content Validity and “Known‐Groups” Validity of an Indian, Comic‐Based, Computerized Task.” Annals of Indian Psychiatry 6, no. 2: 164–168. 10.4103/aip.aip_89_22. doi:10.4103/aip.aip_89_22
210. Wangkawan, T. , C. Lai , P. Munkhetvit , T. Yung , and S. Chinchai . 2020. “The Development and Psychometric Properties of the Visuospatial Working Memory Assessment (VWMA) for Children.” Occupational Therapy International 2020: 8736308. 10.1155/2020/8736308.32292306 PMC7152980 doi:10.1155/2020/8736308 PubMed
211. Weisberg, S. 2005. Applied Linear Regression. 3rd ed. Wiley‐Interscience. 10.1002/0471704091. doi:10.1002/0471704091
212. WHO . 2022. World Mental Health Report: Transforming Mental Health for All. World Health Organization.
213. WHO , and UNICEF . 2024. Mental Health of Children and Young People: Service Guidance. World Health Organization and the United Nations Children's Fund.
214. Wiebe, A. , K. Kannen , M. Li , et al. 2023. “Multimodal Virtual Reality‐Based Assessment of Adult ADHD: A Feasibility Study in Healthy Subjects.” Assessment 30, no. 5: 1435–1453. 10.1177/10731911221089193.35435010 PMC10248306 doi:10.1177/10731911221089193 PubMed
215. Wongkoblap, A. , M. A. Vadillo , and V. Curcin . 2017. “Researching Mental Health Disorders in the Era of Social Media: Systematic Review.” Journal of Medical Internet Research 19, no. 6: e7215. 10.2196/jmir.7215.PMC550995228663166 doi:10.2196/jmir.7215 PubMed
216. Wren‐Lewis, S. , and A. Alexandrova . 2021. “Mental Health Without Well‐Being.” Journal of Medicine and Philosophy: A Forum for Bioethics and Philosophy of Medicine 46: 684–703. 10.1093/jmp/jhab032.PMC864358834668012 doi:10.1093/jmp/jhab032 PubMed
217. Wright‐Berryman, J. , J. Cohen , A. Haq , D. P. Black , and J. L. Pease . 2023. “Virtually Screening Adults for Depression, Anxiety, and Suicide Risk Using Machine Learning and Language From an Open‐Ended Interview.” Frontiers in Psychiatry 14: 1143175. 10.3389/fpsyt.2023.1143175.37377466 PMC10291825 doi:10.3389/fpsyt.2023.1143175 PubMed
218. Wu, H. , X. Yin , K. Miao , J. Yin , and H. Zhao . 2021. “Cardiorespiratory Fitness in Adolescents With Mental Sub‐Health in China.” Annales Médico‐Psychologiques, Revue Psychiatrique 179, no. 1: 33–38. 10.1016/j.amp.2020.08.002. doi:10.1016/j.amp.2020.08.002
219. Wu, M.‐J. , I. C. Passos , I. E. Bauer , et al. 2016. “Individualized Identification of Euthymic Bipolar Disorder Using the Cambridge Neuropsychological Test Automated Battery (CANTAB) and Machine Learning.” Journal of Affective Disorders 192: 219–225. 10.1016/j.jad.2015.12.053.26748737 PMC4727980 doi:10.1016/j.jad.2015.12.053 PubMed
220. Xiang, F. , L. Zhang , Y. Ye , et al. 2024. “Using Pupil Diameter for Psychological Resilience Assessment in Medical Students Based on SVM and SHAP Model.” IEEE Journal of Biomedical and Health Informatics 28, no. 7: 4260–4268. 10.1109/JBHI.2024.3390390.38648147 doi:10.1109/JBHI.2024.3390390 PubMed
221. Yadawad, P. R. , L. Pandey , K. Mallibhat , and U. Mudenagudi . 2024. “Predicting Anxiety Among Young Adults Using Machine Learning Algorithms.” In 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), 1–8. IEEE. 10.1109/I2CT61223.2024.10544191. doi:10.1109/I2CT61223.2024.10544191
222. Yang, Q. , Z. Wang , H. Chen , et al. 2024. “PsychoGAT: A Novel Psychological Measurement Paradigm Through Interactive Fiction Games With LLM Agents (No. arXiv:2402.12326).” arXiv. 10.48550/arXiv.2402.12326. doi:10.48550/arXiv.2402.12326
223. Yang, Z. , H. Li , L. Li , K. Zhang , C. Xiong , and Y. Liu . 2019. “Speech‐Based Automatic Recognition Technology for Major Depression Disorder.” In Human Centered Computing, edited by D. Milošević , Y. Tang , and Q. Zu , 546–553. Springer International Publishing. 10.1007/978-3-030-37429-7_55. doi:10.1007/978-3-030-37429-7_55
224. Yarkoni, T. , and J. Westfall . 2017. “Choosing Prediction Over Explanation in Psychology: Lessons From Machine Learning.” Perspectives on Psychological Science: A Journal of the Association for Psychological Science 12, no. 6: 1100–1122. 10.1177/1745691617693393.28841086 PMC6603289 doi:10.1177/1745691617693393 PubMed
225. Zeulner, T. , G. J. Hagerer , M. Müller , I. Vazquez , and P. A. Gloor . 2024. “Predicting Individual Well‐Being in Teamwork Contexts Based on Speech Features.” Information 15, no. 4: 4. 10.3390/info15040217. doi:10.3390/info15040217
226. Zhao, N. , Z. Zhang , Y. Wang , et al. 2019. “See Your Mental State From Your Walk: Recognizing Anxiety and Depression Through Kinect‐Recorded Gait Data.” PLoS One 14, no. 5: e0216591. 10.1371/journal.pone.0216591.31116785 PMC6530855 doi:10.1371/journal.pone.0216591 PubMed
227. Zhou, M. , and J. Ee . 2012. “Development and Validation of the Social Emotional Competence Questionnaire (SECQ).” International Journal of Emotional Education 4, no. 2: 27–42.