Jul 2026· International Conference on Smart Communications and Networking· pp. 1-6· 0 citations· 11 references
Abstract
Depression and anxiety disorders are among the most prevalent and debilitating mental health conditions worldwide, imposing substantial personal, social, and economic burdens. Although recent advances in Large Language Models (LLMs) have shown promise in supporting mental health assessment and intervention, existing approaches often lack contextual awareness, real-time adaptability, and privacy-preserving personalization. To address these limitations, we propose a novel, context-aware and privacy-preserving mental health evaluation architecture that synergistically integrates LLM-driven intelligence. The proposed system enables personalized, continuous, and stigma-free mental health support by combining structured multiple-choice questionnaires with advanced language models, including GPT-3.5-turbo and Groq, to analyze user inputs, identify behavioral patterns, and predict potential mental health conditions such as depression and anxiety. Furthermore, the platform provides individualized recommendations, including self-care strategies, lifestyle adjustments, mindfulness practices, and referrals to healthcare professionals when appropriate. Recognizing the critical importance of reliability in sensitive healthcare settings, we introduce an ensemble-based aggregation framework that explicitly incorporates classification confidence and uncertainty quantification across multiple LLMs. Experimental results demonstrate that the proposed approach outperforms existing LLM models. By prioritizing user anonymity and data privacy, the proposed system reduces psychological barriers to seeking mental health support and promotes early intervention.
Health anxiety has emerged as a major psychological concern in contemporary society due to increased exposure to online medical information, heightened awareness of diseases, and rapid dissemination of health-related content through digital media. Existing measures assessing health anxiety are predominantly developed within Western cultural contexts and may inadequately capture culturally specific illness beliefs and health-related behaviors observed among Indian adults. The present study aimed to develop and validate the Health Anxiety Inventory (HAI), a culturally grounded multidimensional instrument designed to assess health anxiety among adults. The scale was developed based on cognitive-behavioral and socio-cultural theoretical frameworks. An initial pool of 30 items across six dimensions was generated through literature review, expert consultation, and analysis of socio-cultural health beliefs. The dimensions included Anticipatory Health Worry, Bodily Sensation Monitoring, Catastrophic Interpretation, Reassurance Seeking and Healthcare Utilisation, Functional Impairment and Avoidance, and Socio-Cultural Health Beliefs. The inventory was administered to 183 college students selected through convenience sampling. Reliability analysis revealed excellent internal consistency (Cronbach’s α = .912). Item-total correlations ranged from .32 to .68, indicating satisfactory construct representation. Expert evaluations supported content validity, while theoretical coherence and statistical findings supported construct validity. The findings suggest that the HAI is a reliable and culturally relevant instrument suitable for assessing health anxiety among adults. The inventory may be useful in psychological assessment, counseling interventions, public mental health screening, and behavioral medicine research.
Krishnamurthy V. S.· Journal of Psychology and So...· 0 citations
Mental health issues, especially depressive symptoms, among young adults represent a public health challenge. Conventional psychological assessment tools have limited sensitivity and specificity for identifying individuals at risk. This study aims to develop an explainable machine learning-based model to stratify concurrent depression risk in young adults. This study included 100,257 college students and collected mental health variables including depression, anxiety, resilience, parent-child relationship, and duration of mobile phone usage. The screening capabilities of 13 machine learning algorithms were systematically evaluated and compared. The SHapley Additive exPlanations (SHAP) framework was employed for the interpretability of the final model. The median scores for parent-child relationship, resilience, anxiety, and mobile phone usage time was 42.0, 28.0, 1.0 and 28.0, respectively. Among the 13 machine learning algorithms, the XGBoost model demonstrated superior performance. The final multivariate screening model achieved an area under the curve (AUC) of 0.887, a sensitivity of 0.787, a specificity of 0.830, and an accuracy of 0.816 in classifying young adults' concurrent depression risk. The SHAP analysis showed the importance of each variable: anxiety (2.303) > resilience (0.774) > parent-child relationship (0.708) > mobile phone usage time (0.411). The final multivariate model exhibited stable performance during cross-validation (AUC = 0.885 ± 0.032), significantly better than the single-variable model (P < 0.001) and better screening reliability (Brier score 0.153). The final multivariate XGBoost model provides a highly accurate and interpretable approach for young adults' depression risk stratification. As the model was developed using cross-sectional data collected during the COVID-19 campus lockdown, prospective validation is required before clinical deployment. Notably, anxiety level emerged as the most influential risk factor, and resilience demonstrated a significant protective effect.
AI is significantly impacting the way that mental health diagnostic tools are developed through their ability to
provide affordable, accessible and efficient means of detecting psychological disorders like depression. While the current
state of screening includes many effective tools (i.e., Clinical Interviews and Self- Reported Questionnaires) they have some
inherent shortcomings; these include, but are not limited to, being subjective and/or delayed diagnoses, lack of access to
individuals who may be experiencing difficulties with their mental health, and dependency on the availability of
professional interventions. The shortfalls identified above demonstrate the need for the development of intelligent systems,
capable of conducting rapid and accurate evaluations of an individualʼs mental health. An AI-driven Depression Level
Prediction System was therefore created to collect structured clinical information, as well as unstructured textual input in
order to create a full and complete assessment of an individualʼs mental health condition. Utilizing the PHQ 9 survey
instrument as the basis for collecting clinical information, the system utilizes Natural Language Processing techniques to
evaluate user-generated text, thereby gaining further insight into an individualʼs emotional and psychological trends.
The system described herein utilizes three machine learning-based predictive models Random Forest, SVM,
XGBoost) to predict an individualʼs level of depression as one of four categories (minimal, mild, moderate or severe).
Unlike prior binary prediction models utilized in the context of mental health evaluations, the described model
provides fine-tuned evaluations that can be more effectively used in practical applications of mental health
monitoring. Additionally, Explainable AI techniques were incorporated into the design of the system to improve
transparency and interpretability of the results produced by the system. Such capabilities enable both patients and
clinicians to identify specific variables within the results that contributed to the systemʼs predictions. The modular nature
of the system enables scalability, flexibility and efficient operation of the system even when utilizing lightweight
hardware that does not require extensive computing capabilities. Experimental validation demonstrated that the described
system achieved greater accuracy and better generalization than other systems currently available. Through its ability to
process both behavioral inputs, questionnaire responses and textual sentiment analysis, the system offers a holistic view
of an individualʼs mental health status. Beyond improving early detection, the described system can assist clinicians and
patients in making informed decisions regarding treatment options for issues related to mental health. Therefore, the
system serves as a connection between traditional healthcare practices and emerging AI technology to provide a private
and secure method for evaluating mental health conditions.
Danda Shruthi, Annamaneni Sai, Kalal Taruni et al.· International Journal of Inn...· 0 citations
Digital mental health applications (DMHAs) are emerging as accessible and cost-effective tools to address the growing global mental health burden. They include solutions like CBT-based apps, mindfulness tools, mood trackers, and AI chatbots, offering real-time support and continuous monitoring. Research shows they can reduce symptoms of anxiety, depression, and stress, especially when based on evidence-based therapies However, challenges remain. Many apps lack proper clinical validation, user engagement often declines over time, and concerns about data privacy, security, and algorithmic bias persist. While DMHAs are valuable as supplementary tools, they cannot fully replace traditional therapy. The most effective approach is a hybrid model combining digital tools with professional care. The paper recommends stronger regulations, improved design, and better clinical validation to enhance their effectiveness.
Grace Ndlovu, Samuel Johnson· International Journal of Inn...· 0 citations
Introduction: Anxiety and depression are the most prevalent mental health disorders worldwide, placing an increasing burden on public health systems. However, certain transdiagnostic factors may modulate vulnerability to these disorders: personality traits, emotional regulation, and social support. Objective: To examined these factors, classifying them as either risk or protective through correlation analyses and qualitative comparative analyses in a clinical sample. Methods: After applying inclusion and exclusion criteria, the final sample consisted of 61 participants (73.8% female, 24.6% male, 1.6% other genders) aged between 20 and 66 years (M = 43.79; SD = 12.75). Results: Neuroticism was associated with higher levels of anxiety and depression, whereas extraversion predicted better mental health. Additionally, emotion dysregulation correlated positively with both psychopathologies. Finally, perceived social support emerged as a sufficient condition for lower anxiety levels; conversely, its absence was linked to higher levels of both anxiety and depression. Conclusions: These findings highlight the importance of further investigating risk and protective factors related to highly prevalent mental health problems like anxiety and depression. Better understanding these factors can help improve assessment, diagnosis, and treatment within clinical practice.
Selene Valero-Moreno, Olga Ribera-Asensi, Saray Giménez-Benavent et al.· Universitas Médica· 0 citations
Kegelaers and colleagues provide a timely critique of mental health screening in high-performance sport, highlighting concerns regarding predictive validity, feasibility, effectiveness, and potential harms. We welcome this debate and agree that screening can become problematic when used uncritically, symbolically, or without sufficient follow-up capacity. At the same time, if such critiques are interpreted as discouraging mental health screening as a practice, they may unintentionally reinforce mental health-related stigma by implying that mental ill-health is uniquely unsuitable for routine assessment, monitoring, or early support in high-perfomance sport. We argue that the central issue is not screening per se, but the role screening is given within athlete care systems. Screening is best understood as a structured wellbeing check-in and supportive gateway that can inform triage and facilitate clinical conversation, contextual assessment, and care, rather than diagnosis, surveillance, or stand-alone intervention. Concerns about specific instruments also need to be interpreted in relation to their intended constructs and implementation roles. For example, limitations of the Athlete Psychological Strain Questionnaire (APSQ) as a broad triage tool need not negate its value as a measure of athlete psychological distress. Responsible implementation depends on informed consent, confidentiality, clinical governance, mental health literacy, culturally responsive communication, and clear care pathways. This reframing allows the field to take the risks of screening seriously while keeping mental health integrated within routine athlete health care.
Yasutaka Ojio, Simon Rice, Yavuz Lima et al.· Psychology of Sport And Exer...· 0 citations