Fozle Rabbi Shafi, M. Anwar Hossain, Salimur Choudhury
Large Language Model (LLM)-based systems increasingly rely on function calling to enable structured and controllable interaction with external data sources, yet existing datasets do not address mental health-oriented access to wearable sensor data. This paper presents a synthetic function-calling dataset designed for mental health assistance grounded in wearable health signals such as sleep, physical activity, cardiovascular measures, stress indicators, and metabolic data. The dataset maps diverse natural language queries to standardized API calls derived from a widely adopted health data schema. Each sample includes a user query, a query category, an explicit reasoning step, a normalized temporal parameter, and a target function. The dataset covers explicit, implicit, behavioral, symptom-based, and metaphorical expressions, which reflect realistic mental health-related user interactions. This resource supports research on intent grounding, temporal reasoning, and reliable function invocation in LLM-based mental health agents and is publicly released to promote reproducibility and future work.
Wayupuk Sommuang, Kun Kerdthaisong, Pasin Buakhaw
et al.
Students' mental well-being is vital for academic success, with activities such as studying, socializing, and sleeping playing a role. Current mobile sensing data highlight this intricate link using statistical and machine learning analyses. We propose a novel LLM agent-based simulation framework to model student activities and mental health using the StudentLife Dataset. Each LLM agent was initialized with personality questionnaires and guided by smartphone sensing data throughout the simulated semester. These agents predict individual behaviors, provide self-reported mental health data via ecological momentary assessments (EMAs), and complete follow-up personality questionnaires. To ensure accuracy, we investigated various prompting techniques, memory systems, and activity-based mental state management strategies that dynamically update an agent's mental state based on their daily activities. This simulation goes beyond simply replicating existing data. This allows us to explore new scenarios that are not present in the original dataset, such as peer influence through agent-to-agent interactions and the impact of social media. Furthermore, we can conduct intervention studies by manipulating activity patterns via sensing signals and personality traits using questionnaire responses. This provides valuable insights into the behavioral changes that could enhance student well-being. The framework also facilitates hypothetical interviews with LLM agents, offering deeper insights into their mental health. This study showcases the power of LLM-driven behavioral modeling with sensing data, opening new avenues for understanding and supporting student mental health.
Meghna Roy Chowdhury, Wei Xuan, Shreyas Sen
et al.
Mental health issues among college students have reached critical levels, significantly impacting academic performance and overall wellbeing. Predicting and understanding mental health status among college students is challenging due to three main factors: the necessity for large-scale longitudinal datasets, the prevalence of black-box machine learning models lacking transparency, and the tendency of existing approaches to provide aggregated insights at the population level rather than individualized understanding. To tackle these challenges, this paper presents I-HOPE, the first Interpretable Hierarchical mOdel for Personalized mEntal health prediction. I-HOPE is a two-stage hierarchical model that connects raw behavioral features to mental health status through five defined behavioral categories as interaction labels. We evaluate I-HOPE on the College Experience Study, the longest longitudinal mobile sensing dataset. This dataset spans five years and captures data from both pre-pandemic periods and the COVID-19 pandemic. I-HOPE achieves a prediction accuracy of 91%, significantly surpassing the 60-70% accuracy of baseline methods. In addition, I-HOPE distills complex patterns into interpretable and individualized insights, enabling the future development of tailored interventions and improving mental health support. The code is available at https://github.com/roycmeghna/I-HOPE.
Purpose: With the rise of mental health risks globally, it is urgent to provide effective mental health support. However, a holistic understanding of how people seek help for mental health problems remains limited, impeding the development of evidence-based intervention programs to facilitate help-seeking behavior. This study reviews current theories that guide empirical research on young adults' help-seeking behavior using technologies, identifies limitations in existing frameworks, and proposes directions for future research. Methods: We searched databases that are most likely to contain mental health help-seeking practices in relation to information technology, including PubMed, ACM Digital Library, Web of Science, PsycInfo, ScienceDirect, EBSCO, and Cochrane Library. Results: Of 2443 abstracts reviewed, 43 studies met the criteria and were included in the analysis. We identified 16 theories and models. They represent seven perspectives to view mental health help-seeking and reveal factors such as accessibility, stigma, and social support as key factors influencing help-seeking. Limitations: We summarized the theories and models and categorized them based on their primary perspectives. Cross-perspective connections could be explored in future reviews. Conclusions: A holistic approach to creating culturally sensitive multi-level interventions that consider individual, interpersonal, and community factors is needed to advance effective mental health help-seeking support strategies.
We present a continuous-time portfolio selection framework that reflects goal-based investment principles and mental accounting behavior. In this framework, an investor with multiple investment goals constructs separate portfolios, each corresponding to a specific goal, with penalties imposed on fund transfers between these goals, referred to as mental costs. By applying the stochastic Perron's method, we demonstrate that the value function is the unique constrained viscosity solution of a Hamilton-Jacobi-Bellman equation system. Numerical analysis reveals several key features: the free boundaries exhibit complex shapes with bulges and notches; the optimal strategy for one portfolio depends on the wealth level of another; investors must diversify both among stocks and across portfolios; and they may postpone reallocating surplus from an important goal to a less important one until the former's deadline approaches.
The deployment of large language models (LLMs) in mental health and other sensitive domains raises urgent questions about ethical reasoning, fairness, and responsible alignment. Yet, existing benchmarks for moral and clinical decision-making do not adequately capture the unique ethical dilemmas encountered in mental health practice, where confidentiality, autonomy, beneficence, and bias frequently intersect. To address this gap, we introduce Ethical Reasoning in Mental Health (EthicsMH), a pilot dataset of 125 scenarios designed to evaluate how AI systems navigate ethically charged situations in therapeutic and psychiatric contexts. Each scenario is enriched with structured fields, including multiple decision options, expert-aligned reasoning, expected model behavior, real-world impact, and multi-stakeholder viewpoints. This structure enables evaluation not only of decision accuracy but also of explanation quality and alignment with professional norms. Although modest in scale and developed with model-assisted generation, EthicsMH establishes a task framework that bridges AI ethics and mental health decision-making. By releasing this dataset, we aim to provide a seed resource that can be expanded through community and expert contributions, fostering the development of AI systems capable of responsibly handling some of society's most delicate decisions.
Penelitian ini bertujuan untuk mengetahui dampak perceraian orang tua terhadap kesehatan mental anak yang berasal dari keluarga broken home di Desa Jatisrono. Perceraian merupakan salah satu faktor yang dapat mengganggu kestabilan emosi dan psikologis anak, yang berdampak pada kesejahteraan mental mereka. Berdasarkan data statistik, angka perceraian di Indonesia terus meningkat, dan dampak dari perceraian tersebut dapat mempengaruhi perkembangan emosional dan psikologis anak, menyebabkan berbagai gangguan mental seperti kecemasan, depresi, dan penurunan kepercayaan diri. Penelitian ini menggunakan pendekatan kualitatif deskriptif dengan lokasi di Desa Jatisrono, Kecamatan Semampir, Kabupaten Surabaya. Teknik pengumpulan data meliputi wawancara semi-terstruktur, observasi non-partisipatif, dan dokumentasi, dengan melibatkan empat informan yang merupakan anak-anak dari keluarga broken home di desa tersebut. Hasil penelitian menunjukkan bahwa anak-anak yang mengalami perceraian orang tua cenderung mengalami gangguan kesehatan mental, termasuk perasaan kesedihan yang mendalam, kecemasan, serta gangguan sosial dan akademik. Sebagian besar anak menunjukkan kesulitan dalam membangun hubungan sosial yang sehat dan memiliki kecenderungan menarik diri dari lingkungan sosial. Penelitian ini mengungkapkan pentingnya dukungan emosional yang kuat dari lingkungan sekitar, terutama keluarga dan masyarakat, untuk membantu anak-anak mengatasi dampak negatif dari perceraian orang tua. Hasil penelitian ini diharapkan dapat memberikan wawasan bagi orang tua, pendidik, dan masyarakat dalam memahami dampak perceraian terhadap anak dan memberikan dukungan yang diperlukan untuk menjaga kesehatan mental mereka.
Mental health disorders are one of the most serious diseases in the world. Most people with such a disease lack access to adequate care, which highlights the importance of training models for the diagnosis and treatment of mental health disorders. However, in the mental health domain, privacy concerns limit the accessibility of personalized treatment data, making it challenging to build powerful models. In this paper, we introduce MentalArena, a self-play framework to train language models by generating domain-specific personalized data, where we obtain a better model capable of making a personalized diagnosis and treatment (as a therapist) and providing information (as a patient). To accurately model human-like mental health patients, we devise Symptom Encoder, which simulates a real patient from both cognition and behavior perspectives. To address intent bias during patient-therapist interactions, we propose Symptom Decoder to compare diagnosed symptoms with encoded symptoms, and dynamically manage the dialogue between patient and therapist according to the identified deviations. We evaluated MentalArena against 6 benchmarks, including biomedicalQA and mental health tasks, compared to 6 advanced models. Our models, fine-tuned on both GPT-3.5 and Llama-3-8b, significantly outperform their counterparts, including GPT-4o. We hope that our work can inspire future research on personalized care. Code is available in https://github.com/Scarelette/MentalArena/tree/main
Pretrained foundation models and transformer architectures have driven the success of large language models (LLMs) and other modern AI breakthroughs. However, similar advancements in health data modeling remain limited due to the need for innovative adaptations. Wearable movement data offers a valuable avenue for exploration, as it's a core feature in nearly all commercial smartwatches, well established in clinical and mental health research, and the sequential nature of the data shares similarities to language. We introduce the Pretrained Actigraphy Transformer (PAT), the first open source foundation model designed for time-series wearable movement data. Leveraging transformer-based architectures and novel techniques, such as patch embeddings, and pretraining on data from 29,307 participants in a national U.S. sample, PAT achieves state-of-the-art performance in several mental health prediction tasks. PAT is also lightweight and easily interpretable, making it a robust tool for mental health research. GitHub: https://github.com/njacobsonlab/Pretrained-Actigraphy-Transformer/
Gustavo A. Basílio, Thiago B. Pereira, Alessandro L. Koerich
et al.
Major Depressive Disorder and anxiety disorders affect millions globally, contributing significantly to the burden of mental health issues. Early screening is crucial for effective intervention, as timely identification of mental health issues can significantly improve treatment outcomes. Artificial intelligence (AI) can be valuable for improving the screening of mental disorders, enabling early intervention and better treatment outcomes. AI-driven screening can leverage the analysis of multiple data sources, including facial features in digital images. However, existing methods often rely on controlled environments or specialized equipment, limiting their broad applicability. This study explores the potential of AI models for ubiquitous depression-anxiety screening given face-centric selfies. The investigation focuses on high-risk pregnant patients, a population that is particularly vulnerable to mental health issues. To cope with limited training data resulting from our clinical setup, pre-trained models were utilized in two different approaches: fine-tuning convolutional neural networks (CNNs) originally designed for facial expression recognition and employing vision-language models (VLMs) for zero-shot analysis of facial expressions. Experimental results indicate that the proposed VLM-based method significantly outperforms CNNs, achieving an accuracy of 77.6%. Although there is significant room for improvement, the results suggest that VLMs can be a promising approach for mental health screening.
Mental health support in colleges is vital in educating students by offering counseling services and organizing supportive events. However, evaluating its effectiveness faces challenges like data collection difficulties and lack of standardized metrics, limiting research scope. Student feedback is crucial for evaluation but often relies on qualitative analysis without systematic investigation using advanced machine learning methods. This paper uses public Student Voice Survey data to analyze student sentiments on mental health support with large language models (LLMs). We created a sentiment analysis dataset, SMILE-College, with human-machine collaboration. The investigation of both traditional machine learning methods and state-of-the-art LLMs showed the best performance of GPT-3.5 and BERT on this new dataset. The analysis highlights challenges in accurately predicting response sentiments and offers practical insights on how LLMs can enhance mental health-related research and improve college mental health services. This data-driven approach will facilitate efficient and informed mental health support evaluation, management, and decision-making.
Alessandro De Grandi, Federico Ravenda, Andrea Raballo
et al.
The increasing demand for mental health services has highlighted the need for innovative solutions, particularly in the realm of psychological conversational AI, where the availability of sensitive data is scarce. In this work, we explored the development of a system tailored for mental health support with a novel approach to psychological assessment based on explainable emotional profiles in combination with empathetic conversational models, offering a promising tool for augmenting traditional care, particularly where immediate expertise is unavailable. Our work can be divided into two main parts, intrinsecaly connected to each other. First, we present RACLETTE, a conversational system that demonstrates superior emotional accuracy compared to state-of-the-art benchmarks in both understanding users' emotional states and generating empathetic responses during conversations, while progressively building an emotional profile of the user through their interactions. Second, we show how the emotional profiles of a user can be used as interpretable markers for mental health assessment. These profiles can be compared with characteristic emotional patterns associated with different mental disorders, providing a novel approach to preliminary screening and support.
This study explores the psychosocial impacts and coping strategies caregivers face while caring for children with autism. The study employed a qualitative method to analyze the data collected through semi-structured interviews. Interviews were conducted with 20 purposively selected informants at PMLCH. The data were transcribed and analyzed thematically, focusing on the study objectives. The findings indicate that caregivers who live with an autistic child experience significant psychological stress as well as mental and physical health issues. The findings further revealed that the psychological impact of caregivers living with a child with autism includes psychological and emotional stress, financial constraints, a lack of professional guidance, limited access to support services, cultural beliefs and practices, and stigma and social isolation. Meanwhile, caregivers use religious and socio-cultural support, educational programs, self-efficacy, advocacy and awareness, traditional healing practices, and social support as coping strategies. Additionally, caregivers advocate for improving infrastructure and mechanisms to improve their experiences living with an autistic child. The study highlights the need for caregivers to receive free or low-cost professional guidance and counseling. The study concluded that it is essential that government, family, and community organizations support caregivers emotionally and financially to cope with the prevailing psychological stress.
Sexual violence is an important issue that must be resolved as quickly and precisely as possible. In general, many cases of sexual violence are experienced by women from various sectors. These victims need help not only to catch the perpetrator and provide counseling, but also need protection in the form of disguised identity. There have been many mental healing efforts provided by various parties to victims of sexual violence, but still few focus on disguising the identities of the victims. In fact, victims also need their identity to be protected as best as possible. This effort has been carried out by one of the religious education institutions in Aceh, namely Dayah Diniyah Darussalam. The Dayah that he leads is used as a safe house for victims of sexual violence and also provides various efforts to restore the mental health of the victims, one of which is by disguising their identity as victims. Departing from this topic, this article examines the communication strategies developed by the Dayah to fight discrimination against victims of sexual violence. This research was studied using a qualitative approach and data was collected by means of in-depth interviews, observation and documentation. This research uses Reflexive Thematic Analysis (RTA) to analyze the found data. The results of the research are that efforts to disguise identity can be used as a communication strategy to protect victims of sexual violence.
Keywords: disguise of identity, communication strategy, sexual violence, resistance, discrimination
Lennart Brocki, George C. Dyer, Anna Gładka
et al.
Mental health counseling remains a major challenge in modern society due to cost, stigma, fear, and unavailability. We posit that generative artificial intelligence (AI) models designed for mental health counseling could help improve outcomes by lowering barriers to access. To this end, we have developed a deep learning (DL) dialogue system called Serena. The system consists of a core generative model and post-processing algorithms. The core generative model is a 2.7 billion parameter Seq2Seq Transformer fine-tuned on thousands of transcripts of person-centered-therapy (PCT) sessions. The series of post-processing algorithms detects contradictions, improves coherency, and removes repetitive answers. Serena is implemented and deployed on \url{https://serena.chat}, which currently offers limited free services. While the dialogue system is capable of responding in a qualitatively empathetic and engaging manner, occasionally it displays hallucination and long-term incoherence. Overall, we demonstrate that a deep learning mental health dialogue system has the potential to provide a low-cost and effective complement to traditional human counselors with less barriers to access.
Background: The role of balanced diet in the life of an individual physically challenged or not cannot be overlooked. The condition of the physically challenged children attracts little or no attention. Several factors have been identified as causes of malnutrition in physically challenged persons. A nutritional diet is one of the factors that can help to reduce this phenomenon. The study was designed to examine the effect of a nutrition diet on health status of physically challenged students at Ade Okubanjo Institute for the Blind at Ijebu-Igbo.
Method: This study used a descriptive survey research design and was conducted in 2022. 120 students were selected as the population of this study of which 100 were retuned valid. The research location was Ade Okubanjo Institute for the Blind, Ijebu-Igbo. A self-structured questionnaire was used to measure the nutrition diet of physically challenged students. To do so, 100 questionnaires were analyzed using a purposive sampling techniques method. Nutritional diet and health status questionnaire was the instrument used for this study and questions about physical performance, nutritional diet, lack of adequate nutrition and family/parental status questions were asked from the participants. Cronbach’s alpha of NHSQ was 0.72. The data analysis method included the descriptive statistics were analyzed using chi-square.
Result: Findings revealed that physical activities performance will significantly influence the nutrition diet of physically challenged children (Cal. value = 125.748a,, p-value = .000.), Lack of adequate nutrition will significantly influence the nutrition diet of physically challenged children (Cal. value = 46.180a,, p-value = .000.) also mental health status significantly influence the nutrition diet of physically challenged children (Cal. value = 41.165a,, p-value = .000.), Family/parental status will significantly affect the nutritional diet intake of the physically challenged (Cal value = 41.165a, , p-value = .000.).
Conclusion: The findings concluded that Physical performance, Lack of adequate nutrition, Mental status and Family/parental status significantly affect the nutritional diet intake of the physically challenged students at Ade Okubanjo Institute for the Blind.
Communities. Classes. Races, Social pathology. Social and public welfare. Criminology
Shamini Jain, Eileen McKusick, Lorna Ciccone
et al.
Objectives: This study examined the feasibility and effectiveness of a virtually-delivered, biofield-based sound healing treatment to reduce anxiety for individuals meeting criteria for Generalized Anxiety Disorder. Design: This one-group, mixed-method feasibility study was conducted virtually via Zoom during the SARS-CoV-2 Pandemic. Fifteen participants with moderate to high levels of anxiety as determined by the Generalized Anxiety Disorder-7 (≥10), were enrolled. Intervention: Five certified Biofield Tuning Practitioners performed the interventions. Participants were given three weekly, hour-long sound healing treatments virtually, over a month’s period. Outcome Measures: Attrition rates and reports on feasibility of intervention delivery and outcomes assessment were obtained by participants. Data on anxiety, positive and negative affect, spiritual experience, perceived stress, and quality of life were obtained via validated surveys and analyzed via repeated-measures analysis of variance with intention-to-treat. Linguistic inquiry and word count was utilized to assess changes in affective processing as reflected in participants’ spoken words over the course of the intervention. Qualitative interviews were conducted to further determine tolerability and experiences with receiving BT that may not have been captured by survey and language data. Results: Attrition rates were 13.3%, with two participants dropping out of the study after one session. The remaining participants reported acceptability of the data collection process and intervention delivery. Intention to treat analyses revealed statistically significant reductions in anxiety (State-Trait Anxiety Inventory), negative affect (Positive and Negative Affect Scale), and perceived stress (Perceived Stress Scale) (p < .001 in all cases). Linguistic and word count analysis revealed a significant linear decrease (p = .01) of participants’ use of negative affect words over the course of the intervention. Qualitative data results are reported in another paper. Conclusions: Results indicate that BT delivered virtually is feasible and amenable to study, and that the impact of BT may be substantial in reducing anxiety and improving mental health. This is the first study of its kind to report clinically significant reductions in anxiety levels in response to a virtually-delivered, biofield-based sound therapy. Data will be used to power a randomized controlled trial to more deeply examine the effects of BT on whole-person healing for those suffering from anxiety.
Purpose: Task sharing in psychological treatments has been recognized as an effective strategy for bridging the global mental health treatment gap. However, more research is needed to better support its implementation in routine care. Mental health services users' engagement with treatment is a crucial implementation factor, yet empirical evidence on its determinants remains sparse. The current study aims to investigate social support as a predictor of users’ session attendance, a key indicator of treatment engagement, within a task-shared psychological treatment. Methods: This is a secondary analysis of cohort study data from the Program for Improving Mental Health Care (PRIME) implemented in Sehore district, India, where trained non-specialist health workers delivered manualized treatment for depression and alcohol use disorder (AUD; n = 240 in depression cohort, n = 190 in AUD cohort). Quasi-Poisson regression models were used to assess the association between users’ perceived social support at baseline and treatment session attendance at 3-month follow-up, controlling for socio-demographic and clinical characteristics. Result: Within the depression cohort, a 4-point increase in social support score at baseline predicted a higher number of treatment sessions attended by 3-month follow up (IRR = 1.44, 95% CI: 1.06, 1.93). Within the AUD cohort, we noted insufficient statistical evidence for a weak association between users’ social support and the number of treatment sessions attended in adjusted analysis (IRR = 1.02; 95% CI: 0.69, 1.49). Conclusion: Our findings suggest that the implementation of task-shared psychological treatments for depression into routine care may be enhanced by strategies that activate or build upon the functional roles of users’ social support.
Modern medical research shows that art aesthetic plays a positive role in healing and relieving people’s stress, improving mental health and improving social adaptability. Based on the aesthetic experience of visitors, this article conducts an empirical study on the aesthetic experience of the Long March Memorial Museum in Ninghua County, Fujian province, by means of survey data questionnaire (SD) and in-depth interview. Firstly, to conduct a questionnaire survey to understand the psychological characteristics of visitors’ aesthetic experience. Secondly, the combination of in-depth interviews and the aesthetic differences of public art psychological analysis. Thirdly, to clarify the relationship between public art aesthetics and psychological healing. By constructing a model of the relationship between public art aesthetics and psychological healing, it puts forward five ways of psychological healing, such as enhancing aesthetic experience, arousing life interest, enriching cultural and artistic knowledge, shaping individual psychology and relieving emotional pressure.
Contribution: Public art aesthetics is not only influenced by the politics, culture, customs and lifestyles of society but also has a close relationship with religious beliefs. This article attempts to explain the relationship between public art aesthetics and psychological healing from the dimension of cognitive psychology and proposes a path for public art aesthetics to promote psychological healing, so as to enrich and expand the connotation of traditional aesthetic thought and further deepen the study of religious art in psychological healing, aiming to provide useful ideas and references for promoting the all-round development of human beings.
Dristy Gurung, Brandon A. Kohrt, Syed Shabab Wahid
et al.
Stigma among primary care providers (PCPs) is a barrier to successful integration of mental health services in primary healthcare settings globally. Therefore, cross-culturally adaptable and feasible strategies are needed to reduce stigma among PCPs. This protocol is for a multi-site pilot study that aims to adapt and evaluate cross-cultural feasibility and acceptability of a social contact-based primary healthcare intervention in 7 sites in 5 low-and-middle-income countries. A mixed methods pilot study using an uncontrolled before-after study design will be conducted in China (Beijing, Guangzhou), Ethiopia (Sodo), India (Bengaluru, Delhi), Nepal (Syangja), and Tunisia (Testour). The intervention, entitled REducing Stigma among HealthcAre ProvidErs (RESHAPE), is a collaboration with people with lived experience of mental health conditions (PWLE), their family members, and aspirational figures (who are PCPs who have demonstrated high motivation to integrate mental health services). PWLE and their family members are trained in a participatory technique, PhotoVoice, to visually depict and narrate recovery stories. Aspirational figures conduct myth busting exercises and share their experiences treating PWLE. Outcomes among PCPs will include stigma knowledge, explicit and implicit attitudes, and mental healthcare competencies. To understand the feasibility, and acceptability of the intervention, qualitative interviews will be carried out with PWLE, family members, and aspirational figures, PhotoVoice trainers, mental health specialists co-leading the primary care trainings, and PCPs receiving mental health training. The sites will also generate evidence regarding feasibility, acceptability, recruitment, retention, fidelity, safety, and usefulness of the intervention to make further adaptations and modifications. The results will inform cross-cultural guidelines for collaboration with PWLE when conducting mental health training of primary healthcare workers. The results will be used to design future multi-site hybrid trials focusing on effectiveness and implementation.