John Torous
YOU?
Author Swipe
A Paradigm Shift in Progress: Generative AI’s Evolving Role in Mental Health Care Open
Generative artificial intelligence (AI) is reshaping mental health but the direction of that change remains unclear. In this commentary, we examine the recent evidence and trends in mental health AI to identify where AI can provide value f…
View article: Development of an at‐home cognitive “vital sign” to detect cognitive changes in Alzheimer's disease
Development of an at‐home cognitive “vital sign” to detect cognitive changes in Alzheimer's disease Open
Background Patients with Early Alzheimer's Disease (AD) can have fluctuations in their cognitive abilities. A rapid, significant change could indicate a serious health condition ranging from a urinary tract infection to delirium from brain…
FDA-authorized software as a medical device in mental health: a perspective on evidence, device lineage, and regulatory challenges Open
FDA approval is widely regarded as a benchmark of quality for medical devices. However, concerns persist regarding its regulatory framework for digital mental health devices. This perspective article examined FDA-authorized Software as a M…
Social Media Detox and Youth Mental Health Open
Importance The association between social media use and youth mental health remains poorly understood, with recent systematic reviews reporting inconsistent and conflicting findings. These discrepancies reflect the overreliance on self-rep…
View article: Beyond counting clicks: rethinking engagement in digital mental health
Beyond counting clicks: rethinking engagement in digital mental health Open
Summary User engagement remains a challenge in digital mental health. This editorial reconsiders engagement as a process rather than an outcome, introducing a four-step model to define, measure and link engagement to outcomes. The approach…
H3-MOSAIC: multimodal generative AI for semantic place detection from high-frequency GPS on H3 grids in mental health geomatics Open
H3-MOSAIC provides a scalable, auditable pipeline for semantic place detection from high-frequency GPS. Multimodal fusion markedly improves accuracy and consistency. Proprietary models are most robust on hard classes and open-source models…
Five years of app evaluation: Insights from a framework in practice – a systematic review on the m-health index and navigation database Open
Our findings suggest that evidence and privacy concerns are prevalent across almost all health app categories, highlighting the need for stronger regulatory oversight and improved validation standards. MIND serves as a valuable tool for ev…
Mindbench.ai: an actionable platform to evaluate the profile and performance of large language models in a mental healthcare context Open
Individuals are increasingly utilizing large language model (LLM)-based tools for mental health guidance and crisis support in place of human experts. While AI technology has great potential to improve health outcomes, insufficient empiric…
Accelerating Digital Mental Health: The Society of Digital Psychiatry’s Three-Pronged Road Map for Education, Digital Navigators, and AI Open
Digital mental health tools such as apps, virtual reality, and artificial intelligence (AI) hold great promise but continue to face barriers to widespread clinical adoption. The Society of Digital Psychiatry, in partnership with JMIR Menta…
Evaluating the performance of general purpose large language models in identifying human facial emotions Open
We evaluated the ability of three leading LLMs (GPT-4o, Gemini 2.0 Experimental, and Claude 3.5 Sonnet) to recognize human facial expression using the NimStim dataset. GPT and Gemini matched or exceeded human performance, especially for ca…
View article: An AI-Based Behavioral Health Safety Filter and Dataset for Identifying Mental Health Crises in Text-Based Conversations
An AI-Based Behavioral Health Safety Filter and Dataset for Identifying Mental Health Crises in Text-Based Conversations Open
Large language models often mishandle psychiatric emergencies, offering harmful or inappropriate advice and enabling destructive behaviors. This study evaluated the Verily behavioral health safety filter (VBHSF) on two datasets: the Verily…
Smartphone Apps for Cardiovascular and Mental Health Care: Digital Cross-Sectional Analysis Open
Background The rapidly expanding digital health landscape offers innovative opportunities for improving health care delivery and patient outcomes; however, regulatory and clinical frameworks for evaluating their key features, effectiveness…
Accelerating Digital Mental Health: The Society of Digital Psychiatry’s Three-Pronged Roadmap for Education, Digital Navigators, and AI. (Preprint) Open
UNSTRUCTURED Digital mental health tools, including apps, virtual reality, and AI, show increasing evidence of benefit, yet their translation into routine clinical practice remains limited. To bridge this gap, the Society of Digital Psych…
Charting the evolution of artificial intelligence mental health chatbots from rule‐based systems to large language models: a systematic review Open
The rapid evolution of artificial intelligence (AI) chatbots in mental health care presents a fragmented landscape with variable clinical evidence and evaluation rigor. This systematic review of 160 studies (2020‐2024) classifies chatbot a…
Governing AI in Mental Health: 50-State Legislative Review Open
Background Mental health–related artificial intelligence (MH-AI) systems are proliferating across consumer and clinical contexts, outpacing regulatory frameworks and raising urgent questions about safety, accountability, and clinical integ…
Developing theory-informed implementation strategies to embed a suicide safety planning intervention app into a psychiatric emergency department: co-design study using the Behaviour Change Wheel Open
Background Safety planning is a commonly used, evidence-based intervention for suicide prevention. There is a need for continuous engagement with safety plans post-discharge, and the improvement of safety plan portability has been discusse…
Interpreting psychiatric digital phenotyping data with large language models: a preliminary analysis Open
Background Digital phenotyping provides passive monitoring of behavioural health but faces implementation challenges in translating complex multimodal data into actionable clinical insights. Digital navigators, healthcare staff who interpr…
View article: Barriers and facilitators to usability of a smartphone-based digital mental health tool in older adults: Insights from a secondary analysis of mindLAMP
Barriers and facilitators to usability of a smartphone-based digital mental health tool in older adults: Insights from a secondary analysis of mindLAMP Open
These findings suggest that with modest training, older adults can engage with digital health tools and report positive usability experiences. Differences in usability outcomes by sex, race, and education point to potential characteristics…
Leveraging Large Language Models and Patient Portal Messages for Early Identification of Depression Open
Importance Large language model (LLM)-assisted early warning system may help overcome existing barriers to timely depression diagnosis in patients with cardiovascular disease (CVD). This novel application of LLMs to screen patient messages…
Standardizing and Scaffolding Health Care AI-Chatbot Evaluation: Systematic Review Open
Background Health care chatbots are rapidly proliferating, while generative artificial intelligence (AI) outpaces existing evaluation standards. Objective We aimed to develop a structured, stakeholder-informed framework to standardize eval…
Sleep Estimation from Low Frequency Smartphone Sensors via Bayesian Hidden Markov Model Open
Sleep disturbances are recognized as transdiagnostic markers and potential mechanistic contributors to psychiatric illness, yet objective sleep monitoring remains rare in large-scale psychiatric research due to infrastructure and methodolo…
Telemedicine Special Registrations for Controlled Substances Open
This Viewpoint discusses the Drug Enforcement Agency’s aim to limit diversion of controlled substances with special registration requirements for telemedicine visits.