A5005901640- Mental Health via Writing
- Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes
- Artificial Intelligence in Healthcare and Education
- Mental Health Research Topics
- Digital Mental Health Interventions
- Treatment of Major Depression
- Perfectionism, Procrastination, Anxiety Studies
- Healthcare Systems and Public Health
- Occupational Health and Safety Research
- Migration, Health and Trauma
- Machine Learning in Healthcare
- Mental Health Treatment and Access
- Functional Brain Connectivity Studies
- Electroconvulsive Therapy Studies
- Child and Adolescent Psychosocial and Emotional Development
- Misinformation and Its Impacts
- Cardiac Health and Mental Health
- EEG and Brain-Computer Interfaces
- Optimism, Hope, and Well-being
- Telemedicine and Telehealth Implementation
- Topic Modeling
- Pharmacological Receptor Mechanisms and Effects
- Opinion Dynamics and Social Influence
- Tryptophan and brain disorders
University of Pennsylvania
2019-2025
Stanford University
2024
National Center for PTSD
2024
VA Palo Alto Health Care System
2024
South University
2023
Icahn School of Medicine at Mount Sinai
2016-2017
Abstract Large language models (LLMs) such as Open AI’s GPT-4 (which power ChatGPT) and Google’s Gemini, built on artificial intelligence, hold immense potential to support, augment, or even eventually automate psychotherapy. Enthusiasm about applications is mounting in the field well industry. These developments promise address insufficient mental healthcare system capacity scale individual access personalized treatments. However, clinical psychology an uncommonly high stakes application...
Depression has robust natural language correlates and can increasingly be measured in using predictive models. However, despite evidence that use varies as a function of individual demographic features (e.g., age, gender), previous work not systematically examined whether how depression's association with by race. We examine race moderates the relationship between (i.e., first-person pronouns negative emotions) from social media posts self-reported depression, matched sample Black White...
Large language models (LLMs) such as Open AI’s GPT-3 and -4 (which power ChatGPT) Google’s PaLM, built on artificial intelligence, hold immense potential to support, augment, or even eventually fully automate psychotherapy. Enthusiasm about applications is mounting in the field well industry. These developments promise address insufficient mental healthcare system capacity scale individual access personalized treatments. However, clinical psychology an uncommonly high stakes application...
Clinical scientists disagree about whether worry and rumination are distinct or represent a unitary construct. To inform this debate, we performed series of meta-analyses evaluating the relationship between different forms rumination. A total 719 effect sizes ( N = 69,305) were analyzed. Worry showed large association with global brooding emotion-focused subtypes rs .51–.53). However, even when corrected for measurement error, correlations did not approach unity (ρs .57–.62). smaller, though...
Depression has been associated with heightened
There is growing scientific excitement about detecting depression from people’s language use, but this work rarely accounts for anxiety, which overlaps substantially and co-occurs frequently with depression. Using clinical interviews individuals varying levels of we found that some patterns are shared by these conditions, whereas other distinguish them. Depressed show more I-usage (e.g., “I,” “me,” “my”) sadness words “low,” “sad,” “alone”), while anxious use a much broader array negative...
Perseverative thinking (PT), or repetitive negative thinking, has historically been measured using global self-report scales. New methods of assessment are needed to advance understanding this inherently temporal process. We developed an intensive longitudinal method for assessing PT. A mixed sample 77 individuals ranging widely in trait PT, including persons with PT-related disorders (generalized anxiety disorder, major depression) and without psychopathology, used a joystick provide...
Use of large language models such as ChatGPT (GPT-4) for mental health support has grown rapidly, emerging a promising route to assess and help people with mood disorders, like depression. However, we have limited understanding GPT-4's schema that is, how it internally associates interprets symptoms. In this work, leveraged contemporary measurement theory decode GPT-4 interrelates depressive symptoms inform both clinical utility theoretical understanding. We found assessment depression: (a)...
Artificial intelligence (AI), particularly large language models (LLMs), has garnered significant attention for their potential to augment and possibly even replace current forms of psychological assessment or treatment. However, AI technologies have yet demonstrate the capacity effect lasting change. This paper outlines five key criteria developing effective clinical psychology interventions, grounded in science principles emerging evidence from mental health field: 1) attending mechanisms...
Though evidence-based treatments are effective, existing dissemination efforts expensive and difficult to scale. Novel solutions— especially those that offer active learning strategies, repeat skill practice personalized feedback therapists — needed fill this gap. To address this, we developed TherapyTrainer, which uses large language models (LLMs) allow delivering written exposure therapy (WET) for PTSD AI-Patients while receiving expert from an AI-Consultant. Here present initial...
Depression has robust natural language correlates, and can increasingly be measured in using predictive models. However, despite evidence that use varies as a function of individual demographic features (e.g., age, gender), previous work not systematically examined whether how depression’s association with by race. Here, we race moderates the relationship between (i.e., first-person pronouns negative emotions) self-reported depression, matched sample Black White participants. Analyses...
The current classification of anxiety is cumbersome; does not align with evidence that problems cut across disorder categories; and fails to acknowledge severity matters, even at low levels. We developed a new distills key features – intensity, avoidance, pervasiveness, onset disorders, allowing any individual be located along gradient from none severe for each feature. This transdiagnostic dimensional approach much simpler than the DSM anxiety, incorporates information about severity,...
The current conceptualization of anxiety in the Diagnostic and Statistical Manual Mental Disorders, Fifth Edition (DSM-5)-which includes 11 disorders plus additional anxiety-related conditions-does not align with accumulating evidence that is transdiagnostic dimensional nature. Transdiagnostic models have been proposed, yet they measure at either a very broad (e.g., "anxiety") or narrow "performance anxiety") level, overlooking intermediate properties cut across DSM disorders. Using...