Psychiatry

A Foundation Model for Wearable Movement Data in Mental Health Research.

Wearable movement data is collected by nearly all commercially available smartwatches and is a valuable resource for mental health research, reflecting fine-grained temporal behavioral trends. Despite its promise, the development of foundation models for health wearable modeling remains limited when compared to clinical image and text analysis. We designed transformers with patch embeddings and us...

Detection of Posttraumatic Stress Disorder With Rest-Activity Data: Machine Learning Approach Using Wearable and Self-Report Data.

BACKGROUND: Growing evidence suggests that disruptions in rest-activity rhythms may serve as relevant markers of posttraumatic stress disorder (PTSD). Despite the emergence of machine learning methods applied to actigraphy and self-report data, few studies have used these approaches to identify individuals with clinically diagnosed PTSD. Prior work has focused on predicting probable PTSD based on ...

Determinants of Medical Help-Seeking Behavior Following Case Finding of Early Cognitive Impairment: Semistructured Interview Study of Patients and Caregivers.

BACKGROUND: Timely medical follow-up after a diagnosis of cognitive impairment, such as mild cognitive impairment (MCI) or dementia, is imperative for...

AI-guided integration of aging-related functional assessment to predict nonresponse to cardiac rehabilitation in heart failure.

BACKGROUND: Cardiac rehabilitation (CR) improves functional capacity and outcomes in patients with heart failure (HF). However, a clinically significa...

Automated Safety Testing and Reporting Application for Conversational Safety Monitoring of Generative AI Tools for Mental Health: Development and Validation Study.

BACKGROUND: Artificial intelligence (AI)-based conversational tools are rapidly expanding within mental health care as a means of increasing access an...

The association of early life experiences with prenatal depression: A machine learning-based predictive model.

BACKGROUND: Prenatal depression is highly prevalent and associated with early-life adversities like adverse childhood experiences (ACEs) and school bu...

From EEG signals to quantitative assessment: predicting depression severity using a novel deep learning framework.

The assessment of depression severity still relies primarily on subjective rating scales, with a lack of objective quantitative biomarkers. This study...

Urinary copper is linked to regional cortical volume reductions in adolescents with major depressive disorder.

Major depressive disorder (MDD) is highly prevalent among adolescents, but its neurobiological mechanisms remain unclear. Neuroimaging studies have sh...

Bridging pediatric to adult care in cystinosis: a scoping review of healthcare transition of care protocols and a roadmap for future practice.

Cystinosis is a rare lysosomal storage disorder that affects approximately 1 in 100,000 to 200,000 live births worldwide. Long-term graft success in c...

The multilevel exploration test, a novel paradigm to measure exploratory behavior in depression animal models and the involvement of the PL-ZI circuit.

Diminished drive is one of the core symptoms of major depressive disorder (MDD) diagnosis, yet its underlying neural mechanisms remain elusive, primar...

Personalized machine learning guided intervention for optimizing lifestyle behaviors in depression: a pilot study.

Personalized data-driven interventions for depression are much needed. Here, we leveraged N-of-1 machine learning (ML) to optimally target behavioral ...

Application of artificial intelligence-assisted education for postoperative pulmonary rehabilitation: a hybrid model of AI and nurse-driven support.

OBJECTIVE: To explore the clinical value of AI-assisted pulmonary rehabilitation education in patients undergoing thoracoscopic surgery for lung cance...

Mitigating Bias in Multi-Label Medical Text Classification: A Cooperative Training Framework with Dynamic Debiasing.

MOTIVATION: Medical text classification plays a critical role in clinical decision support, automated diagnosis, and biomedical research. However, dee...

A Doubly Robust Machine Learning Procedure to Estimate Disparities by Race/Ethnicity and Sex in the Relationship Between Adverse Childhood Experiences and Suicidality.

OBJECTIVE: Suicide is a leading cause of death among youth, and adverse childhood experiences (ACEs) are established risk factors for suicidality. Thi...

Leveraging Machine Learning and Network Biology Approaches to Predict Brain Gene Expression from Blood Transcriptomes.

Blood-based biomarkers offer a promising non-invasive strategy for detecting disease-related changes and monitoring tissue and organ health, including...

Using smartphone surveys to predict next-week suicide attempts.

Clinicians are tasked with predicting and preventing suicidal behavior among their patients; however, there is currently no method for accurately pred...

Chatbot relational dependence and psychosis risk: Conversational artificial intelligence as a potential behavioral addiction context.

Conversational artificial intelligence (AI) chatbots are increasingly used for emotional support, companionship, and psychological reflection. Their c...

Large Language Models in Mental Health Research and Treatment.

Mental health challenges add immensely to the global burden of disease, yet traditional approaches to psychological assessment and care remain resourc...

A contrastive reconstruction vision transformer model for intelligent diagnosis of autism spectrum disorder.

Automated assessment through the analysis of facial expressions in autism can assist in early screening, providing strong support for timely intervent...

Genital-prioritized attentional bias in lifelong premature ejaculation: behavioral evidence from eye-tracking and machine learning.

Lifelong premature ejaculation (LPE) involves altered responses to sexual cues. Neuroimaging has identified attention-related neural abnormalities in ...