A5035429361- Machine Learning in Healthcare
- Mental Health Research Topics
- Schizophrenia research and treatment
- Dementia and Cognitive Impairment Research
- Biomedical Text Mining and Ontologies
- Bipolar Disorder and Treatment
- Mental Health via Writing
- Chronic Disease Management Strategies
- Topic Modeling
- Genetic Associations and Epidemiology
- Health Systems, Economic Evaluations, Quality of Life
- Treatment of Major Depression
- Mental Health Treatment and Access
- Advanced Causal Inference Techniques
- Diet and metabolism studies
- Digital Mental Health Interventions
- Suicide and Self-Harm Studies
- Diabetes Treatment and Management
- Explainable Artificial Intelligence (XAI)
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Obesity and Health Practices
- Healthcare Decision-Making and Restraints
- Cancer survivorship and care
- Obsessive-Compulsive Spectrum Disorders
- Homicide, Infanticide, and Child Abuse
Massachusetts General Hospital
2020-2025
Harvard University
2015-2025
Broad Institute
2020-2025
Mass General Brigham
2024
Massachusetts Institute of Technology
2020
National Taiwan University
2010
Antidepressant selection is largely a trial-and-error process. We used electronic health record (EHR) data and artificial intelligence (AI) to predict response four antidepressants classes (SSRI, SNRI, bupropion, mirtazapine) 4 12 weeks after antidepressant initiation. The final set comprised 17,556 patients. Predictors were derived from both structured unstructured EHR models accounted for features predictive of treatment minimize confounding by indication. Outcome labels through expert...
<sec> <title>BACKGROUND</title> The integration of large language models (LLMs) in mental health care is an emerging field. There a need to systematically review the application outcomes and delineate advantages limitations clinical settings. </sec> <title>OBJECTIVE</title> This aims provide comprehensive overview use LLMs care, assessing their efficacy, challenges, potential for future applications. <title>METHODS</title> A systematic search was conducted across multiple databases including...
Importance With the rising prevalence of mental disorders among children and adolescents, identifying modifiable associations is critical. Objective To examine association between physical fitness disorder risks. Design, Setting, Participants This nationwide cohort study used data from Taiwan National Student Fitness Tests Health Insurance Research Databases January 1, 2009 to December 31, 2019. were divided into 2 cohorts targeting anxiety depression (1 996 633 participants)...
Background Strong and consistent associations between access to firearms suicide have been found in ecologic individual-level observational studies. For adolescents, a seminal case–control study estimated that living home with (vs without) firearm was associated fourfold increase the risk of death by suicide. Methods We use data from nationally representative 10 123 US adolescents aged 13–18 years (1) measure how much who live differ those do not ways related their suicide, (2) incorporate...
Abstract Metformin, a diabetes drug with anti-aging cellular responses, has complex actions that may alter dementia onset. Mixed results are emerging from prior observational studies. To address this complexity, we deploy causal inference approach accounting for the competing risk of death in emulated clinical trials using two distinct electronic health record systems. In intention-to-treat analyses, metformin use associates lower hazard all-cause mortality and cause-specific onset, after...
Abstract Bipolar disorder is a leading contributor to disability, premature mortality, and suicide. Early identification of risk for bipolar using generalizable predictive models trained on diverse cohorts around the United States could improve targeted assessment high individuals, reduce misdiagnosis, allocation limited mental health resources. This observational case-control study intended develop validate as part multisite, multinational PsycheMERGE Network across large biobanks with...
Background Early identification of bipolar disorder (BD) provides an important opportunity for timely intervention. In this study, we aimed to develop machine learning models using large‐scale electronic health record (EHR) data including clinical notes predicting early‐onset BD. Methods Structured and unstructured were extracted from the longitudinal EHR Mass General Brigham system. We defined three cohorts aged 10–25 years: (1) full youth cohort ( N = 300,398); (2) a subcohort by having...
Current clinician-based and automated risk assessment methods treat the of suicide-related behaviors (SRBs) as static, while in actual clinical practice, SRB fluctuates over time. Here, we develop two closely related model classes, Event-GRU-ODE Event-GRU-Discretized, that can predict dynamic events a continuous trajectory across future time points, even without new observations, updating these estimates data become available. Models were trained validated for prediction using large...
Background Selective serotonin reuptake inhibitors (SSRIs) were recently approved by the FDA to treat vasomotor symptoms associated with menopause. No prior study has directly examined whether fracture risk is increased among perimenopausal women who initiate SSRIs or a population of without mental disorders more generally. Methods Female patients illness, aged 40–64 years, initiated compared cohort H2 antagonists (H2As) proton-pump (PPIs) in 1998–2010, using data from claims database....
Growing evidence has shown that applying machine learning models to large clinical data sources may exceed clinician performance in suicide risk stratification. However, many existing prediction either suffer from "temporal bias" (a bias stems using case-control sampling) or require training on all available patient visit data. Here, we adopt a "landmark model" framework aligns with practice for of suicide-related behaviors (SRBs) electronic health record database. Using the landmark...
Hospital-based biobanks are being increasingly considered as a resource for translating polygenic risk scores (PRS) into clinical practice. However, since these originate from patient populations, there is possibility of bias in estimation due to overrepresentation patients with higher frequency healthcare interactions.PRS schizophrenia, bipolar disorder, and depression were calculated using summary statistics the largest available genomic studies sample 24 153 European ancestry participants...
Abstract Objective Early identification of bipolar disorder (BD) provides an important opportunity for timely intervention. In this study, we aimed to develop machine learning models using large-scale electronic health record (EHR) data including clinical notes predicting early-onset BD. Method Structured and unstructured were extracted from the longitudinal EHR Mass General Brigham system. We defined three cohorts aged 10 – 25 years: (1) full youth cohort (N=300,398); (2) a sub-cohort by...
The feasible intervention strategy at the prodromal state of psychosis is under debate. We report nine subjects clinically in a putative who responded to low‐dose aripiprazole within first week medication. conjecture that pathophysiological processes might be easier modify by antipsychotics and we believe short‐term trial antipsychotic agents convenient option for ultra high risk psychosis. urge specific attention monitor dissolution psychotic‐like symptoms carefully order have better...
ABSTRACT Metformin, an antidiabetic drug, triggers anti-aging cellular responses. Aging is the principal risk factor for dementia, but previous observational studies of diabetes drugs metformin vs. sulfonylureas have been mixed. We tested hypotheses that improves survival and reduces relative to sulfonylureas, by emulating target trials in electronic health records diabetic patients at academic-centered healthcare system US a wide-ranging group primary care practices UK. To address...
ABSTRACT Background Hospital-based biobanks have become an increasingly prominent resource for evaluating the clinical impact of disease-related polygenic risk scores (PRS). However, biobank cohorts typically rely on selection volunteers who may differ systematically from non-participants. Methods PRS weights schizophrenia, bipolar disorder, and depression were derived using summary statistics largest available genomic studies. These then calculated in a sample 24,153 European ancestry...
Suicide is one of the leading causes death in US, and number attributable deaths continues to increase. Risk suicide-related behaviors (SRBs) dynamic, SRBs can occur across a continuum time locations. However, current SRB risk assessment methods, whether conducted by clinicians or through machine learning models, treat as static are confined specific times locations, such following hospital visit. Such paradigm unrealistic fluctuates creates gaps availability scores. Here, we develop two...
Timely diagnosis of dementia is important to patients and their caregivers for advanced planning, yet under-diagnosed by healthcare professionals under-coded in claims data. Sensitive specific tools detect cognitive concerns diverse clinical settings could prompt referral evaluation specialist care.We developed a deep learning natural language processing (NLP) method unstructured clinician notes from electronic health records (EHR). We leveraged gold-standard set ∼1000 sampled randomly three...
Bipolar disorder is a leading contributor to disability, premature mortality, and suicide. Early identification of risk for bipolar using generalizable predictive models trained on diverse cohorts around the United States could improve targeted assessment high individuals, reduce misdiagnosis, allocation limited mental health resources. This observational case-control study intended develop validate as part multisite, multinational PsycheMERGE Consortium across large biobanks with linked...
ABSTRACT Efficient, accurate phenotyping for antidepressant treatment response in electronic health records (EHRs) could facilitate precision psychiatry applications but remains a challenge. Increasingly, artificial intelligence methods using “deep learning” applied to clinical data have shown promise complex classification problems. Here, we systematically evaluate the performance of eight deep-learning-based natural language processing models classifying antidepressants large real-world...
Dementia is a neurodegenerative disorder that causes cognitive decline and affects more than 50 million people worldwide. under-diagnosed by healthcare professionals - only one in four who suffer from dementia are diagnosed. Even when diagnosis made, it may not be entered as structured International Classification of Diseases (ICD) code patient's charts. Information relevant to impairment (CI) often found within electronic health records (EHR), but manual review clinician notes experts both...