A5069204117- Machine Learning in Healthcare
- HIV/AIDS Research and Interventions
- Adolescent Sexual and Reproductive Health
- Artificial Intelligence in Healthcare
- Artificial Intelligence in Healthcare and Education
- Pharmaceutical Practices and Patient Outcomes
- Liver Disease Diagnosis and Treatment
- HIV, Drug Use, Sexual Risk
- Heart Failure Treatment and Management
- Health, Environment, Cognitive Aging
- Advanced Causal Inference Techniques
- Mobile Health and mHealth Applications
- HIV/AIDS drug development and treatment
- Blood Pressure and Hypertension Studies
- Electronic Health Records Systems
- Healthcare cost, quality, practices
- Receptor Mechanisms and Signaling
- Ethics in Clinical Research
- Explainable Artificial Intelligence (XAI)
- HIV Research and Treatment
- Machine Learning and Data Classification
- Primary Care and Health Outcomes
- Sex work and related issues
- Chronic Disease Management Strategies
- Neural dynamics and brain function
University of North Carolina at Chapel Hill
2018-2023
Emory University
2021
Centers for Disease Control and Prevention
2021
Public Health Department
2020
Massachusetts Institute of Technology
2012
Habits tend to form slowly but, once formed, can have great stability. We probed these temporal characteristics of habitual behaviors by intervening optogenetically in forebrain habit circuits as rats performed well-ingrained runs a T-maze. trained perform maze habit, confirmed the behavior devaluation tests, and then, during ( ca. 3 s), we disrupted population activity small region medial prefrontal cortex, infralimbic cortex. In accordance with evidence that this is necessary for...
Machine learning (ML) has seen impressive growth in health science research due to its capacity for handling complex data perform a range of tasks, including unsupervised learning, supervised and reinforcement learning. To aid researchers understanding the strengths limitations ML facilitate integration into their studies, we present here guideline integrating an analysis through structured framework, covering steps from framing question study design techniques specialized types.
Identifying optimal medical treatments to improve survival has long been a critical goal of pharmacoepidemiology. Traditionally, we use an average treatment effect measure compare outcomes between plans. However, new methods leveraging advantages machine learning combined with the foundational tenets causal inference are offering alternative effect. Here, three unique, precision medicine algorithms (random forests, residual weighted learning, efficient augmentation relaxed learning) identify...
Abstract Introduction HIV care and treatment in cross‐border areas East Africa face challenges perhaps not seen to the same extent other geographic areas, particularly for mobile migrant populations. Here, we estimate proportion of people with found these each stage cascade, including who knows their status, on virally suppressed. Methods Participants (n = 11,410) working or socializing public places selected cross border were recruited between June 2016 February 2017 using Priorities Local...
Abstract Background Transmitted drug resistance (TDR) compromises clinical management and outcomes. surveillance identification of growing transmission clusters are needed in the Southeast, epicenter US HIV epidemic. Our study investigated prevalence dynamics North Carolina. Methods We analyzed mutations (SDRMs) using partial pol sequences from patients presenting to 2 large outpatient clinics 1997 2014. was defined as ≥1 SDRMs among antiretroviral therapy (ART)–naïve patients. Binomial...
Abstract Introduction East African cross‐border areas are visited by mobile and vulnerable populations, such as men, female sex workers, men who have with truck drivers, fisher folks young women. These groups may not benefit from traditional HIV prevention interventions available at the health facilities where they live, but services offered public venues identified places people meet new sexual partners (e.g. bars, nightclubs, transportation hubs guest houses). The goal of this analysis was...
Statistical Modeling:The Two Cultures was first published, algorithmic modeling techniques have gone from controversial to commonplace in the statistical community.While widespread adoption of these methods as part contemporary statistician's toolkit is a testament Dr. Breiman's vision, number high-profile failures models suggests that final remark "the emphasis needs be on problem and data" has been less widely heeded.In spirit Breiman, we detail an emerging research community statistics...
<sec> <title>UNSTRUCTURED</title> Machine learning (ML) has seen impressive growth in health science research due to its capacity for handling complex data perform a range of tasks including unsupervised learning, supervised and reinforcement learning. To aid researchers understanding the strengths limitations ML, facilitate integration into their studies, we present here guideline integrating ML an analysis as well brief primer extra details supplement. This paper will touch on not only...