Research
Explore our publications and preprints advancing healthcare through rigorous AI evaluation.
SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care
Large language models (LLMs) deployed in clinical decision support risk acquiescing to patient pressure for guideline-discordant care. We developed SycoEval-EM, […]
Teaching large language models to reason like expert diagnosticians
Differential diagnosis is an iterative process that integrates patient information with broader medical knowledge. Clinical case series such as the […]
Towards Conversational Medical AI with Eyes, Ears and a Voice
The practice of medicine relies not only upon skillful dialogue but also on the nuanced exchangeand interpretation of rich auditory […]
Deployment and Evaluation of an EHR-integrated, Large Language Model-Powered Tool to Triage Surgical Patients
Surgical co-management (SCM) is an evidence-based model in which hospitalists jointly manage medically complex perioperative patients alongside surgical teams. Despite […]
Clinician input steers frontier AI models toward both accurate and harmful decisions
Large language models (LLMs) are entering clinician workflows, yet evaluations rarely measure how clinician reasoning shapes model behavior during clinical […]
MedAgentBrief for Hospital Course Summarization: Safety, Use, and Discharge Documentation Burden
Importance: High-quality discharge summaries are essential for safe care transitions but contribute substantially to clinician documentation burden and burnout. While […]
Adoption and Use of LLMs at an Academic Medical Center
While large language models (LLMs) can support clinical documentation needs, standalone tools struggle with “workflow friction” from manual data entry. […]
MedAgentBench v2: Improving Medical LLM Agent Design
MedAgentBench is the first benchmark for evaluating LLM agents on clinical tasks in a FHIR-compliant EHR. In this paper, we […]
SmartAlert: Implementing Machine Learning-Driven Clinical Decision Support for Inpatient Lab Utilization Reduction
Repetitive laboratory testing unlikely to yield clinically useful information is a common practice that burdens patients and increases healthcare costs. […]
First, do NOHARM: towards clinically safe large language models
Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain […]
Latest News
View allGet the latest on our studies, grant awards, and media coverage.
