Thanks to pilot funding from the Duke Center for Computational and Digital Health Innovation, Jason Luck and his team taken a major step forward in researching youth head injuries.
Large language models (LLMs) excel on multiple-choice clinical diagnosis benchmarks, yet it is unclear how much of this performance reflects underlying probabilistic reasoning. We study this through questions from MedQA, where the task is to select the most likely diagnosis. We introduce the Frequency-Based Probabilistic Ranker (FBPR), a lightweight method that scores options with a…
Clinical communication is central to patient outcomes, yet large-scale human annotation of patient-provider conversation remains labor-intensive, inconsistent, and difficult to scale. Existing approaches based on large language models typically rely on single-task models that lack adaptability, interpretability, and reliability, especially when applied across various communication frameworks and clinical domains. In this study, we developed a…
Distribution shift can lead to degradation in the performance of machine learning models. This concern is particularly salient in medicine, in which several forces can lead to shifts in Electronic Health Record (EHR) data. Distribution shift in the text domain is vastly understudied, but increasingly important, given the widespread integration of large language models into…
Radiology reports contain essential clinical information but often remain in unstructured, free-text formats. Notably, multiple imaging examinations performed simultaneously (such as CT head, facial bones, and cervical spine in trauma cases) may be bundled into a single report that consolidates findings from all studies into one free-text document, written jointly. Because individual sentences may reference…
Clinical decision support tools built on electronic health records often experience performance drift due to temporal population shifts, particularly when changes in the clinical environment initially affect only a subset of patients, resulting in a transition to mixed populations. Such case-mix changes commonly arise following system-level operational updates or the emergence of new diseases, such…
Developing computable phenotypes (CP) based on electronic health records (EHR) data requires “gold-standard” labels for the outcome of interest. To generate these labels, clinicians typically chart-review a subset of patient charts. Charts to be reviewed are most often randomly sampled from the larger set of patients of interest. However, random sampling may fail to capture…
Calcitonin gene-related peptide (CGRP) inhibitors are increasingly used in the United States (US) for the prevention and treatment of migraine, but population-based data on their cardiovascular risk profile are lacking. Research Objective/Aims: To evaluate the association between CGRP inhibitor initiation and cardiovascular events. Methods: This was a retrospective, observational, cohort study using claims data from a proprietary,…
The Semaglutide and Cardiovascular Outcomes in Obesity without Diabetes (SELECT) trial showed that the glucagon-like peptide-1 receptor agonist (GLP1-RA) semaglutide was effective versus placebo for the secondary prevention of atherosclerotic cardiovascular disease. However, the comparative effectiveness of GLP-1RA versus other FDA-approved antiobesity medications (bupropion-naltrexone [BN] and phentermine-topiramate [PT]) has not been evaluated. Research Objective/Aims: To determine…
Multiple clinical trials have demonstrated that glucagon-like peptide 1 receptor agonists (GLP-1 Ras) improve symptoms, physical function, and potentially reduce hospitalizations in selected populations with HFpEF. However, the effectiveness of GLP-1 RAs in real-world populations with HFpEF is not well-characterized. Research Questions/Hypothesis: To evaluate the association between GLP-1 RA use and clinical outcomes in patients with…