193 papers
Analysis of over 19 million US patient records reveals that individuals with hypermobile Ehlers-Danlos Syndrome face a significantly elevated risk of developing Long COVID, particularly when overlapping with autonomic or immune dysregulation, and suggests that viral infections may often unmask previously undiagnosed cases of the disorder.
This study demonstrates that a collaborative approach combining multiple large language models significantly outperforms individual models in systematic review screening, achieving higher accuracy (99.9% precision and 98.5% recall) and reducing manual effort by 63.5%.
This study demonstrates that when carefully prompted, ChatGPT-4.0 outperforms human coders in generating high-quality, detailed, and complete descriptions of innovations within NIH grant abstracts focused on opioid addiction treatment.
This paper introduces Sino-US-DrugQA, a bilingual benchmark dataset of 11,871 questions derived from US and Chinese pharmaceutical regulations, which reveals that while current large language models perform well on monolingual regulatory queries, they face significant challenges in cross-jurisdictional comparative reasoning, necessitating expert oversight for high-stakes compliance applications.
In a study using ASPREE trial data, Random Survival Forests (RSF) demonstrated comparable discrimination and calibration to standard Random Forests (RF) for predicting disability-free longevity, suggesting that RSF does not always offer superior predictive accuracy over RF for time-to-event outcomes.
This study demonstrates that a standardized prompt-based framework achieves clinical-grade accuracy across five large language models from four independent vendors when analyzing biomarkers from 4,018 NHANES patients, confirming the feasibility of vendor-independent AI systems for clinical decision support.
This paper proposes and validates a hybrid model that integrates a Large Language Model with a Mixed-Integer Linear Programming solver to generate personalized, nutritionally accurate, and practical meal plans, demonstrating superior overall performance compared to standalone LLM or MILP approaches.
This paper presents a computational pipeline that combines asymmetric semantic aggregation of patient phenotypes with network propagation to improve the accuracy and clinical consistency of rare disease diagnosis, outperforming existing methods in identifying correct diagnoses and generating coherent differential hypotheses.
This matched pre-post study of over 6,000 clinical notes reveals that ambient AI documentation systems significantly alter the linguistic structure of History of Present Illness sections by increasing length, syntactic complexity, and coherence while reducing ambiguity, whereas effects on Assessment and Plan sections are minimal, highlighting the need to evaluate these tools beyond efficiency to consider their impact on communication, cognition, and downstream analytics.
This study utilizes a comprehensive "Sleep Chart" across 23 biological aging clocks to demonstrate that both short (<6 hours) and long (>8 hours) sleep durations are associated with accelerated biological aging, increased systemic disease risk, and higher mortality, whereas optimal sleep duration (6.4–7.8 hours) supports healthy aging and longevity.
Contrary to the prevailing assumption that retrieval-augmented generation (RAG) mitigates hallucinations, this study demonstrates that RAG significantly increases unsupported claims in clinical AI, whereas converting heterogeneous patient data into structured, provenance-tracked artifacts offers a more effective approach to ensuring factual accuracy and safety.
This study presents a deep learning framework based on a vision foundation model that not only accurately predicts retinal biological age from fundus images but also disentangles physiological heterogeneity by decomposing aging signals into normative and pathological components linked to systemic health factors like inflammation and hemodynamics.
This study developed and validated a highly accurate, scalable algorithm using electronic health record audit logs to identify the primary frontline clinician for each patient day, demonstrating 91% agreement with manual chart review and enabling the analysis of care continuity patterns across a large inpatient cohort.