Using records from 2,489 youth with type 2 diabetes and 4,018 with type 1 diabetes, CEDAR (Clinical Evidence-Driven Agent for Risk-prediction), an evidence-citing, self-auditing LLM pipeline, outperformed trained machine learning in both cohorts.
Abstract
Large language model (LLM) agents are proposed for clinical prediction but are untested in pediatrics, where cohorts are small and outcomes are uncommon. Using records from 2,489 youth with type 2 diabetes (T2D) and 4,018 with type 1 diabetes (T1D), spanning structured data, note-derived social determinants and, in T1D, continuous glucose monitoring data, we predicted seven T2D outcomes, four also in T1D, at 24 months from 18 months of follow-up. CEDAR (Clinical Evidence-Driven Agent for Risk-prediction), an evidence-citing, self-auditing LLM pipeline, outperformed trained machine learning in both cohorts (pooled area under the receiver operating characteristic curve 0.815 versus 0.656 to 0.700 in T2D and 0.756 versus 0.603 to 0.631 in T1D), most on the sparsely screened outcomes. Only 4 of 70,246 values it cited did not match the chart. Reading only the evidence and reasoning cited by CEDAR, two pediatric endocrinologists reached the same prediction as CEDAR in about nine of ten cases, agreeing with each other on 90.5%.
This independent study develops and evaluates an endto-end longitudinal diabetes-risk modeling pipeline using twelve years of annual health-check data from 6,892 Thai patients, developing a dual-track recommendation system: a horizonspecific pure-prediction leaderboard for passive patient-risk screening, and an interve...
This paper presents an explainable AI pipeline for diabetes screening that learns from non-laboratory, self-reported health indicators and then provides patient-specific, actionable risk rationales clinicians can audit and communicate. A deep neural classifier, gradient boosting, and a regularized logistic baseline are...
Mafaz Mohammed Nadherssa· International Journal of Int...· 0 citations
lectronic health records (EHRs) were primarily designed to document care, rather than forecast disease. Within
the past five years, research experts have queried whether machine learning can be used to mine the same records, including
lab values, years of diagnosis codes, clinical notes, and medication orders, to ident...
Nicolla Eddy Wopara· International Journal of Inn...· 0 citations
Introduction Early onset hypertension is often overlooked despite its association with lifelong cardiovascular disease risk. We developed an interpretable machine learning model to predict early onset hypertension in US adults using the 2022 Medical Expenditure Panel Survey, incorporating demographic, socioeconomic, he...
Li-Wei Wu, Kiyoung Kim, P. Washington et al.· Preventing Chronic Disease· 0 citations
Despite the model’s relatively good performance for those without hypertension, the positive predictive value was low, and a significant proportion of true cases remained undetected, suggesting tailored approaches to case-finding may be beneficial in ensuring equity across demographic groups.
Gloria Ihenetu, A. Alkhatib, Vesselin Novov et al.· Journal of Medical Internet...· 0 citations
Evidence on ML-based risk prediction models for T2DM applicable to primary care remains limited despite growing interest in AI for diabetes prediction; greater emphasis is needed on external validation, calibration, prospective implementation, and evaluation across diverse primary care populations before widespread cli...
Rashita Ravi, J. Olickal· Frontiers in Public Health· 0 citations
