Review

Evaluating a large language model for identifying key comorbidities in discharge summaries of patients with obesity: a comparative validation study against ICD codes using MIMIC-IV.

T. Suenghataiphorn Kanachai Boonpiraks Vitchapong Prasitsumrit N. Kulthamrongsri Pojsakorn Danpanichkul

Jul 2026 · International Journal of Obesity · 0 citations · 20 references

Medicine

TL;DR

The LLM showed promising concordance with ICD codes for T2DM, HTN, OSA, and HLD in obesity patient discharge summaries, including against ICD-9/10 coding and against manual review.

DOI PubMed Semantic Scholar

View source

Similar papers

Open access Sep 2026

Integrating structured and unstructured EHR data to characterize social and behavioral factors associated with frequent emergency department use among patients with cardiovascular disease

Objective: The goal was to integrate structured and unstructured data from the electronic health record (EHR) to identify social and behavioral determinants of health (SBDH) factors and evaluate their association with high emergency department (ED) utilization among cardiovascular disease (CVD) patients. Methods: A cus...

T. Metzger, S. Morrell, S. Roy et al. · medRxiv · 0 citations

Aug 2026

Journal of Health Economics and Outcomes Research

ICD-10-CM codes demonstrate high specificity and PPV but low sensitivity, indicating that while coded cases are likely true obesity, many patients with obesity are not captured in claims.

Effie L. Kuti, Emma L. Richard, K. Schott et al. · Journal of health economics... · 0 citations

Open access Aug 2026

Diagnostic accuracy of electronic medical record retrieval methods and a large language model for identifying cardiovascular events: a multisite retrospective validation study in a medical system in the United States

In this multisite retrospective validation study, the LLM-assisted workflow showed strong but context-dependent performance for identifying cardiovascular events from the EMR, and ICD-based retrieval remained competitive for some use cases.

Omar H. Ibrahim, J. Farina, Milagros Pereyra Pietri et al. · BMJ Open · 0 citations

Open access Sep 2026

medicalcoder: a unified and longitudinally aware framework for International Classification of Diseases code-based comorbidity assessment in R

The developed medicalcoder package provides a unified, reproducible framework for ICD-based comorbidity assessment in modern clinical datasets.

Peter E. Dewitt, Seth Russell, James A. Feinstein et al. · JAMIA Open · 0 citations

Open access Sep 2026

Agreement Between ICD-10 Code–Only and Composite Definitions of Asthma Exacerbations in Electronic Health Records: A Multicenter Cohort Study in Taiwan, 2017-2023

ICD-10 code–only definition demonstrated high overall agreement with the composite definition, driven primarily by agreement on non-events, but limited agreement for identified exacerbations, suggesting that the two definitions may capture different levels of exacerbations.

Chun-Tse Hung, Cheng An, Chi-Won Suk · Clinical Epidemiology · 0 citations

Open access Sep 2026

Is It Feasible to Assess Clinical Remission in Asthma via a Customized Data Extraction Approach from a Real-World Clinical Electronic Medical Records Database in Japan? A Retrospective Real-World Study.

It may be feasible to assess CR using EMR data in Japanese patients with asthma, however, infrequent recording of CR components in clinical practice, particularly ACT and lung function tests, limits availability of EMR data for CR assessments and the potential generalizability of CR findings.

H. Nagase, T. Sakagami, Masashi Takano et al. · Journal of Asthma · 0 citations