On Using Large Language Models to Enhance Clinically-Driven Missing Data Recovery Algorithms in Electronic Health Records

2025-10-04

AI Summary

Electronic health record (EHR) data frequently suffer from missing and erroneous entries, and conventional manual chart review is labor-intensive and poorly scalable. To address this, we propose a novel paradigm for missing-value imputation that synergistically integrates clinical knowledge with large language models (LLMs). Specifically, we construct a dynamic diagnostic anchor roadmap grounded in ICD-10 codes; the LLM generates auxiliary diagnostic hypotheses, which are iteratively refined by clinical experts to enhance the roadmap’s fidelity—thereby enabling automated, context-aware inference of critical missing values (e.g., laboratory results). This work establishes the first closed-loop, human-in-the-loop optimization framework wherein LLMs and clinicians co-evolve diagnostic reasoning for missing-data recovery. Evaluated on a cohort of 1,000 patients, our method achieves imputation accuracy comparable to or exceeding expert manual review, while substantially improving coverage breadth and inference precision. The approach demonstrates strong clinical deployability and scalability for real-world EHR systems.

Technology Category

• Humans and AI: Human-in-the-loop Machine Learning
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Objective: Electronic health records (EHR) data are prone to missingness and errors. Previously, we devised an "enriched" chart review protocol where a "roadmap" of auxiliary diagnoses (anchors) was used to recover missing values in EHR data (e.g., a diagnosis of impaired glycemic control might imply that a missing hemoglobin A1c value would be considered unhealthy). Still, chart reviews are expensive and time-intensive, which limits the number of patients whose data can be reviewed. Now, we investigate the accuracy and scalability of a roadmap-driven algorithm, based on ICD-10 codes (International Classification of Diseases, 10th revision), to mimic expert chart reviews and recover missing values. Materials and Methods: In addition to the clinicians' original roadmap from our previous work, we consider new versions that were iteratively refined using large language models (LLM) in conjunction with clinical expertise to expand the list of auxiliary diagnoses. Using chart reviews for 100 patients from the EHR at an extensive learning health system, we examine algorithm performance with different roadmaps. Using the larger study of $1000$ patients, we applied the final algorithm, which used a roadmap with clinician-approved additions from the LLM. Results: The algorithm recovered as much, if not more, missing data as the expert chart reviewers, depending on the roadmap. Discussion: Clinically-driven algorithms (enhanced by LLM) can recover missing EHR data with similar accuracy to chart reviews and can feasibly be applied to large samples. Extending them to monitor other dimensions of data quality (e.g., plausability) is a promising future direction.

Problem

• Enhancing missing data recovery in EHR using LLM-enhanced algorithms
• Automating expert chart reviews to handle EHR data incompleteness
• Scaling clinically-driven data imputation with large language models

Innovation

• Using large language models to expand clinical diagnosis roadmaps
• Applying ICD-10 code algorithms to recover missing EHR data
• Combining LLM suggestions with clinical expertise for validation