Ensuring Reliability of Curated EHR-Derived Data: The Validation of Accuracy for LLM/ML-Extracted Information and Data (VALID) Framework

TL;DR

This paper introduces a comprehensive framework to evaluate the accuracy, reliability, and fairness of clinical data extracted by large language models from electronic health records, enhancing trustworthiness in oncology research.

Contribution

It presents a novel multidimensional validation framework specifically designed for LLM-extracted clinical data, addressing unique error modes and supporting bias assessment.

Findings

Framework enables variable-level performance benchmarking

Automated checks improve internal consistency and plausibility

Replication analyses confirm dataset fitness-for-purpose

Abstract

Large language models (LLMs) are increasingly used to extract clinical data from electronic health records (EHRs), offering significant improvements in scalability and efficiency for real-world data (RWD) curation in oncology. However, the adoption of LLMs introduces new challenges in ensuring the reliability, accuracy, and fairness of extracted data, which are essential for research, regulatory, and clinical applications. Existing quality assurance frameworks for RWD and artificial intelligence do not fully address the unique error modes and complexities associated with LLM-extracted data. In this paper, we propose a comprehensive framework for evaluating the quality of clinical data extracted by LLMs. The framework integrates variable-level performance benchmarking against expert human abstraction, automated verification checks for internal consistency and plausibility, and replication analyses comparing LLM-extracted data to human-abstracted datasets or external standards. This multidimensional approach enables the identification of variables most in need of improvement, systematic detection of latent errors, and confirmation of dataset fitness-for-purpose in real-world research. Additionally, the framework supports bias assessment by stratifying metrics across demographic subgroups. By providing a rigorous and transparent method for assessing LLM-extracted RWD, this framework advances industry standards and supports the trustworthy use of AI-powered evidence generation in oncology research and practice.