WangLab at MEDIQA-CORR 2024: Optimized LLM-based Programs for Medical Error Detection and Correction

TL;DR

This paper presents WangLab's approach using optimized LLM-based programs for medical error detection and correction, achieving top performance in the MEDIQA-CORR 2024 shared task across three subtasks with different datasets.

Contribution

We introduce a retrieval-based system and a modular pipeline leveraging DSPy for prompt optimization, advancing LLM applications in medical error correction.

Findings

Achieved top performance in all three MEDIQA-CORR 2024 subtasks.

Effective use of external datasets and prompt optimization techniques.

Limitations remain in handling the full diversity of medical errors.

Abstract

Medical errors in clinical text pose significant risks to patient safety. The MEDIQA-CORR 2024 shared task focuses on detecting and correcting these errors across three subtasks: identifying the presence of an error, extracting the erroneous sentence, and generating a corrected sentence. In this paper, we present our approach that achieved top performance in all three subtasks. For the MS dataset, which contains subtle errors, we developed a retrieval-based system leveraging external medical question-answering datasets. For the UW dataset, reflecting more realistic clinical notes, we created a pipeline of modules to detect, localize, and correct errors. Both approaches utilized the DSPy framework for optimizing prompts and few-shot examples in large language model (LLM) based programs. Our results demonstrate the effectiveness of LLM based programs for medical error correction. However, our approach has limitations in addressing the full diversity of potential errors in medical documentation. We discuss the implications of our work and highlight future research directions to advance the robustness and applicability of medical error detection and correction systems.