WangLab at MEDIQA-CORR 2024: Optimized LLM-based Programs for Medical Error Detection and Correction
This work addresses patient safety risks from medical errors in clinical documentation, but it is incremental as it builds on existing LLM and framework methods.
The paper tackled medical error detection and correction in clinical text, achieving top performance in all three subtasks of the MEDIQA-CORR 2024 shared task by developing retrieval-based and pipeline systems using LLM-based programs optimized with DSPy.
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.