Enhancing patient Comprehension: An effective sequential prompting approach to simplifying EHRs using LLMs
Mahshad Koohi H. Dehkordi, Shuxin Zhou, Yehoshua Perl, Fadi P. Deek, Andrew Jeffrey Einstein, Gai Elhanan, Zhe He, Hao Liu · 2024
Electronic Health Record (EHR) notes often contain complex medical language, making them difficult to understand for patients lacking medical background. Simplifying EHR notes to a 6th-grade reading level is recommended by the American Medical Association to enhance patient comprehension and engagement. Large Language Models (LLMs) show promise in achieving this goal but also face challenges, such as missing and generating false information. In our previous work, we have shown that providing LLMs with highlighted EHRs, where the important information is highlighted, results in more accurate summaries compared to summarizing unhighlighted notes. In this study, we simplify highlighted EHRs with LLMs, specifically ChatGPT-4o, using two approaches: two-step simplification (sequential) and one-step (CoT-based) simplification. In the sequential approach, we generate a structured summary of the highlighted EHR, as a first step, and then we convert this summary into language suitable for a 6th-grade reader, as a second step. In the CoT-based approach, we convert the highlighted EHR into a structured summary understandable for a 6th-grade reader in one step. Evaluating the simplified notes obtained from the two approaches, the sequential approach shows higher completeness (82.35% vs. 75.89%) and correctness, as well as better readability scores (FKGL: 7.72 vs. 10.73; Flesch: 67.71 vs. 45.31) and higher average understandability ratings from ChatGPT-4 (3.92 vs. 3.28), demonstrating its overall superiority in simplifying notes.