# MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters

Source: [MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters](<https://www.sota2.com/research/paper/68fa76d21e209131cea6f491>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:03:16.343Z

Authors: Amin Dada, Osman Alperen Koras, Marie Bauer, Amanda Butler, Kaleb E. Smith, Jens Kleesiek, Julian Friedrich

Published: 2025-02-05T15:56:37.000Z

## Abstract

While increasing patients' access to medical documents improves medical care, this benefit is limited by varying health literacy levels and complex medical terminology. Large language models (LLMs) offer solutions by simplifying medical information. However, evaluating LLMs for safe and patient-friendly text generation is difficult due to the lack of standardized evaluation resources. To fill this gap, we developed MeDiSumQA. MeDiSumQA is a dataset created from MIMIC-IV discharge summaries through an automated pipeline combining LLM-based question-answer generation with manual quality checks. We use this dataset to evaluate various LLMs on patient-oriented question-answering. Our findings reveal that general-purpose LLMs frequently surpass biomedical-adapted models, while automated metrics correlate with human judgment. By releasing MeDiSumQA on PhysioNet, we aim to advance the development of LLMs to enhance patient understanding and ultimately improve care outcomes.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.03298>)

[PDF](<https://arxiv.org/pdf/2502.03298.pdf>)
