Evaluating the Readability of Pediatric Neurocutaneous Syndromes-Related Patient Education Material Created by a Custom GPT With Retrieval Augmentation.

Journal: JMIR dermatology
Published Date:

Abstract

In our study, we developed a GPT assistant with a custom knowledge base for neurocutaneous diseases, tested its ability to answer common patient questions, and showed that a GPT using retrieval augmentation generation can improve the readability of patient educational material without being prompted for a specific reading level.

Authors

  • Nneka Ede
    Department of Biomedical Engineering, Cockrell School of Engineering, The University of Texas at Austin, 1500 Red River Street, Austin, TX, 78701, United States, +15124955555.
  • Robyn Okereke
    Department of Dermatology, Oregon Health and Sciences University, Portland, OR, United States.