Can GPT-3.5 generate and code discharge summaries?
Matúš FalisAryo Pradipta GemaHang DongLuke DainesSiddharth BasettiMichael HolderRose S PenfoldAlexandra BirchBeatrice AlexPublished in: Journal of the American Medical Informatics Association : JAMIA (2024)
While GPT-3.5 alone given our prompt setting is unsuitable for ICD-10 coding, it supports data augmentation for training neural models. Augmentation positively affects generation code families but mainly benefits codes with existing examples. Augmentation reduces out-of-family errors. Documents generated by GPT-3.5 state prompted concepts correctly but lack variety, and authenticity in narratives.