Assessment of Pathology Domain-Specific Knowledge of ChatGPT and Comparison to Human Performance.
Andrew Y WangSherman LinChristopher TranRobert J HomerDan WilsdonJoanna C WalshEmily A GoebelIrene SansanoSnehal SonawaneVincent CockenpotSanjay MukhopadhyayToros TaskinNusrat ZahraLuca CimaOrhan SemerciBirsen Gizem ÖzamrakPallavi MishraNaga Sarika VennavalliPo-Hsuan Cameron ChenMatthew J CecchiniPublished in: Archives of pathology & laboratory medicine (2024)
By demonstrating the ability of ChatGPT to answer pathology-specific questions at a level similar to (GPT-3.5) or exceeding (GPT-4) a trained pathologist, this study highlights the potential of large language models to be transformative in this space. In the future, more advanced iterations of these algorithms with increased domain-specific knowledge may have the potential to assist pathologists and enhance pathology resident training.