Improvements in Cesarean Birth Operative Reports Generated by ChatGPT-4.o Versus ChatGPT-3.5 [ID 1202]

INTRODUCTION: ChatGPT-4.o, the newest model of ChatGPT, boasts improvements in accuracy and detail of responses generated over previous models of ChatGPT. However, no studies to date have examined if the improvements in ChatGPT-4.o have led to improvements in obstetric operative reports generated by ChatGPT. This study compares completeness of cesarean birth operative reports generated by ChatGPT-4.o compared to its earlier counterpart, ChatGPT-3.5. METHODS: Twenty cesarean birth operative reports were generated by both ChatGPT-3.5 and ChatGPT-4.o. Each note was evaluated for inclusion and completeness of history of present illness, operative findings, technique of resection, limits of resection, technique of reconstruction, and closure technique using a Likert scale. Median completeness of the operative reports by each ChatGPT model was compared. RESULTS: Operative reports generated by ChatGPT-4.o demonstrated significant improvement in median Likert score compared to ChatGPT-3.5 in completeness of brief history of present illness ( P <.001), technique of resection ( P =.004), limits of resection ( P <.001), limits of resection ( P <.001), technique of reconstruction ( P <.001), and closure technique ( P <.001). No significant improvement was demonstrated in inclusion of findings ( P =.518). CONCLUSIONS/IMPLICATIONS: Overall, ChatGPT-4.o demonstrated improvements in completeness of cesarean birth operative reports. This occurred in all categories except inclusion of findings. These findings highlight the possibility of utilizing ChatGPT-4.o in generating cesarean birth operative reports. However, further research is needed to determine deficits in inclusion of findings.