Kathleen Jagodnik

Abstract:
Free-text analysis using machine learning based natural language processing shows promise for diagnosing psychiatric conditions. ChatGPT has demonstrated preliminary initial feasibility for this purpose; however, whether it can accurately assess mental illness remains to be determined. This study evaluates the effectiveness of ChatGPT and the text-embedding-ada-002 model in detecting post-traumatic stress disorder following childbirth (CB-PTSD), a maternal postpartum mental illness affecting millions of women annually, with no standard screening protocol.  A sample of 1,295 women over 18 who gave birth in the last six months,  we explore ChatGPT’s and ADA’s potential to screen for CB-PTSD by analyzing maternal childbirth narratives.