AI Model Detects Post-Traumatic Stress Disorder in Women After Childbirth: Study from Massachusetts General Hospital

Massachusetts General Hospital (MGH) has made a groundbreaking discovery in the field of maternal mental health with the development of a generative artificial intelligence (AI) model that can accurately screen for post-traumatic stress disorder (CB-PTSD) in women who have recently given birth. This innovative AI model, developed in collaboration with researchers from Bar-Ilan University in Israel, has the potential to revolutionize the way traumatic childbirth-related PTSD is detected and treated.

The study, published in Scientific Reports, highlights the urgent need for a rapid, low-cost assessment strategy for identifying CB-PTSD in women who have experienced traumatic childbirth. Currently, evaluation of PTSD related to traumatic birth relies on extensive clinician evaluation, which can be time-consuming and costly. The use of AI technology to analyze brief patient narratives of childbirth offers a more efficient, patient-friendly approach to detecting CB-PTSD.

The researchers focused on exploring the capabilities of several models from OpenAI, including ChatGPT, to identify a version that could provide rich insights into maternal mental health following traumatic childbirth. By collecting short narrative accounts from 1,295 women who had recently given birth, the team was able to train the AI model to accurately identify cases of CB-PTSD with 85 percent sensitivity and 75 percent specificity.

Dr. Sharon Dekel, director of MGH’s Postpartum Traumatic Stress Disorders Research Program and senior author of the study, emphasizes the potential clinical benefits of using AI technology to assess PTSD in new mothers. Early intervention is crucial in preventing the progression of this disorder to chronic stages, and the AI model developed by the researchers could facilitate timely treatment for high-risk women.

The emergence of artificial intelligence tools in healthcare has the potential to positively reshape the continuum of care, and Mass General Brigham is at the forefront of incorporating AI into care delivery, workforce support, and administrative processes. Dr. Dekel’s research program is dedicated to exploring women’s mental health following traumatic childbirth, and the development of this AI model represents a significant step forward in improving patient outcomes.

This study was supported by funds from the NIH, and the researchers hope that their innovative approach to screening for CB-PTSD will pave the way for the development of new AI tools for assessing other mental health disorders. The potential impact of this research on maternal mental health is significant, and the researchers are optimistic about the future applications of AI technology in improving patient care.

Source:
Massachusetts General Hospital
Journal reference:
Bartal, A., et al. (2024). AI and narrative embeddings detect PTSD following childbirth via birth stories. Scientific Reports. doi.org/10.1038/s41598-024-54242-2.