AI Tool Precisely Detects Postpartum Hemorrhage

An AI tool called Flan-T5 identified postpartum hemorrhage with 95% precision and detected 47% patients with the condition.

Flan-T5, an AI tool exhibited 95 percent accuracy in identifying patients with postpartum hemorrhage and resulted in detecting 47 percent more patients with the condition compared to standard methods of tracking through billing codes.

This new study was conducted by investigators from Brigham and Women’s Hospital and published in npj Digital Medicine ().

AI Tool Steps-Up Postpartum Hemorrhage Diagnosis

Postpartum hemorrhage is the leading cause of maternal mortality and morbidity worldwide and a common pregnancy complication. This serious medical condition is understudied and not universally defined or well represented in health records.

Postpartum Hemorrhage
Excessive hemorrhage after delivering a baby can be an emergency, leading to shock and even death if not arrested. Can this be prevented?

‘The Flan-T5 tool showed great promise for helping clinicians to identify subpopulations that are at higher risk of postpartum hemorrhage. #AItool #pregnancy #postpartumhemorrhage #womenshealth’

The study used the large language model Flan-T5 to extract medical concepts from electronic health records in order to better define and identify the populations impacted by postpartum hemorrhage.

“We need better ways to identify the patients that have this complication, as well as the different clinical factors associated with it,” said corresponding author Vesela Kovacheva, MD, of the Department of Anesthesiology, Perioperative and Pain Medicine.

“There are so many amazing large language models being developed right now, and this approach could be used with other conditions and diseases.”

Wearable Optical Device Helps Early Detection of Postpartum Hemorrhage
Laser speckle wearable gadget helps in the early detection of postpartum hemorrhage, potentially reducing maternal mortality rates.

The emergence of artificial intelligence tools in healthcare has been groundbreaking and has the potential to positively reshape the continuum of care. Mass General Brigham, as one of the nation’s top integrated academic health systems and largest innovation enterprises, is leading the way in conducting rigorous research on new and emerging technologies to inform the responsible incorporation of AI into care delivery, workforce support, and administrative processes.

Because conditions like postpartum hemorrhage include a large spectrum of patients, symptoms, and causes, the research team used the Flan-T5 model to analyze comprehensive information from electronic health records to help them better categorize subpopulations of patients.

Postpartum Hemorrhage Treatment Using Pelvic Arterial Embolization Saves Lives and Preserves Uterus
Pelvic arterial embolization or PAE, a minimally invasive, life-saving therapy, is a safe and effective treatment for postpartum hemorrhage, say researchers

They prompted the Flan-T5 model with lists of concepts known to be associated with postpartum hemorrhage and then asked it to extract them from the discharge summaries of a cohort of 131,284 patients who gave birth at Mass General Brigham hospitals between 1998-2015. This method achieved rapid and accurate results without the need for manual labeling.

“Ideally, we would like to be able to predict who will develop postpartum hemorrhage before they do so, and this is a tool that can help us get there,” said first author Emily Alsentzer, PhD, a research fellow in the Division.

Reduction of Severe Maternal Morbidity from Postpartum Hemorrhage
Ways to prevent obstetric hemorrhage have been highlighted in the study.

Next, the team plans to continue to use this approach to look at other pregnancy complications and hopes their work will help address growing maternal health crises in the United States.

“This approach can be applied to many future studies,” said Kovacheva. “And it could be used to help guide real-time medical decision making, which is very exciting and valuable to me as a clinician.”

Reference:

Zero-shot Interpretable Phenotyping of Postpartum Hemorrhage Using Large Language Models - (https://www.nature.com/articles/s41746-023-00957-x)

Source-Eurekalert