JMIR Publications

ABSTRACT

Background:

Cardiovascular conditions (e.g., cardiac and coronary conditions, hypertensive disorders of pregnancy, and cardiomyopathies) were the leading cause of maternal mortality between 2017 and 2019. The use of machine learning to identify patients at increased risk for hypertensive disorders in pregnancy is on the rise, but a gap to identify pregnant individuals at higher risk of morbidity and mortality using the power of ML and Big Data including electronic health records (EHR) remains.

Objective:

To evaluate the ability of a proprietary machine learning (ML) algorithm, Healthy Outcomes for all Pregnancy Experiences- Cardiovascular-Risk Assessment Technology (HOPE-CAT), to identify cardiovascular (CV) conditions related to maternal outcomes.

Methods:

Retrospective data from the electronic health record (EHR) of a large healthcare system was investigated by HOPE-CAT in a virtual server environment. The ML algorithm assessed risk factors selected by clinical experts in cardio-obstetrics, and risk profiles were generated for every patient. The profiles were paired with clinical outcomes, wherein a delta was calculated between the date of the risk profile and the actual diagnosis in the EHR.

Results:

The study included 604 pregnancies resulting in birth; the majority of patients identified as Black (80%) between 21-34 years (84%). Preeclampsia (91%) was the most common condition, followed by thromboembolism (3%) and acute kidney disease/failure (2%). The average delta was 56.8 days between the identification of risk factors by HOPE-CAT and the first date of diagnosis or intervention of a related condition.

Conclusions:

This study provides additional evidence to support ML in obstetrical patients to enhance the early detection of CV conditions during pregnancy. ML can synthesize multi-day patient presentations to enhance provider decision-making. The utilization of ML technologies holds the potential to reduce maternal health disparities.