HOPE-CAT is a machine-learning-based risk-assessment algorithm that identifies factors that may indicate the development of cardiovascular conditions that lead to maternal morbidity and mortality. By monitoring a pregnant patient's aggregated health data (e.g., medical records, wearables and device data, and self-reported data) in real time, HOPE-CAT stratifies a patient's risk and alerts providers to changes in a patient's risk status.

Current efforts to reduce cardiovascular-based maternal morbidity and mortality are reactive. Often occurring in a disjointed system, patient encounters and, consequently, data collection occur every few weeks or months over the course of a pregnancy, and even less frequently postpartum.

HOPE-CAT constantly monitors a patient's aggregated health data (e.g., medical records, wearable and device data, and self-reported data) in real time, stratifies a patient's risk, and alerts providers to changes in a patient's risk status.

The machine-learning-based technology identifies signs of risk sooner than would be discovered in a clinical setting, prompting proactive intervention and reducing outcomes of maternal morbidity and mortality.

HOPE-CAT is a proactive tool that identifies signs of risk before a patient experiences complications or a medical emergency, prompting intervention and fostering proactive care, unlike other diagnostic and treatment models.