SBIR Phase I: Mobile Health Platform for Malignant Hypertension Prediction

点击翻译按钮获取中文摘要

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will result from the development of a scalable and predictive software platform with a remote monitoring service that analyzes patient blood pressure data and delivers clinical recommendations, enabling healthcare providers to triage patients before their hypertension devolves into heart attack and stroke, and shortening the interval to achieve blood pressure control from the standard of care (18 to 24 months) to as little as 10 weeks. This model is beneficial on a societal level because the hypertension epidemic affects 1 in 3 adults in the United States, creating financial and quality of life burdens on more than 100 million people and costs the healthcare system $131 billion annually. On a business and financial level, the model's prevention of adverse healthcare events will result in major cost savings for healthcare providers, insurers, and public health authorities. High blood pressure affects 40% of adults over 25 globally, and is a major factor in cardiovascular disease, the number one worldwide cause of death, which occurs primarily in developing countries. Preventing and predicting high blood pressure will transform how chronic diseases are treated around the world. This Small Business Innovation Research (SBIR) Phase I project aims to develop an algorithmic model to predict malignant hypertension physiology. Pharmacology-based blood pressure prediction has been demonstrated in small studies of continuous 24-hour blood pressure monitoring but has not been translated to point-of-care mobile management in the outpatient setting. Developing a model of pharmacology-based blood pressure prediction using blood pressure variability, rate of progression, and deviation from pharmacologic baseline that portends heart attack and stroke is critical to point-of-care mobile management for hypertension. Moreover, predictive analytics based on contextual data related to patient physiology has not yet been developed. This Phase 1 project applies existing algorithmic modeling to hypertension management by collecting unique data from hypertensive patients including daily physiological data collected from wearable blood pressure devices, pharmacology data derived from tracking medication adherence and time of medication consumption, contextual data including diet, exercise and sleep, and patients' clinical records, to develop a predictive model that alerts clinicians when patients' blood pressure is trending towards a negative health event. This predictive model will incur minimal cost and structural changes to existing healthcare infrastructure while reducing hospitalizations, generating massive cost savings for providers, and significantly improving patient outcomes.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.