QuBBD: From Personalized Predictions to Better Control of Chronic Health Conditions

点击翻译按钮获取中文摘要

The United States spends twice as much annually on health care than the next-highest spender but significantly under-performs in quality of care metrics, such as life expectancy and infant mortality. Hospital care accounts for about a third of U.S. health care spending. It has been estimated that nearly $30 billion in hospital care costs each year are potentially preventable, with about half of that amount due to hospitalizations related to the two major chronic diseases: heart diseases and diabetes. Electronic Health Records, and the emerging digital data from home-based devices, smart phones, and wearables, offer a great opportunity to develop a systematic approach towards better management of chronic conditions in an outpatient setting and the prevention of hospitalizations required to treat acute episodes resulting from poor control of a patient's condition. This project will utilize digital health data to develop predictive models that anticipate future undesirable events, such as hospitalizations, re-admissions, and transitioning to an acute stage of a disease. These predictions will be used to trigger personalized interventions, ranging from increased monitoring and doctor visits to optimized treatment policies adapted to each patient. The project supports a collaboration between mathematical scientists and a physician at a major safety-net hospital, which treats a significant percentage of low-income and underrepresented groups.The research will focus on two broad tasks: (1) predictive analytics, and (2) personalized interventions. Task 1 develops methods for predictions in two time scales, long and medium. These predictions target hospitalizations and rely upon new supervised machine learning approaches that combine classification with clustering as a way of enhancing performance and offering interpretable results. In addition, anomaly detection methods are proposed for shorter-term predictions. Task 2 focuses on interventions seeking to prevent events predicted under Task 1. Interventions include increased monitoring and optimizing treatment policies using Markov Decision Processes and perturbation analysis methods. Methodological advances will include methods for joint clustering and classification, anomaly detection, learning and improving policies for Markov Decision Processes, and perturbation analysis techniques.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.