EAGER/Collaborative Research: Sensing, Modeling and Optimization of Postoperative Heart Health Management

点击翻译按钮获取中文摘要

Postoperative outcomes are critical to the quality of life of many patients. However, after discharge, there are currently few sensor-based decision support systems extending to home, workplace, and community. Postoperative care primarily depends on episodic follow-up visits and rare electrocardiograms. Very little has been done to continuously monitor clinical parameters of postoperative patients, estimate clinical status, and further help optimal management of postoperative recovery. This EArly-concept Grant for Exploratory Research (EAGER) award supports fundamental research to develop a collaborative sensing, statistical modeling and decision-making strategy for optimizing postoperative management of heart health. This research will help clinicians and patients leverage the fast development of sensing and mobile technology to achieve a substantial boost in smart postoperative management. As a result, this project will provide education on heart-healthy living and raise the awareness of smart health. In addition, realizing a better postoperative care will achieve a reduction in healthcare costs. A broader impact in education will be realized through new curriculum modules, training of healthcare professionals, and recruitment of under-represented students.In current practice, ad hoc strategies are widely used for managing postoperative risks. This award will make possible a new sensor-based, patient-centered management of heart health that can overcome several limitations of existing practices. In particular, it will empower clinicians and patients to (1) quantitatively measure the quality of life before and after cardiac procedures, (2) optimize postoperative cardiac care and decrease arrhythmia recurrences, and (3) improve lifestyle modifications and positively influence general postoperative outcomes. If successful, this research will lead to new data imputation algorithms to tackle uncertainty in patient-centered sensing, extract sensor-based biomarkers of cardiac risks, model the evolving dynamics of cardiac conditions, and optimize postoperative management under uncertainty. The success of this project will invoke a new "sensing-modeling-optimization" approach to theoretically formulate relationships connecting physiological signals from postoperative patients, useful information from analytical models with smart postoperative health management. Analytical methods and tools will be generally applicable to handle data veracity, feature extraction, risk prognostics, and process optimization in sensor-based monitoring and control of cardiovascular systems.