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

美国每年在医疗保健上的支出是排名第二的国家的两倍，但在预期寿命和婴儿死亡率等医疗质量指标方面表现明显不佳。医院护理约占美国医疗保健支出的三分之一。据估计，每年近300亿美元的医院护理费用是潜在可以预防的，其中约一半是与两种主要慢性疾病：心脏病和糖尿病有关的住院费用。电子健康记录和来自家庭设备、智能手机和可穿戴设备的新兴数字数据提供了一个很好的机会，可以开发一种系统的方法，以更好地管理门诊环境中的慢性病，并防止因对患者病情控制不善而需要住院治疗急性发作。该项目将利用数字健康数据来开发预测模型，以预测未来的不良事件，如住院、再次住院和过渡到疾病的急性阶段。这些预测将被用来触发个性化干预，范围从增加监测和医生就诊到针对每个患者的优化治疗政策。该项目支持数学科学家和一家大型安全网医院的医生之间的合作，该医院治疗相当大比例的低收入和代表性不足的群体。研究将集中在两个广泛的任务上：(1)预测分析，和(2)个性化干预。任务1开发了两个时间尺度的预测方法，长期和中期。这些预测以住院为目标，并依赖于新的有监督的机器学习方法，这种方法将分类与聚类相结合，作为提高性能和提供可解释结果的一种方式。此外，还提出了用于短期预测的异常检测方法。任务2侧重于设法预防任务1中预测的事件的干预措施。干预措施包括利用马尔可夫决策过程和扰动分析方法加强监测和优化治疗政策。方法方面的进步将包括联合聚类和分类的方法、异常检测、学习和改进马尔可夫决策过程的政策，以及扰动分析技术。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

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.