ABSTRACT

Population health management (PHM) is the concept of maintaining or improving the well-being of individuals by better identifying and monitoring individuals to address health needs at all points along the care continuum through cost-effective and tailored health solutions. While the key step is to stratify the population into different risk groups and design personalized interventions, the current PHM programs are not effective at targeting the appropriate group that most likely to benefit.

This research evaluates risk stratification issues with two important aspects of PHM, care coordination, and chronic disease management, and proposes strategies that can potentially serve as more effective solutions to identify at-risk population and help make better decisions to improve health outcomes. Specifically, three studies are presented: 1) emergency department (ED) utilization in critical access hospitals; 2) prediction models for 30-day all-cause hospital readmissions; and 3) longitudinal medication adherence behavior for type 2 diabetes patients. The application is demonstrated using administrative and medical claims data. Results showed that, for critical access hospitals, over 50% of the ED visits could be treated at primary care settings which indicates a shortage of primary care physicians in rural areas, and a significant proportion of patients with ED transfers returned to their local community within a relatively short time frame. For larger hospitals with readmission concerns, additional evaluation metrics and data imbalance issues might be worth considering for boosting the predictive performance of prediction models that estimate 30-day readmission risk. The recent machine learning techniques were found to perform better than the conventional logistic regression. Group-based trajectory models provided value in identifying different medication adherence behavior for patients with chronic conditions such as type 2 diabetes. This work illustrates some limitations of the current methods and identifies opportunities for a more accurate approach to help design targeted interventions and fulfill the goal of PHM.