Challenge

The Health Resources & Services Administration (HRSA) distributes awards to health centers across the nation and is responsible for evaluating their performance on an annual basis. This assessment involves analyzing a comprehensive matrix of performance indicators, which includes 17 clinical measures and various health center characteristics. Some examples of these characteristics are the percentage of uninsured individuals, minority representation, homeless population, and farm workers. This thorough evaluation ensures that the awarded health centers maintain high standards of care and service.

Solution

REI tackled this challenge by employing a Machine Learning technique called Lasso Regression. They collected data for each clinical measure, patient, and health information, along with the corresponding demographic information for each clinic, which included factors such as insurance status and minority representation. This process allowed REI to develop a model that identified the most influential factors affecting performance concerning each measure. Utilizing the R programming language, REI efficiently processed vast amounts of data in just a few days, promptly providing valuable insights to their customer.

Impact

The analysis involved processing a vast amount of data containing numerous intricate factors, enabling the quick extraction of meaningful performance measures. These performance measures offered timely, actionable insights into the performance and funding of health centers serviced by HRSA. The entire process proved to be both resource and time-efficient, making it an effective solution for evaluating and managing health center performance.