A hospital readmission is an episode when a patient who had been discharged from a hospital is admitted again within a specified time interval. Readmission rates have increasingly been used as an outcome measure in health services research and as a quality benchmark for health systems. Hospital readmission rates were formally included in reimbursement decisions for the Centers for Medicare and Medicaid Services (CMS) as part of the Patient Protection and Affordable Care Act (ACA) of 2010, which penalizes health systems with higher than expected readmission rates through the Hospital Readmission Reduction Program. The real-world clinical care data provided in this competition comes from multiple hospitals across the United States for several years.
The challenge: Readmissions
In this machine learning problem, the exacting task is of trying to predict whether or not a patient will be readmitted to the hospital. The target takes on binary values where 0 implies that the patient was not readmitted, and 1 implies that the patient was readmitted. Thus, predicting the latter. The classification model will be evaluated using log loss.