Readmission Risk-based Discharge and Planned Admission Decision Support System

Readmission of patients after a short period of time from their discharge costs billions of dollars to governments every year. It has been shown that effective follow-up and improved coordinated care of the patient may prevent re-hospitalization after discharge. In this research, we will develop an integrated readmission risk monitoring system that will continuously monitor patients, and act as an auxiliary decision support system to provide clinicians with the risk of readmission during the entire period of a patient’s stay, as well as after the discharge through the periodic remote measurements taken by the patient at home. The part of the project include (i) developing statistical machine learning models to predict the risk of readmission for most costly select disease groups (e.g., myocardial infarction, pneumonia, diabetes mellitus, Alzheimer’s disease, etc.), (ii) identifying unplanned readmission cases in a personalized and adaptive way, (iii) locating and eliminating data entry errors, (iv) developing a patient discharge decision support system based on readmission risk, and (v) developing a remote follow-up program integrated with readmission risk prediction models that will recommend health care providers a planned admission or doctor visit in a proactive manner for patients with high readmission risk. We will also develop a cost-aware optimization model to balance the risk of readmission with the financial cost of admission on the healthcare system. Furthermore, this research includes the development of mobile and web apps to enable patients to remotely enter their self-measured data as well as to present various reports to both patients and healthcare providers.