Predict Patient Readmissions
The healthcare industry is facing financial pressure to reduce readmissions. Patient readmissions are estimated to cost over $41 billion annually. Readmissions, specifically when patients are readmitted within 30 days of discharge, are quality metrics that hospitals watch closely. Many readmissions could be prevented if hospitals can identify the factors that indicate readmission in the patient population. AI can provide the reasons that will lead to readmission and provide recommendations for the types of treatments that are most likely to be successful given the patient’s history.
We would use a variety of data from sources including Patient demographics; Hospitalization characteristics such as the admission source, admission type, and others; After care data: Discharge disposition and Discharge type; Length of hospitalization; Medical procedures during hospitalization; Medications administered during hospitalization; and many others in machine learning algorithms to uncover hidden patterns in the data. Indicators of readmission are identified along with patients who are at risk. This information provides the hospital staff, who are at the point of impact, with actionable information.
In healthcare, the data sources can be very complex and in many disparate locations. AI is ideally suited for this type of large, complex data inputs for machine learning models to predict future events and outcomes, and overall risk. Predicting patient readmission provides insights that are extremely valuable in pinpointing areas for hospital decision makers to focus on when developing a care plan for the patient along with providing a crucial set of markers that lead to effective preventative measures and lower costs.