Cleveland Clinic developed a predictive “readmission risk score” model using electronic medical record (EMR) data and 18 clinical and social variables to identify patients at high risk of hospital readmission within 30 days. The model supports personalized care planning and targeted interventions to reduce unnecessary readmissions, improve quality of care, and lower healthcare costs.
- 15.9% average 30-day readmission rate over 3 years
- 10% reduction in readmissions over 2 years
- Risk score identifies top 5% high-risk patients
- Consistent model performance across diagnoses and demographics
High readmission rates increased costs and reduced patient satisfaction; manual risk assessment was inefficient
Developed and continuously validated a predictive risk score model using EMR data, integrated into clinical workflows to guide discharge planning and follow-up
- Reduced readmissions by 10%
- Improved personalized care and resource allocation
- Enhanced physician awareness of readmission risks
- Maintained model accuracy during COVID-19 pandemic
