Patients with congestive heart failure (CHF) pose a challenge to health systems because the chronic condition often means frequent hospital stays and varying readmissions. According to the Centers for Medicaid & Medicare Services (CMS), CHF patients have a rate of readmission within 30 days that runs as high as 33.8 percent, compared to the average readmission rate of around 24.8 percent for all U.S. patients. As a result, starting in 2012, CMS began penalizing hospitals with above-average readmission rates for CHF.
To improve the quality of healthcare and patient outcomes while helping health systems avoid financial penalties, Leidos analyzed how an information-based health data analytics approach could be used to create a probability-based model that would forecast the likelihood of CHF readmission, based on a broad set of clinical and non-clinical factors. Leidos’ team of commercial and federal healthcare experts, health informaticists, physicians, scientists, statisticians, and mathematicians studied the diverse set of factors that influence CHF readmission in search of a working model.
Ultimately, Leidos’ multidisciplinary team identified three types of factors that may affect readmission of CHF patients: patient-specific factors, hospital-specific factors, and socioeconomic factors. By collecting and analyzing these data as part of the treatment process, hospitals and case managers are better equipped to identify patients at risk for readmission before they are discharged from the hospital.