Readmission Prediction Using Hybrid Logistic Regression

Predictive analytics has a prominent role in the field of healthcare. A massive amount of medical data is available such as diagnosing the disease, symptoms of illness, healthcare cost, mortality risk, and so on. Readmission prediction has great significance in improving patient care. This paper represents a Hybrid Logistic Regression (HLR) prediction model for large datasets. This model is the combination of k-means clustering and Logistic Regression in pyspark approach. The patients are clustered based on medical data, and Logistic Regression applied for the prediction approach. Further performance evaluation of the model is calculated and compared with other methods. It achieved better accuracy when compared with the existing feature selection algorithm