Economic Impact Analysis of Hospital Readmission Rate and Service Quality Using Machine Learning

The hospital readmission rate has been proposed as an important outcome indicator computable from routine statistics. The purpose of this research is to investigate the Economic Impact of service in hospitals and integrated delivery networks in the United States based on the readmission rates as the target variable. The data set includes information from 130 hospitals and integrated delivery networks in the United States from 1999 to 2008 to investigate significance of different factors in readmission rate. The dataset contains 101,766 patients’ encounters and 50 variables. The 30-day readmission rate is considered as an indicator of the quality of the health providers and is used as target variable in this project. Preliminary data analysis shows that age, admission type, discharge disposition etc. is correlated to the readmission rate and will be incorporated for further data analysis. Data analysis are performed on the diabetic patient dataset to develop a classification model to predict the likelihood for a discharged patient to be readmitted within 30 days. KNN, Naive Bayes and Logistic Regression algorithm were used to classify data and KNN appears to be the best approach to develop the model. Hospitalisations and drug prescriptions accounted for 50% and 20% of total readmission expenditure, respectively. Long term nursing home care after hospital admission cost an additional £46.4 million. With the ability to identify those patients who are more likely to be readmitted within 30 days, we can deploy the hospital resources more economically affordable while improving services. Based on the results it can be concluded that the direct cost of readmission rate for hospitals rose to £459 million in 2000 and nursing home costs rose to £111 million. Also, it can be perceived that a reduced length of hospital stay was associated with increased readmission rates for jaundice and dehydration.