Big Data Analytics Predicting Risk of Readmissions of Diabetic Patients

Healthcare holds paramount importance where analytics can be applied to achieve insights about patients, identify bottlenecks and enhance the business efficiency. Readmission rates cater to the quality of treatment provided by the hospitals. Readmission results from improper medication, early discharge, unmonitored discharge, meager care of hospital staff. To identify high risk of readmission through data analytics leads to accessibility to healthcare providers to develop programs to improve the quality of care and institute targeted interventions. The proper implementation of these analytic methods aid in proper utilization of resources in hospitals thus reduces the readmission rate and the cost incurred due to re-hospitalization. Evolving predictive modeling solutions is highly challenging for recognizing risks of readmission in healthcare informatics. The procedure involves integration of numerous factors such as clinical factors, socio-demographic factors, health conditions, disease parameters, hospitality quality parameters and various other parameters that can be specific to requirement of each individual health provider. Big data consists of large data sets that require high computational processing to procure the data patterns, trends and associations. The effectiveness of big data and its analytics in predicting the risk of readmission in diabetics patients has been dealt in the research. The aim of this project is to determine the risk predictors that can cause readmission among diabetic patients and detailed analysis has been performed to predict risk of readmission of diabetic patients.