Developing HPCC Based COPD Readmission Risk Analysis Platform

Hospital Readmissions prevention shows a potential of huge cost savings and delivering better quality of care to the patients. This is a comparative study performed on existing readmission analysis frameworks based on data type, data size, disease conditions, algorithms and other features. This study shows that existing frameworks do not consider a very basic aspect of readmission risk analysis, taking huge amount of data in consideration. The available patient data for readmission risk analysis has datasets which have high dimensionality and high number of instances, moreover there is more data produced everyday which can be used on a continuous basis to improve the prediction power. This study proposes a High Performance Computing Cluster based Big Data readmission risk analysis platform which uses Naïve Bayes classification algorithm. The study also shows that the overall evaluation time using Big Data and Parallel computing platform has been decreased with great margin as compared with other researches in this area.