BIG DATA AND PREDICTIVE ANALYTICS IN HEALTHCARE: INTERDISCIPLINARY APPROACHES TO BUSINESS, LAW, AND EDUCATION

Abstract

The term predictive analytics and big data are changing healthcare in that sense that they will be able to make decisions based on data to enhance patient outcomes and improved workflow. The paper has explained four predictive models, Decision Tree, Random Forest, Support Vector Machine (SVM) and Gradient Boosting which were applied to a sample of 50,000 anonymized patient records. These were to predict disease onset, hospital readmissions, and outcomes of treatment. After the preprocessing of the data and selection of features, 25 important predictors could be identified. The best model with 92 percent precision, and 93 percent recall and AUC-ROC of 0.96 was Gradient Boosting. Both random Forest and SVM were reported to be at 92 percent accurate and the Decision Tree was a little bit less. Besides clinical application, the paper discusses a broader business, legal, and education implication- states that it has strategic planning, privacy compliance and curriculum design applications. The findings suggest that the ensemble-based models could not just enhance the healthcare decision making but overcome the operational, legal and the educational challenges, develop innovation and interdisciplinary collaboration.