Predictive Analytics in Healthcare

Agenda

Predictive Analytics in Healthcare

Analysis overview

Value-based Purchasing

HCAHPS Overview

HCAHPS Dimensions

Quality Improvement

Appendix

References

Predictive Analytics in Healthcare

Predictive Analytics Predictive Analytics builds models based on data that can help forecast the future regarding probabilities. Models cannot correctly predict the future but can provide insights for individuals to make effective decisions. Predictive analytics uses many statistical techniques ranging from regression modeling to machine learning to data mining to make projections about future events. The necessary work of an analyst is to build a data framework through the following primary goals: gathering data, building information and gaining actionable insights. The insights should enhance a leader’s ability to make improved decisions. This framework for data analysis provides the background for the various forms of analytics. Analytics can be described as taking place in three distinct phases: Descriptive analytics, Predictive analytics, and Prescriptive analytics.

For this project, the focus is on using predictive analytics. Predictive analytics builds models based on data that can help forecast the future regarding probabilities. Models cannot perfectly predict the future but can provide insights for individuals to make effective decisions. Predictive analytics uses many statistical techniques ranging from regression modeling to machine learning to data mining to make projections about future events. In healthcare, the use of predictive models has become popular in disease management and population health. For example, some healthcare organizations have begun to examine early indicators of diabetes to help prevent and lower costs associated with diabetes management. This analytics activity is significant as, according to the Centers for Disease Control and Prevention, more than 75 percent of total healthcare spending in the United States is related to chronic healthcare conditions. At Hennepin County Medical Center, the population health analysts discovered that individuals diagnosed with HIV also suffered from poor nutrition. A predictive model was constructed showing the positive impact of improved nutrition on health care costs. Today, HCMC distributes healthy food with HIV medications for many of the patients in this population and have found overall costs to be reduced. In short, predictive models have become a standard approach to help decrease overall costs, improve quality outcomes, and lower overall patient risk. Predictive Tools Three methods are typically