Predictive Analytics using Health Claims Data

Information derived from health claims and insurance plans data can provide insights into a patient and a population health status and inform healthcare plans and providers on patient health trajectories, potential interventions and cost efficiency. Claims data include patient demographics, procedures, medical conditions, prescription drugs and healthcare resources used for specific conditions over extended periods of time.

We developed methods and models to predict population health score and multiple types of patient risks, including obesity, diabetes, mortality, and the onset of serious medical conditions. 

Our models leverage several public and private data sets from multiple data sources that include CDC, county level data from 2018 County Health Rankings, state and national level data from America’s Health Rankings, Drug bank and others.

Our model also predicts members’ most possible race, disease prevalence and risk based on race, age, location and published literature to calculate personal health score and assign them to one of 4 categories Low-risk, Rising-risk, High-risk, and Highly complex.

Collaborating Partners: Magellan PBM & Leading Edge TPA
Sponsor: Clean Health