Reducing the Rate of Readmissions

The client had limited or inefficient integration of its data sources, which made it difficult to see patients through a longitudinal lens. The client was, however, uniquely positioned to leverage the expansive patient data contained within its network of care, and set out to do so in 2012. Specifically, they wanted to improve the outcomes of patients with Ischemic Heart Disease (IHD) through improved care management with goals of reducing readmission rates, better managing patient cholesterol levels, and better managing patient blood pressure. Specifically, the regional healthcare provider was interested in implementing a machine learning platform, that quickly automates complex analytical processes and integrates powerful information into existing applications and portals.

The ThingWorx Machine Learning team set out to develop three ThingWorx Machine Learning-oriented solutions to improve care of IHD patients for our client: • The implementation team would create an integrated, longitudinal data platform for patients with IHD. • ThingWorx Machine Learning would then be applied to provide data-driven care management programs for patients with IHD that could be implemented at all levels of patient care. • ThingWorx Machine Learning would continually evaluate the impact of the program on the overall health, health care, and health cost for the targeted IHD patients. To get a free demo of ThingWorx 8: http://solutions.iotone.com/thingworx

• [Process Optimization - Real Time Monitoring]
  The medical condition of individuals can be identified in near real-time which helps reduce readmission rates for their patient populations.
• [Data Management - Data Analysis]
  ThingWorx Machine Learning, with its people, processes, and technology, helped to automate key insights, predictions, and increase analytical maturity to make our client more efficient, cost effective, and save more lives.

• The client now effectively manages 2990 patients that have IHD with data- driven solutions designed by the ThingWorx Machine Learning teams.

• ThingWorx Machine Learning automatically generates models to predict and identify the top 5% high readmission risk patients.