A pilot program run in collaboration between IMB, Epic and Carilion Clinic has used predictive analytics to identify 8,500 patients at risk for heart failure.
The pilot program analyzed electronic medical record data from Carilion Clinic, an eight-hospital system based in Roanoke, Va., to identify patients' risk factors for heart failure. IBM's natural language processing technology was able to include unstructured data, such as clinician notes and discharge documents, providing a more complete picture of the patient and allowing the pilot program to identify 3,500 more at-risk patients than predictive modeling using just structured data.
"We've learned that predictive analytics insights from both structured and unstructured data is imperative to meet our goal of improving patient care at lower costs," said Steve Morgan, MD, CMIO of Carilion Clinic, in a news release. "We were very impressed with the accuracy and usability of IBM's predictive modeling, which the IBM team developed and deployed in six weeks. These results and innovations are helping us move the needle on quality and the costs of care."
More Articles on Data Analytics:
CEO Summit Takeaway: Think Big (Data)
VHA, Kaiser Permanente Partner on Data Analytics, Connected Care
Big Data, Better Care: Walgreens' Clinics Turn to Analytics