Enterprise IT vendor IBM today announced new investments in its US Federal Healthcare Practice to address the technology needs of public sector health institutions.
The company added big data solutions for advanced clinical care from its IBM Watson Group, new collaborations with IBM Research focused on data management.
The company also announced the appointment of Keith Salzman as chief medical information officer for IBM Federal.
IBM’s healthcare team includes more than 300 federal healthcare consultants and dozens of medical doctors and healthcare professionals who are focused on care systems transformation. This broad team supports IBM’s Federal Healthcare Practice, which is led by Vice President Giovanna Patterson.
Congressional Budget Office says the US Federal Government is expected to spend $13.95 trillion on major healthcare related operations and programs through 2024.
IBM will make big data and cognitive computing solutions available to federal healthcare clients to help aggregate and analyze clinical information to improve care and reduce costs.
Also, IBM Advanced Care Insights is now available to support healthcare providers with new insights from clinical, social and behavioral data. The solution utilizes IBM Content Analytics and Natural Language Processing (NLP) to extract insight from physician notes, lab results and other narrative content within electronic health record (EHR) systems.
IBM has reviewed more than 2 million patient encounters at Carilion Clinic, a Virginia health system in collaboration with Epic and Carilion Clinic.
After applying the Advanced Care Insights solution to these records, they identified 8,500 patients at risk for developing congestive heart failure in a pilot project that could lead to early intervention and better care for these patients.
The results were achieved through predictive modeling of data in Carilion Clinic’s electronic health records, including unstructured data such as clinicians’ notes and discharge documents that are not often analyzed. The pilot applied content analytics and predictive modeling to identify at-risk patients with an 85 percent accuracy rate.