In its latest foray into healthcare, IBM has produced a solution that uses its natural language processing (NLP) technology to improve the quality of care and reduce costs. The NLP approach is the same as the one that the IBM Watson supercomputer used to defeat human contestants on the "Jeopardy" TV game show.
Austin, Texas-based Seton Healthcare Family, a healthcare system that is part of Ascension Health, will be the first provider organization to employ IBM's new Content and Predictive Analytics for Healthcare. In combination with other health IT products, Seton will use the Big Blue application--which converts unstructured data into structured data--to focus on the root causes of readmissions and how to ultimately prevent them.
"With this solution, we can access an integrated view of relevant clinical and operational information to drive more informed decision making," Charles J. Barnett, president and CEO of Seton, said in an IBM press release. "For example, by predicting readmission candidates, we can reduce costly and preventable readmissions, decrease mortality rates, and ultimately improve the quality of life for our patients."
More than 80 percent of clinical data is unstructured today. That includes physician notes, registration forms, discharge summaries and other documents. IBM claims that its new analytics solution can extract medical facts from this mass of unstructured documentation and "understand" the relationships between them. By organizing this information, the company says, its application can yield insights into trends, patterns, and deviations from the norm, and predict outcomes of treatment.
IBM has been very active lately in the healthcare space. Last February, for example, it entered an agreement with Nuance Communications to use the Watson NLP technology in healthcare. Several months later, Nuance announced it would develop a Watson-based NLP approach to improve EHR documentation in partnership with the University of Pittsburgh Medical Center.
To learn more:
- read the IBM press release
- see the Healthcare IT News article