A year after starting work with IBM to develop ways for the Watson supercomputer to support medical training and serve as a doctor’s assistant, the Cleveland Clinic has issued a progress report that includes two new technologies.
The clinic and IBM have developed WatsonPaths, a new process to train the supercomputer to interact with clinicians in a way that is more natural, enabling them to understand the data sources that Watson consulted and how it made recommendations.
WatsonPaths will support medical students by having them use Watson to try to resolve hypothetical clinical simulations, helping the students learn how to navigate content, consider hypotheses and find evidence to support answers, diagnoses and treatment options, while also grading Watson’s ability. The expectation is that students will learn how to focus on critical thinking skills and leveraging information tools, while Watson will get smarter at medical language and assembling chains of evidence from available content.
IBM and Cleveland Clinic also are testing Watson EMR Assistant with the goal of having deep, real-time and user-friendly clinical decision support in electronic health records systems. Electronic records can hold vast amounts of information over long periods of time and EMR Assistant will filter through the data to find relevant information that likely won’t be found today, such as a relevant blood test from several years ago.
“Working with de-identified EMR data provided by Cleveland Clinic, Watson EMR Assistant is able to collate key details in the past medical history, generate a problem list of clinical concerns that may require care and treatment, highlight key lab results and medications that correlate with the problem list, and classify important events throughout the patient’s care presented within a chronological timeline,” the organizations explain.
This piece originally appeared at Health Data Management. Published with permission.
If you liked this story, you might also be interested in these:
Register or login for access to this item and much more
All Information Management content is archived after seven days.
Community members receive:
- All recent and archived articles
- Conference offers and updates
- A full menu of enewsletter options
- Web seminars, white papers, ebooks
Already have an account? Log In
Don't have an account? Register for Free Unlimited Access