Two Watson-based tools offer docs real-time analysis

Scientists have trained IBM's "Jeopardy!" champ Watson to interact more naturally with doctors in two new projects aimed at improving patient care.

The work is a collaboration between IBM Research and the Cleveland Clinic along with Lerner College of Medicine of Case Western Reserve University.

WatsonPaths aims to help doctors diagnose patients and solve medical problems. To do so, it can understand spoken language and can consult reams of medical research in an instant, reports Crain's Cleveland Business.

The Watson EMR Assistant project helps physicians uncover key information from patients' medical records to inform their care.

"On Jeopardy! it was not necessarily critical to know how Watson arrived at its answer. But doctors … will want to understand what information sources Watson consulted, what logic it applied and what inferences it made in arriving at a recommendation," Eric Brown, IBM Research Director of Watson Technologies, said of WatsonPaths in an announcement. "We've been able to significantly advance technologies that Watson can leverage to handle more and more complex problems in real time and partner with medical experts in a much more intuitive fashion."

WatsonPaths pulls from reference materials, clinical guidelines and medical journals in real time, analyzing a situation from multiple angles. As staff interact with the technology, it uses machine learning to improve as it assimilates more material.

Watson EMR Assistant uses natural language processing to efficiently sift through an EHR with a deep semantic understanding of the content, both in structured and unstructured fields, to better make sense of it all. 

The EMR Assistant has been the focus of a pilot project for the past three weeks, according to Crain's, while the medical school is still working out how to best use WatsonPaths.

Cleveland Clinic began working with IBM on the technology about a year ago to improve medical school training.

Meanwhile, Memorial Sloan-Kettering Cancer Center is using a cloud-based version of Watson technology to enable clinicians to provide personalized treatments to patients.

And Indianapolis-based WellPoint has a project at the Cedars-Sinai Samuel Oschin Comprehensive Cancer Institute in Los Angeles to use Watson to provide decision support.

To learn more:
- read the Crain's article
- find the announcement

Suggested Articles

An assessment looking at 12 health systems that allow patients to download their health records to their smartphones via APIs finds modest uptake.

The National Institutes of Health-led All of Us precision medicine health research database project has enrolled 230,000 participants.

Hospitals must pursue a deliberate strategy for managing their public image—and a powerful tool for doing so is inpatient clinical data registries.