FIRST LOOK: A Machine Learning Algorithm to Reduce Costs and Increase Quality
Diagnostic tests are the lynchpin of medical care. From a health point of view, bad testing can lead to missed or incorrect diagnoses. From a cost point of view, bad testing is a major source of unneeded expenditures—the majority of the care labeled as “low value” by the Choosing Wisely campaign were diagnostic tests.
And yet testing decisions are notoriously hard – especially in a world where every patient is a “big data” challenge. Electronic health records hold exponentially increasing amounts of data as patients age, medical complexity increases, and technology expands rapidly. Doctors must absorb all this information in deciding which, if any, tests to deploy.
My team is building algorithms to aid physicians in these testing decisions – we have one completed prototype and several in the works. Importantly we are finding that these algorithms add value in two different ways. First, they can save costs – by dramatically reducing low-value testing of patients in whom nothing is found. Second, they can actually improve health outcomes – by identifying large pools of “misses”: untested patients who actually could have been caught, had they been tested in time. I will discuss what we might need to take these prototypes to scale as well as the kind of partnerships needed to build and apply these algorithms.
For more information about Dr. Obermeyer’s research, please contact Partners HealthCare Innovation by clicking here.
Most Recent Posts:
Exploring AI’s Impact on Industry, left to right: panelists, Marc Succi, MD, Daniela Rus and Paul English,…
Lilit Garibyan, MD, PhD, a dermatologist at the Wellman Center for Photomedicine and an associate professor of…
The Inflation Reduction Act: Responses From Experts on Implications for Biopharmaceutical Innovation
September 21, 2023—Two panel discussions on the Inflation Reduction Act at the World Medical Innovation Forum in…