A new paper in the New England Journal of Medicine offers a blueprint for how doctors can use artificial intelligence to help them diagnose diseases.

The authors outline the benefits of machine learning to reduce physician error and streamline the healthcare system.

They also highlight the challenges of using AI in medicine — cautioning that even machines can’t be perfect.

Isaac Kohane, MD, PhD, one of the paper’s authors and chair of the biomedical informatics department at Harvard Medical School, joined WBUR’s Morning Edition host Bob Oakes to discuss the findings.

Listen to the interview.

Originally published on WBUR’s CommonHealth.