Newswise — PHILADELPHIA – Jefferson advances as a finalist in the nationwide challenge to improve health outcomes through artificial intelligence, sponsored by the U.S. Centers for Medicare & Medicaid Services. Each of the seven CMS finalists receives a $60,000 prize and the opportunity to win the grand prize of $1 million or $230,000 for the runner-up.

A multidisciplinary team of data scientists, data engineers, and physicians combined their collective experience to create the submission for the CMS Artificial Intelligence Health Outcomes Challenge. The winner will show how AI and machine learning can more strongly predict unplanned admissions and adverse events at hospitals and skilled nursing facilities. These insights can help healthcare providers to identify risk, intervene early, and ultimately improve patient outcomes. CMS, in collaboration with the American Academy of Family Physicians and the Laura and John Arnold Foundation, evaluated more than 300 initial entries on the predictive accuracy, explanation quality, and deployment potential of their models.  

“Our dashboard overcomes the ‘implementation challenge’ by bringing to life each patient’s data,” explains J. Alex Wrem, MD, medical information officer at Jefferson Health and assistant professor in Family Medicine at the Sidney Kimmel Medical College of Thomas Jefferson University. “The collaboration of clinicians with analytics experts allows us to see the patient in the data, and then use artificial intelligence to make decisions about delivering the care the patient needs.”

To advance to the final round, Jefferson pulled ahead of 300 initial entries, and 25 semi-finalists including Merck, IBM, the Mayo Clinic, and Accenture.

 “It’s easy to build an algorithm that makes a prediction,” says Dr. Michael Li, principal investigator and director of Health Data Science at Jefferson Health. “It’s much harder to make that prediction with strong accuracy, and even more difficult to implement and adopt AI in healthcare practice.”

In the last round, CMS will provide participants will more Medicare claims data to crunch and announce the winners by the end of April 2021.

"True transformation in health care depends on creative people building a bright future with digital tools like AI, which is why I am incredibly proud of our team for making this final round," said Stephen K. Klasko, MD, MBA, president of Thomas Jefferson University and CEO of Jefferson Health. "These are the teams who are innovating ways to use big data, so that we can take that learning and improve care where patients need us most.”