Rochester, Minn.-based Mayo Clinic developed an artificial intelligence model using electrocardiogram data that outperformed the current model for end-stage liver disease score in predicting severe liver disease and liver-related death among transplant patients.
Findings from the AI-cirrhosis-ECG model, or ACE, were published in JHEP Reports in 2024 and highlighted by Mayo Clinic Sept. 30. Researchers said ACE may help address limitations of the MELD score, which does not fully capture complications such as ascites and portal hypertension.
Doug Simonetto, MD, a transplant hepatologist at Mayo Clinic in Rochester, said ACE performed significantly better because it detects disease indicators missed by MELD. The team trained the tool on data from more than 75,000 patients, showing a progressive rise in risk scores that peaked before transplant and dropped after surgery.
Bashar Aqel, MD, director of the Mayo Clinic Transplant Center in Phoenix said the model could eventually be combined with MELD to optimize organ allocation. Andrew Keaveny, MD, a transplant hepatologist at Mayo Clinic in Jacksonville, Fla., added that it may help refine transplant listing decisions and improve patient outcomes.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.