As rates of obesity, hypertension, type 2 diabetes, and sleep apnea increase, so are cases of advanced chronic liver disease and hepatic fibrosis, or cirrhosis. This problem led researchers at Mayo Clinic to develop an artificial intelligence (AI) model that doubled the number of diagnoses of advanced chronic liver disease in asymptomatic patients, helping doctors treat them before the disease progressed. "Chronic liver disease is a progressive process, so the sooner we can diagnose it, the sooner we can prevent it from advancing to irreversible stages," explains Doug Simonetto, M.D., a transplant hepatologist at Mayo Clinic and the lead author of the study published in Nature Medicine. Early intervention can reduce the likelihood that a patient will need a liver transplant in the future. The heart and liver are closely related. Hepatic fibrosis can cause a local increase in pressure that affects the heart. Therefore, a heart rhythm test called an electrocardiogram (ECG) can detect changes in heart electrical activity related to advanced liver disease. Dr. Simonetto and his colleagues developed an AI model to analyze data from 11,513 Mayo Clinic patients who underwent routine ECGs. The model identified patterns associated with advanced liver disease and detected twice as many cases compared to standard methods. Diagnoses were confirmed by validated imaging tests or blood tests. "As a family physician, I have often seen how advanced liver disease—which often has no symptoms until it becomes irreversible—can go unnoticed," explains David Rushlow, M.D., a family physician in the Mayo Clinic Health System and co-author of the study. For these patients, the technology not only allowed for a diagnosis to be found but also created an opportunity for better health outcomes, and in some cases, even saved lives." In this randomized clinical trial, 248 clinical professionals from Mayo Clinic in Rochester and throughout the Mayo Clinic Health System participated. "The idea that a simple, non-invasive, and inexpensive test could help identify patients at risk for developing advanced liver disease was very promising. This study gave us the opportunity to evaluate AI in a real-world clinical setting, where the true measure of innovation is whether it improves patient care in the community," says Dr. Rushlow. In the next phase, researchers will follow patients recently diagnosed with advanced liver disease for two years. "We are only just beginning to understand the full potential of AI-powered tools like this and the promise they hold for preventive and personalized care." The research is part of a broader Mayo Clinic effort called the Precure initiative, focused on developing tools that allow clinicians to predict and then intercept biological processes before they evolve into a disease or progress to complex and difficult-to-treat conditions.
