Mayo Clinic researchers have developed an artificial intelligence (AI) model that uses electrocardiogram (ECG) data to improve early diagnosis of advanced chronic liver disease. The new approach resulted in twice as many diagnoses among patients who showed no symptoms, allowing for earlier intervention and treatment.
Chronic liver disease is often not detected until it reaches a late stage, typically after symptoms such as gastrointestinal bleeding, fluid retention, or jaundice appear. Early detection is important because timely treatment can prevent the disease from progressing to irreversible stages and may reduce the need for liver transplants.
"Chronic liver disease is a progressive condition, so the sooner we can diagnose it, the sooner we can stop it from advancing to irreversible stages. Early intervention may decrease the likelihood that a patient will need a liver transplant in the future," said Doug Simonetto, M.D., Mayo Clinic transplant hepatologist and lead author of the study published in Nature Medicine.
The research team developed an AI model that analyzed ECG data from 11,513 patients at Mayo Clinic. Since liver scarring can affect heart function and be detected through changes in electrical signals recorded by ECGs, the model searched for patterns associated with advanced liver disease. Diagnoses made by the AI tool were confirmed through imaging or blood tests.
"As a family physician, I've often seen how advanced liver disease - which frequently has no symptoms until it becomes irreversible - can go undetected," said David Rushlow, M.D., Mayo Clinic Health System family physician and study co-author. "Many patients identified through the AI-ECG model had no idea they were living with advanced liver disease. By identifying these cases earlier, we were able to connect them to the right treatment - at a time when intervention can truly make a difference. For these patients, the technology helped us not only to uncover a diagnosis, it created an opportunity for better health outcomes and, in some cases, may have saved lives."
A total of 248 clinicians across Mayo Clinic locations participated in this randomized clinical trial.
"The idea that a simple, noninvasive and inexpensive test could help identify patients at risk of developing advanced liver disease was very compelling. This study provided an opportunity to evaluate AI in our real-world clinical environment, where the true test of innovation is whether it improves care for patients in the community," said Dr. Rushlow. "We're only beginning to understand the full potential of AI-enabled tools like this and the promise they hold for preventive, personalized care."
Researchers plan to follow up with newly diagnosed patients over two years to assess outcomes. This work is part of Mayo Clinic's broader Precure initiative aimed at creating predictive tools that allow clinicians to intervene before diseases develop or progress into more severe conditions.
