There’s a Fatty Liver Epidemic. AI Could Help Get Ahead of It
Over a billion people worldwide have livers with excess fat, which can lead to a host of medical problems. Researchers think AI tools can spot the condition—and help stop it—early enough to save lives.
A global phenomenon is emerging, affecting more than a billion individuals – a fatty liver epidemic. In many adults and children, liver fat surpasses 5 percent or even 10 percent of the organ's weight, leading to inflammation, cell damage, and fibrosis. This condition impacts roughly 30 percent of adults worldwide and can progress to liver failure, increasing the risk of cardiovascular disease and various cancers.
Regrettably, fatty liver disease often remains undetected until it reaches a critical stage, as it typically doesn't exhibit noticeable symptoms. Consequently, healthcare professionals are exploring how artificial intelligence (AI) could aid in early detection and prevention.
Jeffrey Lazarus, a professor at CUNY Graduate School of Public Health and Health Policy, believes AI could sift through vast electronic health records to identify individuals most at risk of accumulating liver fat. Early detection is crucial, as lifestyle changes like reducing alcohol intake, losing weight, and increasing coffee consumption can reverse early-stage damage. For moderate to advanced liver scarring, treatments like GLP-1 medication semaglutide and drug resmetirom have shown promising results.
However, the challenge lies in the fact that simple, noninvasive methods of assessing liver health are seldom employed, even in high-risk populations such as those with obesity and type 2 diabetes. Tests like the Fib-4 index, which predicts advanced liver fibrosis, and the enhanced liver fibrosis test, which measures liver scarring, are often underutilized due to the time and effort required.
To address this, AI could automate the calculation of Fib-4 scores from routine blood tests, making it more feasible for primary care physicians to identify at-risk patients for referral to liver specialists. Additionally, AI could analyze x-ray images, such as chest x-rays, to identify fatty liver disease with high accuracy. Danish startup Evido has developed an AI algorithm called LiverPRO, which assesses liver fibrosis risk based on age and nine blood-based biomarkers, outperforming the Fib-4 index in predicting serious liver problems.
This AI-based test could help doctors select the most suitable patients for resmetirom treatment without requiring invasive liver biopsies.
Written by urgent.news from Wired's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
