AI can boost early diagnosis of liver disease: Study
A groundbreaking study has found that artificial intelligence (AI) can accurately detect early-stage Metabolic-Associated Steatotic Liver Disease (MASLD) by analyzing electronic health records, offering new hope for early diagnosis and intervention in a condition that often goes undiagnosed until it has progressed to more severe stages.
MASLD, the most common chronic liver disease worldwide, is characterized by the improper accumulation of fat in the liver, a condition commonly associated with obesity, Type-2 diabetes, and abnormal cholesterol levels. Its global prevalence has been rising in recent years, contributing to a heavy clinical burden. The disease often remains asymptomatic in its early stages, which makes timely diagnosis challenging, but if left unchecked, it can rapidly progress to more serious forms of liver disease, including cirrhosis and liver cancer.
“A significant proportion of patients who meet the criteria for MASLD go undiagnosed,” said Dr. Ariana Stuart, lead author of the study and researcher at the University of Washington, US. “This is concerning because delays in early diagnosis increase the likelihood of progression to advanced liver disease.”
In the study, researchers used an AI algorithm to analyze imaging data within electronic health records (EHRs) from three major medical centers in the US. The team found that out of 834 patients who met the clinical criteria for MASLD, only 137 had an official MASLD diagnosis recorded in their health records. This means that a staggering 83% of patients who were at risk for MASLD were not formally diagnosed, despite their records containing clear evidence of the condition.
Dr. Stuart emphasized the potential of AI to complement traditional clinical practices and improve early detection. “Our findings demonstrate how AI can enhance physician workflows and help address the limitations of conventional diagnostic methods,” she said.
The study is set to be presented at *The Liver Meeting*, hosted by the American Association for the Study of Liver Diseases. It adds to a growing body of evidence highlighting AI’s ability to transform liver disease diagnostics. Previous studies have shown that AI can be used to detect liver fibrosis, diagnose non-alcoholic fatty liver disease (NAFLD), differentiate focal liver lesions, diagnose hepatocellular carcinoma, predict outcomes in chronic liver disease, and aid in transplant decision-making.
As AI technologies continue to evolve, they are poised to play an increasingly important role in the early detection and management of MASLD, potentially preventing its progression and reducing the burden of liver-related morbidity and mortality worldwide.
