Artificial intelligence (AI) has demonstrated the ability to accurately detect early-stage metabolic-associated steatotic liver disease (MASLD) by analyzing electronic health records. MASLD is the most common chronic liver disease globally, caused by improper fat accumulation in the liver, leading to severe health issues.
Incidences of MASLD have been rising in recent years, often associated with obesity, type 2 diabetes, and abnormal cholesterol levels. Early detection is crucial, as the condition can develop into more severe forms of liver disease. However, symptoms are typically absent in the initial stages, making diagnosis challenging.
Ariana Stewart from the University of Washington stated, 'A significant number of patients are not diagnosed with MASLD in time, which is concerning as delayed diagnosis increases the risk of liver disease.' The research team utilized AI algorithms to analyze imaging findings from electronic health records across three sites in the U.S., identifying fatty liver disease symptoms in 834 patients, but only 137 had recorded data.
Of those, 83% were undiagnosed despite exhibiting symptoms. The findings will be presented at the Liver Meeting, organized by the American Association for the Study of Liver Diseases. Previous studies have shown that AI can also assist in detecting liver fibrosis and diagnosing non-alcoholic fatty liver disease (NAFLD), as well as in differentiating focal liver lesions, diagnosing hepatocellular carcinoma, predicting chronic liver disease (CLD), and facilitating transplant science.