An artificial intelligence (AI) program may improve the diagnosis rate of metabolic dysfunction-associated steatotic liver disease (MASLD), formerly known as non-alcoholic fatty liver disease, according a study presented at the American Association for the Study of Liver Disease (AASLD) Liver Meeting 2024.

 

Often referred to as “silent diseases,” MASLD and its more severe form, metabolic dysfunction-associated steatohepatitis (MASH), are responsible for a growing proportion of advanced liver disease, mirroring a global rise in obesity. Over time, fat accumulation in the liver can lead fibrosis, cirrhosis and liver cancer.

 

MASLD often has no symptoms, especially in its early stages. Clinical signs and reported symptoms tend to be more evident when MASLD has progressed to MASH. These may include fatigue, nausea and abdominal pain.

 

University of Washington researchers used an AI program trained to identify MASLD in patients within the university medical system.

 

After analyzing electronic health records, the program identified hundreds of undiagnosed MASLD cases.

 

Although according to records, 834 patients met the criteria for MASLD, only 137 were diagnosed. This means about 83% of patients were not.

 

“This is concerning because delays in early diagnosis increase the likelihood of progression to advanced liver disease,” said lead researcher Ariana Stuart, MD, at the AASLD’s annual Liver Meeting, where she presented the preliminary findings of the AI study.

 

A recently published study found that about 4 in 10 U.S. adults have MASLD, but many remain undiagnosed. If left untreated, MASLD can lead to liver fibrosis, cirrhosis and even liver cancer.

 

With no approved medical treatments for MASLD and MASH, management relies on lifestyle changes such as maintaining a healthy weight, eating a balanced diet, limiting alcohol consumption, exercising regularly and getting enough sleep.

 

“People should not interpret our findings as a lack of primary care training or management,” Stuart said. “Instead, our study shows how AI can complement physician workflow to address the limitations of traditional clinical practice.”

 

For more, click #Artificial Intelligence. There, you’ll find headlines such as “AI May Be on Its Way to Your Doctor’s Office, But It’s Not Ready to See Patients,” “Using Artificial Intelligence to Predict Hepatitis C Treatment Results” and “‘Dr. Google’ Meets Its Match: Dr. ChatGPT.”