Estimated 88 percent accuracy seen using electronic health record data, with ability to identify patients not previously diagnosed
WEDNESDAY, Nov. 27, 2024 (HealthDay News) — An algorithm can identify individuals with metabolic dysfunction-associated steatotic liver disease (MASLD) with about 88 percent accuracy using electronic medical record (EMR) data, according to a study presented at The Liver Meeting, the annual meeting of the American Association for the Study of Liver Diseases, held from Nov. 15 to 19 in San Diego.
Ariana Stuart, M.D., from the University of Washington in Seattle, and colleagues described the development of an EMR-based artificial intelligence (AI) algorithm for MASLD identification.
The researchers reported that an iterative natural language processing pattern-recognition AI algorithm achieved about 88 percent accuracy versus manual MASLD diagnosis. Among 957 individuals identified by the algorithm as meeting criteria for MASLD, 56 percent were female, 2 percent American Indian/Native Alaskan, 6 percent Black/African American, 16 percent Asian, 68 percent White, and 12.2 percent Hispanic/Latino(a). More than one-fourth of patients (25.6 percent) had gastrointestinal or hepatology referral, but only 140 had an MASLD-associated diagnostic code. More than seven in 10 individuals (697) were identified as meeting criteria for MASLD diagnosis but did not already carry an MASLD diagnosis.
“People should not interpret our findings as a lack of primary care training or management,” Stuart said in a statement. “Instead, our study shows how AI can complement physician workflow to address the limitations of traditional clinical practice.”