Artificial intelligence/neural network system for the screening of nonalcoholic fatty liver disease and nonalcoholic steatohepatitis

Aim We aimed to develop a novel noninvasive test using an artificial intelligence (AI)/neural network (NN) system (named nonalcoholic steatohepatitis [NASH]-Scope) to screen nonalcoholic fatty liver disease (NAFLD) and NASH. Methods We enrolled 324 and 74 patients histologically diagnosed with NAFLD for training and validation studies, respectively. Two independent pathologists histologically diagnosed patients with NAFLD for validation study. Additionally, 48 subjects who underwent a medical health checkup and did not show fatty liver ultrasonographically and had normal serum aminotransferase levels were categorized as the non-NAFLD group. NASH-Scope was based on 11 clinical values: age, sex, height, weight, waist circumference, aspartate aminotransferase, alanine aminotransferase, gamma-glutamyl transferase, cholesterol, triglyceride, and platelet count. Results The sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operator characteristic curve of NASH-Scope for distinguishing NAFLD from non-NAFLD in the training study and validation study were 99.7% versus 97.2%, 97.8% versus 97.8%, 99.7% versus 98.6%, 97.8% versus 95.7%, and 0.999 versus 0.950, respectively. Those for distinguishing NASH with fibrosis from NAFLD without fibrosis were 99.5% versus 90.7%, 84.3% versus 93.3%, 94.2% versus 98.0%, 98.6% versus 73.7%, and 0.960 versus 0.950. These results were excellent, even when the output data were divided into two categories without any gray zone. Conclusions The AI/NN system, termed as NASH-Scope, is practical and can accurately differentially diagnose between NAFLD and non-NAFLD and between NAFLD without fibrosis and NASH with fibrosis. Thus, NASH-Scope is useful for screening nonalcoholic fatty liver and NASH.

Automated summary

The study aimed to develop a novel noninvasive test using an AI/NN system called NASH-Scope, which showed excellent sensitivity and specificity in distinguishing between NAFLD and NASH in training and validation studies.