Tehran University of Medical Sciences Frontiers in Biomedical Technologies 2345-5837 0 0 2025 05 10 983 983 Dolley Srivastava Maharishi University of Information Technology,Lucknow Himanshu Pandey Department of Computer Science and Engineering,Faculty of Engineering and Technology, University of Lucknow, Lucknow, India Ambuj Agarwal Department of Computer Science and Engineering, School of Engineering and Technology, Sharda University, Greater Noida, India Richa Sharma Department of Computer Science, Maharishi University of Information Technology, Lucknow, India 2024 04 02 2025 04 08 In the past, heavy drinking was often linked to fatty liver. The prevalence of non-alcoholic fatty liver disease (NAFLD), which affects people who do not consume alcohol, has garnered a lot of attention in the last 20 years. Nearly all fatty liver diseases are now the leading cause of liver disease in industrialized nations. Fatty liver has traditionally been defined as having a hepatic fat content of more than 5% of liver weight. Several medical issues, including those caused by medications, poor diet, and infections, may lead to fatty infiltration of the liver. Modern scientific understanding, however, attributes fatty liver in most individuals to either being overweight or obese or to drinking too much alcohol. This research proposes a stacked ensemble approach to detect NAFLD efficiently and achieves 95.9% correct classification accuracy. It also compares the proposed method with other basic and boosting machine learning approaches. To improve machine learning for trustworthy and reliable NAFLD screening and diagnosis, we apply explainable AI methods to the ensemble model to identify the most influential features and patterns for NAFLD predictions. https://fbt.tums.ac.ir/index.php/fbt/article/view/983 https://fbt.tums.ac.ir/index.php/fbt/article/download/983/500