Transactions on Machine Intelligence 2821-1693 2 3 2019 09 01 Predicting the Severity of Non-Alcoholic Fatty Liver Disease Using ANFIS Optimized by Particle Swarm Optimization and Genetic Algorithm 128 140 206042 10.47176/TMI.2019.128 EN S. Zeynali Goldar Department of Electrical Engineering, Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran A. Rikhtehgar Ghiasi Associate Professor, Department of Electrical Engineering, University of Tabriz, Tabriz, Iran 0000-0002-5524-0330 M. A. Badamchizadeh Professor, Department of Electrical Engineering, University of Tabriz, Tabriz, Iran 0000-0002-9999-1152 Journal Article 2019 06 02 The liver is a vital organ and the largest gland in the human body, responsible for numerous essential functions such as metabolism, digestion, protein synthesis, and the removal of harmful toxins. It plays a central role in maintaining overall health and ensuring the body's proper functioning. Malfunction or damage to the liver can lead to a variety of serious health issues, including liver failure, cirrhosis, and fatty liver disease, all of which can significantly impact a person's quality of life and life expectancy. Early detection and accurate diagnosis of liver diseases are crucial for timely treatment, prevention, and minimizing the risk of further complications. Traditional diagnostic methods for liver diseases often involve invasive procedures, which can be expensive, time-consuming, and uncomfortable for patients. This research explores an innovative, non-invasive approach to diagnose and assess the severity of fatty liver disease by analyzing blood test results. The study applies various advanced techniques, including the Adaptive Neuro-Fuzzy Inference System (ANFIS), ANFIS combined with Particle Swarm Optimization (PSO), and ANFIS with Genetic Algorithms (GA), to a dataset collected from the Tabriz University research center. These methods are compared in terms of their accuracy and efficiency in predicting the severity of fatty liver disease, providing valuable insights into the potential of machine learning algorithms for medical diagnostics. The findings aim to contribute to the development of more accessible, cost-effective, and non-invasive diagnostic tools for liver diseases. https://www.tmachineintelligence.ir/article_206042_e86d3bee5a4248ec3aa42d9191c56b32.pdf