Background and Aims: Liver failure, hypertension, and liver cancer are among the major and potentially fatal consequences of liver diseases. Diagnosis and treatment of the diseases continue to possess numerous challenges despite the significant advances of the past decades. Ultrasound imaging is currently a cost-effective and non-invasive diagnostic method for liver diseases. Revolutionary advancements in machine learning techniques, i.e., the use of convolutional neural networks, have produced highly encouraging findings regarding automation of ultrasound image processing. The aim of the current research was to explore artificial intelligence methods in predicting liver disease from ultrasound images. Methods: This systematic review study was conducted in ۲۰۲۵ by searching the reliable databases of PubMed, Scopus, Web of Science, and Google Scholar search engine. The keywords of Artificial Intelligence, Prediction, Liver diseases, and
Ultrasound Images were investigated in related studies without time limitation. English-language articles that investigated artificial intelligence methods to predict the liver disease based on ultrasound scans met the inclusion criteria. Also, review studies and studies that did not focus on patients with liver diseases were excluded. Titles and abstracts were evaluated independently by two evaluators. Then the full text of the articles was checked. Results: A total of ۲۳۰ articles were retrieved from the mentioned databases. After reading the title and abstract of the articles and considering the inclusion and exclusion criteria, finally, ۱۰ articles were included in the study. The findings of the study revealed that artificial intelligence methods would be helpful in correct diagnosis, early treatment facilitation, and eventually the quality of life of liver disease patients. Artificial intelligence can be used by physicians to diagnose these conditions effectively without incurring potential side effects and complications. Conclusion: The result of this research showed that it is possible to utilize artificial intelligence algorithms as a secondary decision-maker in correct diagnosis of the disease, and therefore for primary treatment based on ultrasound images. However, additional
