Liver cirrhosis can be defined as the late stage of liver fibrosis. Most patients with compensated cirrhosis have no obvious symptoms. However, when cirrhosis progresses to the decompensated stage, even accompanied by complications such as gastrointestinal bleeding, hepatic encephalopathy, and liver cancer, it will seriously affect the quality of life and survival time of patients, imposing a heavy economic burden on the country and society. Therefore, early diagnosis and precise intervention of liver cirrhosis are particularly important. Currently, most studies on liver cirrhosis using artificial intelligence are based on machine learning or deep learning techniques to build relevant models for diagnosis or risk prediction. This article provides an overview of the application of artificial intelligence in the early non-invasive diagnosis and risk prediction of liver cirrhosis through these relevant researches in the following areas including imaging, multimodal biomarker screening, and risk prediction of liver diseases