Artificial Intelligence Used for the Diagnosis, Treatment and Surveillance of Hepatocellular Carcinoma: A Systematic Review

Abstract

Introduction: Hepatocellular Carcinoma (HCC) is the most common type of liver cancer, compromising about 75% of all liver cancers. The advancement in artificial intelligence (AI) has paved the way in the field of liver cancers to help clinicians with early diagnosis, treatment guidance and surveillance for HCC. The aim of this review was to summarize different AI-assisted methods that could be used in the diagnosis, treatment, and surveillance of HCC throughout the literature. Methods: PubMed and MEDLINE OVID databases were searched for primary studies involving AI and HCC published from 2012 to February 2022. Data was obtained, including study characteristics and outcome measures: accuracy, area under curve (AUC), specificity, sensitivity, and errors. A narrative synthesis was used to summarize the findings. Results: The systematic search produced 340 studies, of which 36 met the pre-determined eligibility criteria. The studies were published between 2012 to 2020. All the studies with their respective AI models/algorithms were described and summarized in the tables according to their role in the diagnosis, treatment, or surveillance of HCC. All the studies included used different AI algorithms, out of which, most were used for diagnostic purposes (44%), followed by treatment prediction (38%) and then surveillance of HCC (18%). Among studies, 38% reported their results as AUC, 33% of the studies reported accuracy, 19% reported sensitivity and specificity, 4% reported concordance indices (C-indices), 3% reported the mean errors and 2% reported AUROC values for respective AI models used. The accuracy of the diagnostic, treatment and surveillance tools range from 40% to 99%, 50% to 90% and 70% to 95% respectively. Conclusion: Many AI models are available that show promising results for the different applications in diagnosis, treatment, and surveillance of HCC. However, the demand for the generalization of these results remains. Future research should focus on improving the results and accuracy of these algorithms used for HCC to reduce the risks in complicated procedures.