Diagnostic performance of artificial intelligence in predicting recurrence after surgical resection of hepatocellular carcinoma (HCC).

Abstract

e16199 Background: Artificial intelligence (AI) has been suggested as an alternative biomarker for predicting hepatocellular carcinoma (HCC) recurrence after treatment. The aim of this systematic review and meta-analysis was to evaluate the diagnostic performance of AI in predicting recurrence after surgical resection treatment for HCC. Methods: A rigorous and systematic evaluation was conducted on the AI studies related to recurrence after surgical resection for HCC, retrieved from the PubMed/Medline, the Cochrane Library, Web of Science, Embase, Scopus, CINAHL, and Google Scholar databases. The true positive, false positive, true negative, and false negative values were extracted or calculated from the included papers. Sixty studies met the inclusion criteria and were included in the meta-analysis. Results: Fifteen studies with a total of 864 patients met the inclusion criteria. The pooled sensitivity and specificity were 0,76 (95% CI: 0,71-0,80) and 0,75 (95% CI: 0,71-0,79), respectively. Moreover, the area under the summary receiver operating characteristics curve was 0,821, and the diagnostic odds ratio was 9,52 (95% CI: 6,80-13,34), showing a good diagnostic precision in predicting recurrence after surgical resection of HCC. Interestingly, no significant heterogeneity was detected and no evidence of publication bias was present. Conclusions: This study demonstrates the clinical translation potential of AI in predicting recurrence after surgical resection of HCC, with satisfactory results. However, further studies including larger sample size are needed to confirm these findings.