Can artificial intelligence support the clinical decision making for Barcelona clinic liver cancer stage 0/a hepatocellular carcinoma in China?

Abstract

e15634 Background: Artificial intelligence (AI) is emerging as a revolutionary technology with the power to transform healthcare. IBM Watson for Oncology (WFO), as an AI clinical decision support system (CDSS), has been investigated about its impact on clinical decision making in some cancer types and shown potential to be an effective CDSS in cancer care. However, the feasibility of WFO in Chinese patients with hepatocellular carcinoma (HCC) has not been reported. Methods: Artificial intelligence (AI) is emerging as a revolutionary technology with the power to transform healthcare. IBM Watson for Oncology (WFO), as an AI clinical decision support system (CDSS), has been investigated about its impact on clinical decision making in some cancer types and shown potential to be an effective CDSS in cancer care. However, the feasibility of WFO in Chinese patients with hepatocellular carcinoma (HCC) has not been reported. Results: The overall concordance rate was 60.5%, with 53.7% and 61.4% in BCLC stage 0 and A respectively. After the MDT re-review, the overall, BCLC stage 0 and A concordance rate increased to 67.3%, 65.9% and 67.3%. The main discordance was that MDT recommended more aggressive treatment options (eg. hepatectomy) than WFO did. The increase in concordance rate may be due to the progress of treatment of HCC in the past 5 years. Conclusions: With the concordance and reasonability verified by MDT in this study, WFO may provide practical reference in BCLC stage 0/A HCC. Localization is required to cover the disparity in guideline and patient characteristics between China and the US.