Machine Learning–Based Personalized Prediction of Hepatocellular Carcinoma Recurrence After Radiofrequency Ablation

• Published in: Gastro hep advances Vol. 1; no. 1; pp. 29 - 37
• Main Authors: Sato, Masaya, Tateishi, Ryosuke, Moriyama, Makoto, Fukumoto, Tsuyoshi, Yamada, Tomoharu, Nakagomi, Ryo, Kinoshita, Mizuki Nishibatake, Nakatsuka, Takuma, Minami, Tatsuya, Uchino, Koji, Enooku, Kenichiro, Nakagawa, Hayato, Shiina, Shuichiro, Ninomiya, Kota, Kodera, Satoshi, Yatomi, Yutaka, Koike, Kazuhiko
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Inc 2022; Elsevier
• Subjects: DeepSurv; Hepatocellular Carcinoma; Machine Learning; Radiofrequency Ablation; DeepSurv; AST; AFP-L3; PT; MRI; DL; ALT; HCC; MTLR; GBDT; AFP; SVM; RFA; Machine Learning; TB; DCP; DT; CT; Radiofrequency Ablation; HBs; CPH; HCV; Hepatocellular Carcinoma; ML
• ISSN: 2772-5723; 2772-5723
• DOI: 10.1016/j.gastha.2021.09.003

Radiofrequency ablation (RFA) is a widely accepted, minimally invasive treatment for hepatocellular carcinoma (HCC). This study aimed to develop a machine learning (ML) model to predict the risk of HCC recurrence after RFA treatment for individual patients. We included a total of 1778 patients with treatment-naïve HCC who underwent RFA. The cumulative probability of overall recurrence after the initial RFA treatment was 78.9% and 88.0% at 5 and 10 years, respectively. We developed a conventional Cox proportional hazard model and 6 ML models—including the deep learning–based DeepSurv model. Model performance was evaluated using Harrel’s c-index and was validated externally using the split-sample method. The gradient boosting decision tree (GBDT) model achieved the best performance with a c-index of 0.67 from external validation, and it showed a high discriminative ability in stratifying the external validation sample into 2, 3, and 4 different risk groups (P < .001 among all risk groups). The c-index of DeepSurv was 0.64. In order of significance, the tumor number, serum albumin level, and des-gamma-carboxyprothrombin level were the most important variables for the prediction of HCC recurrence in the GBDT model. Also, the current GBDT model enabled the output of a personalized cumulative recurrence prediction curve for each patient. We developed a novel ML model for the personalized risk prediction of HCC recurrence after RFA treatment. The current model may lead to the personalization of effective follow-up strategies after RFA treatment according to the risk stratification of HCC recurrence.