Jianxing Zeng1,2,3, Jinhua Zeng1,2,4, Kongying Lin3, Haitao Lin3, Qionglan Wu5, Pengfei Guo3, Weiping Zhou6, Jingfeng Liu1,2,4. 1. Department of Hepatic Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou, China. 2. The First Affiliated Hospital of Fujian Medical University, Fuzhou, China. 3. Southeast Big Data Institute of Hepatobiliary Health, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou, China. 4. The Liver Center of Fujian Province, Fujian Medical University, Fuzhou, China. 5. Department of Pathology, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou, China. 6. The Third Department of Hepatic Surgery, Eastern Hepatobiliary Surgery Hospital, Second Military Medical University, Shanghai, China.
Abstract
Background: Early recurrence is common for hepatocellular carcinoma (HCC) after surgical resection, being the leading cause of death. Traditionally, the COX proportional hazard (CPH) models based on linearity assumption have been used to predict early recurrence, but predictive performance is limited. Machine learning models offer a novel methodology and have several advantages over CPH models. Hence, the purpose of this study was to compare random survival forests (RSF) model with CPH models in prediction of early recurrence for HCC patients after curative resection. Methods: A total of 4,758 patients undergoing curative resection from two medical centers were included. Fifteen features including age, gender, etiology, platelet count, albumin, total bilirubin, AFP, tumor size, tumor number, microvascular invasion, macrovascular invasion, Edmondson-Steiner grade, tumor capsular, satellite nodules and liver cirrhosis were used to construct the RSF model in training cohort. Discrimination, calibration, clinical usefulness and overall performance were assessed and compared with other models. Results: Five hundred survival trees were used to generate the RFS model. The five highest Variable Importance (VIMP) were tumor size, macrovascular invasion, microvascular invasion, tumor number and AFP. In training, internal and external validation cohort, the C-index of RSF model were 0.725 [standard errors (SE) =0.005], 0.762 (SE =0.011) and 0.747 (SE =0.016), respectively; the Gönen & Heller's K of RSF model were 0.684 (SE =0.005), 0.711 (SE =0.008) and 0.697 (SE =0.014), respectively; the time-dependent AUC (2 years) of RSF model were 0.818 (SE =0.008), 0.823 (SE =0.014) and 0.785 (SE =0.025), respectively. The RSF model outperformed early recurrence after surgery for liver tumor (ERASL) model, Korean model, American Joint Committee on Cancer tumor-node-metastasis (AJCC TNM) stage, Barcelona Clinic Liver Cancer (BCLC) stage and Chinese stage. The RSF model is capable of stratifying patients into three different risk groups (low-risk, intermediate-risk, high-risk groups) in the training and two validation cohorts (all P<0.0001). A web-based prediction tool was built to facilitate clinical application (https://recurrenceprediction.shinyapps.io/surgery_predict/). Conclusions: The RSF model is a reliable tool to predict early recurrence for patients with HCC after curative resection because it exhibited superior performance compared with other models. This novel model will be helpful to guide postoperative follow-up and adjuvant therapy. 2022 Hepatobiliary Surgery and Nutrition. All rights reserved.
Background: Early recurrence is common for hepatocellular carcinoma (HCC) after surgical resection, being the leading cause of death. Traditionally, the COX proportional hazard (CPH) models based on linearity assumption have been used to predict early recurrence, but predictive performance is limited. Machine learning models offer a novel methodology and have several advantages over CPH models. Hence, the purpose of this study was to compare random survival forests (RSF) model with CPH models in prediction of early recurrence for HCC patients after curative resection. Methods: A total of 4,758 patients undergoing curative resection from two medical centers were included. Fifteen features including age, gender, etiology, platelet count, albumin, total bilirubin, AFP, tumor size, tumor number, microvascular invasion, macrovascular invasion, Edmondson-Steiner grade, tumor capsular, satellite nodules and liver cirrhosis were used to construct the RSF model in training cohort. Discrimination, calibration, clinical usefulness and overall performance were assessed and compared with other models. Results: Five hundred survival trees were used to generate the RFS model. The five highest Variable Importance (VIMP) were tumor size, macrovascular invasion, microvascular invasion, tumor number and AFP. In training, internal and external validation cohort, the C-index of RSF model were 0.725 [standard errors (SE) =0.005], 0.762 (SE =0.011) and 0.747 (SE =0.016), respectively; the Gönen & Heller's K of RSF model were 0.684 (SE =0.005), 0.711 (SE =0.008) and 0.697 (SE =0.014), respectively; the time-dependent AUC (2 years) of RSF model were 0.818 (SE =0.008), 0.823 (SE =0.014) and 0.785 (SE =0.025), respectively. The RSF model outperformed early recurrence after surgery for liver tumor (ERASL) model, Korean model, American Joint Committee on Cancer tumor-node-metastasis (AJCC TNM) stage, Barcelona Clinic Liver Cancer (BCLC) stage and Chinese stage. The RSF model is capable of stratifying patients into three different risk groups (low-risk, intermediate-risk, high-risk groups) in the training and two validation cohorts (all P<0.0001). A web-based prediction tool was built to facilitate clinical application (https://recurrenceprediction.shinyapps.io/surgery_predict/). Conclusions: The RSF model is a reliable tool to predict early recurrence for patients with HCC after curative resection because it exhibited superior performance compared with other models. This novel model will be helpful to guide postoperative follow-up and adjuvant therapy. 2022 Hepatobiliary Surgery and Nutrition. All rights reserved.
Authors: Ana Carolina Alba; Thomas Agoritsas; Michael Walsh; Steven Hanna; Alfonso Iorio; P J Devereaux; Thomas McGinn; Gordon Guyatt Journal: JAMA Date: 2017-10-10 Impact factor: 56.272
Authors: Philip J Johnson; Sarah Berhane; Chiaki Kagebayashi; Shinji Satomura; Mabel Teng; Helen L Reeves; James O'Beirne; Richard Fox; Anna Skowronska; Daniel Palmer; Winnie Yeo; Frankie Mo; Paul Lai; Mercedes Iñarrairaegui; Stephen L Chan; Bruno Sangro; Rebecca Miksad; Toshifumi Tada; Takashi Kumada; Hidenori Toyoda Journal: J Clin Oncol Date: 2014-12-15 Impact factor: 44.544