Gu-Wei Ji1,2,3, Ye Fan1,2,3, Dong-Wei Sun1,2,3, Ming-Yu Wu4, Ke Wang1,2,3, Xiang-Cheng Li1,2,3, Xue-Hao Wang1,2,3. 1. Hepatobiliary Center, The First Affiliated Hospital of Nanjing Medical University, Nanjing, People's Republic of China. 2. Key Laboratory of Liver Transplantation, Chinese Academy of Medical Sciences, Nanjing, People's Republic of China. 3. NHC Key Laboratory of Living Donor Liver Transplantation (Nanjing Medical University), Nanjing, People's Republic of China. 4. Department of Hepatobiliary Surgery, Wuxi People's Hospital, Wuxi, People's Republic of China.
Abstract
BACKGROUND: Improved prognostic prediction is needed to stratify patients with early hepatocellular carcinoma (EHCC) to refine selection of adjuvant therapy. We aimed to develop a machine learning (ML)-based model to predict survival after liver resection for EHCC based on readily available clinical data. METHODS: We analyzed data of surgically resected EHCC (tumor≤5 cm without evidence of extrahepatic disease or major vascular invasion) patients from the Surveillance, Epidemiology, and End Results (SEER) Program to train and internally validate a gradient-boosting ML model to predict disease-specific survival (DSS). We externally tested the ML model using data from 2 Chinese institutions. Patients treated with resection were matched by propensity score to those treated with transplantation in the SEER-Medicare database. RESULTS: A total of 2778 EHCC patients treated with resection were enrolled, divided into 1899 for training/validation (SEER) and 879 for test (Chinese). The ML model consisted of 8 covariates (age, race, alpha-fetoprotein, tumor size, multifocality, vascular invasion, histological grade and fibrosis score) and predicted DSS with C-Statistics >0.72, better than proposed staging systems across study cohorts. The ML model could stratify 10-year DSS ranging from 70% in low-risk subset to 5% in high-risk subset. Compared with low-risk subset, no remarkable survival benefits were observed in EHCC patients receiving transplantation before and after propensity score matching. CONCLUSION: An ML model trained on a large-scale dataset has good predictive performance at individual scale. Such a model is readily integrated into clinical practice and will be valuable in discussing treatment strategies.
BACKGROUND: Improved prognostic prediction is needed to stratify patients with early hepatocellular carcinoma (EHCC) to refine selection of adjuvant therapy. We aimed to develop a machine learning (ML)-based model to predict survival after liver resection for EHCC based on readily available clinical data. METHODS: We analyzed data of surgically resected EHCC (tumor≤5 cm without evidence of extrahepatic disease or major vascular invasion) patients from the Surveillance, Epidemiology, and End Results (SEER) Program to train and internally validate a gradient-boosting ML model to predict disease-specific survival (DSS). We externally tested the ML model using data from 2 Chinese institutions. Patients treated with resection were matched by propensity score to those treated with transplantation in the SEER-Medicare database. RESULTS: A total of 2778 EHCC patients treated with resection were enrolled, divided into 1899 for training/validation (SEER) and 879 for test (Chinese). The ML model consisted of 8 covariates (age, race, alpha-fetoprotein, tumor size, multifocality, vascular invasion, histological grade and fibrosis score) and predicted DSS with C-Statistics >0.72, better than proposed staging systems across study cohorts. The ML model could stratify 10-year DSS ranging from 70% in low-risk subset to 5% in high-risk subset. Compared with low-risk subset, no remarkable survival benefits were observed in EHCC patients receiving transplantation before and after propensity score matching. CONCLUSION: An ML model trained on a large-scale dataset has good predictive performance at individual scale. Such a model is readily integrated into clinical practice and will be valuable in discussing treatment strategies.
Authors: Ju Hyun Shim; Mi-Jung Jun; Seungbong Han; Young-Joo Lee; Sung-Gyu Lee; Kang Mo Kim; Young-Suk Lim; Han Chu Lee Journal: Ann Surg Date: 2015-05 Impact factor: 12.969
Authors: Jonathan A C Sterne; Ian R White; John B Carlin; Michael Spratt; Patrick Royston; Michael G Kenward; Angela M Wood; James R Carpenter Journal: BMJ Date: 2009-06-29
Authors: Junichi Shindoh; Andreas Andreou; Thomas A Aloia; Giuseppe Zimmitti; Gregory Y Lauwers; Alexis Laurent; David M Nagorney; Jacques Belghiti; Daniel Cherqui; Ronnie Tung-Ping Poon; Norihiro Kokudo; Jean-Nicolas Vauthey Journal: Ann Surg Oncol Date: 2012-11-21 Impact factor: 5.344