Rong-Yun Mai1,2,3, Jie Zeng2,3, Wei-da Meng1,3, Hua-Ze Lu1,3, Rong Liang3,4, Yan Lin3,4, Guo-Bin Wu1,3, Le-Qun Li1,3, Liang Ma1,3, Jia-Zhou Ye5,6, Tao Bai7,8. 1. Department of Hepatobilliary & Pancreatic Surgery, Guangxi Medical University Cancer Hospital, 71 He Di Road, Nanning, China. 2. Department of Experimental Research, Guangxi Medical University Cancer Hospital, Nanning, 530021, China. 3. Guangxi Liver Cancer Diagnosis and Treatment Engineering and Technology Research Center, Nanning, 530021, China. 4. Department of First Chemotherapy, Guangxi Medical University Cancer Hospital, Nanning, 530021, China. 5. Department of Hepatobilliary & Pancreatic Surgery, Guangxi Medical University Cancer Hospital, 71 He Di Road, Nanning, China. yejiazhou2019@163.com. 6. Guangxi Liver Cancer Diagnosis and Treatment Engineering and Technology Research Center, Nanning, 530021, China. yejiazhou2019@163.com. 7. Department of Hepatobilliary & Pancreatic Surgery, Guangxi Medical University Cancer Hospital, 71 He Di Road, Nanning, China. baitao@gxmu.edu.cn. 8. Guangxi Liver Cancer Diagnosis and Treatment Engineering and Technology Research Center, Nanning, 530021, China. baitao@gxmu.edu.cn.
Abstract
BACKGROUND: The accurate prediction of post-hepatectomy early recurrence (PHER) of hepatocellular carcinoma (HCC) is vital in determining postoperative adjuvant treatment and monitoring. This study aimed to develop and validate an artificial neural network (ANN) model to predict PHER in HCC patients without macroscopic vascular invasion. METHODS: Nine hundred and three patients who underwent curative liver resection for HCC participated in this study. They were randomly divided into derivation (n = 679) and validation (n = 224) cohorts. The ANN model was developed in the derivation cohort and subsequently verified in the validation cohort. RESULTS: PHER morbidity in the derivation and validation cohorts was 34.8 and 39.2%, respectively. A multivariable analysis revealed that hepatitis B virus deoxyribonucleic acid load, γ-glutamyl transpeptidase level, α-fetoprotein level, tumor size, tumor differentiation, microvascular invasion, satellite nodules, and blood loss were significantly associated with PHER. These factors were incorporated into an ANN model, which displayed greater discriminatory abilities than a Cox's proportional hazards model, preexisting recurrence models, and commonly used staging systems for predicting PHER. The recurrence-free survival curves were significantly different between patients that had been stratified into two risk groups. CONCLUSION: When compared to other models and staging systems, the ANN model has a significant advantage in predicting PHER for HCC patients without macroscopic vascular invasion.
BACKGROUND: The accurate prediction of post-hepatectomy early recurrence (PHER) of hepatocellular carcinoma (HCC) is vital in determining postoperative adjuvant treatment and monitoring. This study aimed to develop and validate an artificial neural network (ANN) model to predict PHER in HCCpatients without macroscopic vascular invasion. METHODS: Nine hundred and three patients who underwent curative liver resection for HCC participated in this study. They were randomly divided into derivation (n = 679) and validation (n = 224) cohorts. The ANN model was developed in the derivation cohort and subsequently verified in the validation cohort. RESULTS: PHER morbidity in the derivation and validation cohorts was 34.8 and 39.2%, respectively. A multivariable analysis revealed that hepatitis B virus deoxyribonucleic acid load, γ-glutamyl transpeptidase level, α-fetoprotein level, tumor size, tumor differentiation, microvascular invasion, satellite nodules, and blood loss were significantly associated with PHER. These factors were incorporated into an ANN model, which displayed greater discriminatory abilities than a Cox's proportional hazards model, preexisting recurrence models, and commonly used staging systems for predicting PHER. The recurrence-free survival curves were significantly different between patients that had been stratified into two risk groups. CONCLUSION: When compared to other models and staging systems, the ANN model has a significant advantage in predicting PHER for HCCpatients without macroscopic vascular invasion.
Authors: Peter Ström; Kimmo Kartasalo; Henrik Olsson; Leslie Solorzano; Brett Delahunt; Daniel M Berney; David G Bostwick; Andrew J Evans; David J Grignon; Peter A Humphrey; Kenneth A Iczkowski; James G Kench; Glen Kristiansen; Theodorus H van der Kwast; Katia R M Leite; Jesse K McKenney; Jon Oxley; Chin-Chen Pan; Hemamali Samaratunga; John R Srigley; Hiroyuki Takahashi; Toyonori Tsuzuki; Murali Varma; Ming Zhou; Johan Lindberg; Cecilia Lindskog; Pekka Ruusuvuori; Carolina Wählby; Henrik Grönberg; Mattias Rantalainen; Lars Egevad; Martin Eklund Journal: Lancet Oncol Date: 2020-01-08 Impact factor: 41.316
Authors: Michael D Kluger; Juan A Salceda; Alexis Laurent; Claude Tayar; Christophe Duvoux; Thomas Decaens; Alain Luciani; Jeanne Tran Van Nhieu; Daniel Azoulay; Daniel Cherqui Journal: J Hepatol Date: 2014-12-18 Impact factor: 25.083
Authors: Kang Wang; Wei Xing Guo; Min Shan Chen; Yi Lei Mao; Bei Cheng Sun; Jie Shi; Yao Jun Zhang; Yan Meng; Ye Fa Yang; Wen Ming Cong; Meng Chao Wu; Wan Yee Lau; Shu Qun Cheng Journal: Medicine (Baltimore) Date: 2016-03 Impact factor: 1.889