A Machine Learning Approach Yields a Multiparameter Prognostic Marker in Liver Cancer
Open Access
- 1 March 2021
- journal article
- research article
- Published by American Association for Cancer Research (AACR) in Cancer Immunology Research
- Vol. 9 (3), 337-347
- https://doi.org/10.1158/2326-6066.CIR-20-0616
Abstract
A number of staging systems have been developed to predict clinical outcomes in hepatocellular carcinoma (HCC). However, no general consensus has been reached regarding the optimal model. New approaches such as machine learning (ML) strategies are powerful tools for incorporating risk factors from multiple platforms. We retrospectively reviewed the baseline information, including clinicopathologic characteristics, laboratory parameters, and peripheral immune features reflecting T-cell function, from three HCC cohorts. A gradient-boosting survival (GBS) classifier was trained with prognosis-related variables in the training dataset and validated in two independent cohorts. We constructed a 20-eature GBS model classifier incorporating one clinical feature, 14 laboratory parameters, and five T-cell function parameters obtained from peripheral blood mononuclear cells. The GBS model-derived risk scores demonstrated high concordance indexes (C-indexes): 0.844, 0.827, and 0.806 in the training set and validation sets 1 and 2, respectively. The GBS classifier could separate patients into high-, medium- and low-risk subgroups with respect to death in all datasets (P < 0.05 for all comparisons). A higher risk score was positively correlated with a higher clinical stage and the presence of portal vein tumor thrombus (PVTT). Subgroup analyses with respect to Child-Pugh class, Barcelona Clinic Liver Cancer stage, and PVTT status supported the prognostic relevance of the GBS-erived risk algorithm independent of the conventional tumor staging system. In summary, a multiparameter ML algorithm incorporating clinical characteristics, laboratory parameters, and peripheral immune signatures offers a different approach to identify patients with the greatest risk of HCC-related death.Other Versions
Funding Information
- National Key Sci-Tech Special Project of China (2018ZX10302207)
- National Science Foundation of China (81874435)
- Dengfeng Talent Support Program of Beijing Municipal Administration of Hospitals (DFL20191803)
- Special Fund of Capital Health Research and Development (2020-2-2173)
This publication has 51 references indexed in Scilit:
- Safety and Activity of Anti–PD-L1 Antibody in Patients with Advanced CancerThe New England Journal of Medicine, 2012
- Eight-Signature Classifier for Prediction of Nasopharyngeal Carcinoma SurvivalJournal of Clinical Oncology, 2011
- Hepatocellular CarcinomaThe New England Journal of Medicine, 2011
- Modified RECIST (mRECIST) Assessment for Hepatocellular CarcinomaSeminars in Liver Disease, 2010
- Hepatitis B- and C-related hepatocellular carcinomas yield different clinical features and prognosisEuropean Journal of Cancer, 2006
- Type, Density, and Location of Immune Cells Within Human Colorectal Tumors Predict Clinical OutcomeScience, 2006
- X-TileClinical Cancer Research, 2004
- Prognostic staging system for hepatocellular carcinoma (CLIP score): its value and limitations, and a proposal for a new staging system, the Japan Integrated Staging Score (JIS score)The Esophagus, 2003
- Prospective Validation of the Cancer of the Liver Italian Program(CLIP) Score: A New Prognostic System for Patients With Cirrhosis and Hepatocellular CarcinomaJournal of Hepatology, 2000
- Prognosis of Hepatocellular Carcinoma: The BCLC Staging ClassificationSeminars in Liver Disease, 1999