Cancer Management and Research (Jan 2022)
Machine Learning-Based Model for the Prognosis of Postoperative Gastric Cancer
Abstract
Donghui Liu,1,2 Xuyao Wang,3 Long Li,4 Qingxin Jiang,5 Xiaoxue Li,2 Menglin Liu,2 Wenxin Wang,2 Enhong Shi,2 Chenyao Zhang,2 Yinghui Wang,2 Yan Zhang,1,* Liru Wang1,2,* 1School of Life Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang Province, People’s Republic of China; 2Department of Oncology, Heilongjiang Provincial Hospital, Harbin, Heilongjiang Province, People’s Republic of China; 3Department of Pharmacy, Harbin Second Hospital, Harbin, Heilongjiang Province, People’s Republic of China; 4Department of General Surgery, First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province, People’s Republic of China; 5Department of General Surgery, Harbin 242 Hospital of Genertec Medical, Harbin, Heilongjiang Province, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yan ZhangSchool of Life Science and Technology, Harbin Institute of Technology, No. 92 Xidazhi Street, Nangang District, Harbin, Heilongjiang, People’s Republic of ChinaTel +86 13936253249Email [email protected] WangDepartment of Oncology, Heilongjiang Provincial Hospital, No. 82 Zhongshan Road, Xiangfang District, Harbin, Heilongjiang, People’s Republic of China, Tel +86 13633609001Email [email protected]: The use of machine learning (ML) in predicting disease prognosis has increased, and scientists have adopted different methods for cancer classification to optimize the early screening of cancer to determine its prognosis in advance. In this study, we aimed at improving the prediction accuracy of gastric cancer in postoperation patients by constructing a highly effective prognostic model.Methods: The study used postoperative gastric cancer patient data from the SEER database. The LASSO regression method was used to construct a clinical prognostic model, and four machine learning methods (Boruta algorithm, neural network, support vector machine, and random forest) were used to screen and recombine the features to construct an ML prognostic model. Clinical information on 955 postoperative gastric cancer patients collected from the Affiliated Tumor Hospital of Harbin Medical University was used for external verification.Results: Experimental results showed that the AUC values of 1, 3 and 5 years in the training set, validation set and external validation set of clinical prognosis model and ML prognosis model directly established by LASSO regression are all around 0.8.Conclusion: Both models can accurately evaluate the prognosis of postoperative patients with gastric cancer, which may be helpful for accurate and personalized treatment of postoperative patients with gastric cancer.Keywords: machine learning, gastric cancer, prognosis, Boruta, ElasticNet, SVM, random forest
