Survival Risk Prediction of Esophageal Cancer Based on Self-Organizing Maps Clustering and Support Vector Machine Ensembles
Open Access
- 8 July 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 131449-131460
Abstract
This article provides a method based on self-organizing maps (SOM) neural network clustering and support vector machine (SVM) ensembles to predict the survival risk levels of esophageal cancer. Nine blood indexes related to patient survival are found by using SOM clustering method. Two critical thresholds for survival are found by plotting the receiver operating characteristic (ROC) curve twice, and the lifetime is divided into three risk levels. Using the SVM method, patients’ risk levels are predicted and assessed. Four kernel functions of SVM are compared, and the prediction effect of RBF kernel function is better than other kernel functions. The parameters of SVM are optimized by using genetic algorithm (GA), particle swarm algorithm (PSO) and artificial bee colony (ABC) algorithm. Experimental results show that the prediction accuracies are improved by using optimization algorithms. After comparison, ABC-SVM has better prediction results than GA-SVM and PSO-SVM with a high prediction rate and fast running time.Keywords
Funding Information
- National Key Research and Development Program of China for International S and T Cooperation Projects (2017YFE0103900)
- Joint Funds of the National Natural Science Foundation of China (U1804262)
- State Key Program of National Natural Science of China (61632002)
- Foundation of Young Key Teachers from University of Henan Province (2018GGJS092)
- Youth Talent Lifting Project of Henan Province (2018HYTP016)
- Henan Province University Science and Technology Innovation Talent Support Plan (20HASTIT027)
- Zhongyuan Thousand Talents Program (204200510003)
- Open Fund of State Key Laboratory of Esophageal Cancer Prevention & Treatment (K2020-0010, K2020-0011)
This publication has 46 references indexed in Scilit:
- GA-SVM Algorithm for Improving Land-Cover Classification Using SAR and Optical Remote Sensing DataIEEE Geoscience and Remote Sensing Letters, 2017
- SVM and SVM Ensembles in Breast Cancer PredictionPLOS ONE, 2017
- Optimizing connection weights in neural networks using the whale optimization algorithmSoft Computing, 2016
- Informing etiologic research priorities for squamous cell esophageal cancer in Africa: A review of setting‐specific exposures to known and putative risk factorsInternational Journal of Cancer, 2016
- The Whale Optimization AlgorithmAdvances in Engineering Software, 2016
- A SOM clustering pattern sequence-based next symbol prediction method for day-ahead direct electricity load and price forecastingEnergy Conversion and Management, 2015
- Artificial Fish School Algorithm Applied in a Combinatorial Optimization ProblemInternational Journal of Intelligent Systems and Applications, 2010
- A distributed PSO–SVM hybrid system with feature selection and parameter optimizationApplied Soft Computing, 2008
- A Simulated Annealing-Based Multiobjective Optimization Algorithm: AMOSAIEEE Transactions on Evolutionary Computation, 2008
- PI3-K/Akt pathway contributes to IL-6-dependent growth of 7TD1 cellsCancer Cell International, 2003