Abstract
In order to find the blood indicators significantly associated with the survival of esophageal cancer and predict the classification of patients’ risk levels in an affordable, convenient, and accurate manner, a method based on self-organizing maps (SOM) neural network clustering and support vector machine prediction risk levels is proposed. Seventeen blood indicators of 501 esophageal cancer patients are pretreated. Nine factors related to patient survival are found by using SOM clustering method, and verified by using COX multi-factor risk regression model. Two critical thresholds for survival are found by plotting the ROC curve twice, and the lifetime are divided into three risk levels. The following is to select the data information of 9 blood indicators of 180 patients, including risk level 1, risk level 2, and risk level 3. Using the SVM method, patients’ risk levels are predicted, the accuracy rate reached 91.11%. After the parameters optimization of genetic algorithm (GA), the accuracy rate reached 93.33%. Compared with BP neural network, it is concluded that SVM is superior to BP neural networks algorithm, and GA-SVM is better than SVM. This article provides a new method for early diagnosis and prediction of esophageal cancer.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Menya, D., Kigen, N., Oduor, M.: Traditional and commercial alcohols and esophageal cancer risk in Kenya. Int. J. Cancer 144(3), 459–469 (2019)
Gillies, C., Farrukh, A., Abrams, R.: Risk of esophageal cancer in achalasia cardia: a meta-analysis. JGH Open 3(3), 196–200 (2019)
Lin, S., Zhang, N.: Radiation modality use and cardiopulmonary mortality risk in elderly patients with esophageal cancer. Cancer 122(6), 917–928 (2016)
Raymond, D., Seder, C., Wright, C.: Predictors of major morbidity or mortality after resection for esophageal cancer: a society of thoracic surgeon’s general thoracic surgery database risk adjustment model. Ann. Thorac. Surg. 102(1), 207–214 (2016)
Takeuchi, M., Suda, K., Hamamoto, Y.: Technical feasibility and oncologic safety of diagnostic endoscopic resection for superficial esophageal cancer. Gastrointest. Endosc. 88(3), 456–46 (2018)
McCormack, V., Menya, D., Munishi, M.: Informing etiologic research priorities for squamous cell esophageal cancer in Africa: a review of setting-specific exposures to known and putative risk factors. Int. J. Cancer 140(2), 259–271 (2017)
Miwata, T., et al.: Risk factors for esophageal stenosis after entire circumferential endoscopic submucosal dissection for superficial esophageal squamous cell carcinoma. Surg. Endosc. 30(9), 4049–4056 (2015). https://doi.org/10.1007/s00464-015-4719-3
Omari, T., Szczesniak, M., Maclean, J.: Correlation of esophageal pressure-flow analysis findings with bolus transit patterns on video fluoroscopy. Dis. Esophagus 29(2), 166–173 (2016)
Jin, C., Pok, G., Lee, Y.: A SOM clustering pattern sequence-based next symbol prediction method for day-ahead direct electricity load and price forecasting. Energy Convers. Manag. 90, 84–92 (2015)
Delgado, S., Higuera, C., Calle-Espinosa, J.: A SOM prototype-based cluster analysis methodology. Expert Syst. Appl. 88, 14–28 (2017)
El-Zimaity, H., Di, P., Novella, R.: Risk factors for esophageal cancer: emphasis on infectious agents. Ann. N. Y. Acad. Sci. 1434(1), 319–332 (2018)
Ide, S., Toiyama, Y., Shimura, T.: Angiopoietin-like protein 2 acts as a novel biomarker for diagnosis and prognosis in patients with esophageal cancer. Ann. Surg. Oncol. 22(8), 2585–2592 (2015)
Zeng, H., Zheng, R., Zhang, S.: Esophageal cancer statistics in China, 2011: estimates based on 177 cancer registries. Thorac. Cancer 7(2), 232–237 (2016)
Kanzaki, N., Kataoka, T., Etani, R.: Analysis of liver damage from radon, X-ray, or alcohol treatments in mice using a self-organizing map. J. Radiat. Res. 58(1), 33–40 (2017)
Roy, A., Bhattacharya, S., Guin, K.: Prediction of esophageal cancer using demographic, lifestyle, patient history, and basic clinical tests. Int. J. Adv. Eng. Sci. Appl. Math. 9(4), 214–223 (2017). https://doi.org/10.1007/s12572-017-0199-0
Yerokun, B., Sun, Z., Yang, C.: Minimally invasive versus open esophagostomy for esophageal cancer: a population-based analysis. Ann. Thorac. Surg. 102(2), 416–423 (2016)
Haisley, K.R., Hart, C.M., Kaempf, A.J., Dash, N.R., Dolan, J.P., Hunter, J.G.: Specific tumor characteristics predict upstaging in early-stage esophageal cancer. Ann. Surg. Oncol. 26(2), 514–522 (2018). https://doi.org/10.1245/s10434-018-6804-z
Arnold, M., Laversanne, M., Brown, L.: Predicting the future burden of esophageal cancer by histological subtype: international trends in incidence up to 2030. Am. J. Gastroenterol. 112(8), 1247 (2017)
Mora, A., Nakajima, Y., Okada, T.: Comparative study of predictive mortality scores in esophagostomy with three-field lymph node dissection in patients with esophageal cancer. Dig. Surg. 36(1), 67–75 (2019)
Huang, S., Cai, N., Pacheco, P.P.: Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics-Proteomics 15(1), 41–51 (2018)
Kourou, K., Exarchos, T.P., Exarchos, K.P.: Machine learning applications in cancer prognosis and prediction. Comput. Struct. Biotechnol. J. 13, 8–17 (2015)
Sun, J., Zhao, X., Fang, J., Wang, Y.: Autonomous memristor chaotic systems of infinite chaotic attractors and circuitry realization. Nonlinear Dyn. 94(4), 2879–2887 (2018). https://doi.org/10.1007/s11071-018-4531-4
Huang, M.W., Chen, C.W., Lin, W.C.: SVM and SVM ensembles in breast cancer prediction. PLoS ONE 12(1), e0161501 (2017)
Sukawattanavijit, C., Chen, J., Zhang, H.: GA-SVM algorithm for improving land-cover classification using SAR and optical remote sensing data. Geosci. Remote Sens. Lett. 14(3), 284–288 (2017)
Tao, Z., Huiling, L., Wenwen, W.: GA-SVM based feature selection and parameter optimization in hospitalization expense modeling. Appl. Soft Comput. 75, 323–332 (2019)
Acknowledgements
This work was supported in part by the National Key R and D Program of China for International S and T Cooperation Projects (2017YFE0103900), in part by the Joint Funds of the National Natural Science Foundation of China (U1804262), in part by the State Key Program of National Natural Science of China under Grant 61632002, in part by the National Natural Science of China under Grant 61603348, Grant 61775198, Grant 61603347, and Grant 61572446, in part by the Foundation of Young Key Teachers from University of Henan Province (2018GGJS092), and in part by the Youth Talent Lifting Project of Henan Province (2018HYTP016) and Henan Province University Science and Technology Innovation Talent Support Plan under Grant 20HASTIT027.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yang, Y., Li, Z., Wang, Y. (2020). Risk Prediction of Esophageal Cancer Using SOM Clustering, SVM and GA-SVM. In: Pan, L., Liang, J., Qu, B. (eds) Bio-inspired Computing: Theories and Applications. BIC-TA 2019. Communications in Computer and Information Science, vol 1160. Springer, Singapore. https://doi.org/10.1007/978-981-15-3415-7_29
Download citation
DOI: https://doi.org/10.1007/978-981-15-3415-7_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3414-0
Online ISBN: 978-981-15-3415-7
eBook Packages: Computer ScienceComputer Science (R0)