Application of Stacked Ensemble Techniques in Head and Neck Squamous Cell Carcinoma Prognostic Feature Subsets

Owusu, Damianus Kofi; Nyarko, Christiana Cynthia; Acquah, Joseph; Yarney, Joel

doi:10.22044/jadm.2023.12420.2388

Document Type : Original/Review Paper

Authors

¹ University of Mines and Technology, Ghana.

² Department of Mathematical Sciences, Faculty of Engineering, University of Mines and Technology, Tarkwa, Ghana.

³ Department of Radiotherapy and Oncology, National Centre for Radiotherapy & Nuclear Medicine, Korle Bu, Accra, Ghana.

https://doi.org/10.22044/jadm.2023.12420.2388

Abstract

Head and neck cancer (HNC) recurrence is ever increasing among Ghanaian men and women. Because not all machine learning classifiers are equally created, even if multiple of them suite very well for a given task, it may be very difficult to find one which performs optimally given different distributions. The stacking learns how to best combine weak classifier models to form a strong model. As a prognostic model for classifying HNSCC recurrence patterns, this study tried to identify the best stacked ensemble classifier model when the same ML classifiers for feature selection and stacked ensemble learning are used. Four stacked ensemble models; in which first one used two base classifiers: gradient boosting machine (GBM) and distributed random forest (DRF); second one used three base classifiers: GBM, DRF, and deep neural network (DNN); third one used four base classifiers: GBM, DRF, DNN, and generalized linear model (GLM); and fourth one used five base classifiers: GBM, DRF, DNN, GLM, and Naïve bayes (NB) were developed, using GBM meta-classifier in each case. The results showed that implementing stacked ensemble technique consisting of five base classifiers on gradient boosted features achieved better performance than achieved on other feature subsets, and implementing this stacked ensemble technique on gradient boosted features achieved better performance compared to other stacked ensemble techniques implemented on gradient boosted features and other feature subsets used. Learning stacked ensemble technique having five base classifiers on GBM features is clinically appropriate as a prognostic model for classifying and predicting HNSCC patients’ recurrence data.

Keywords

Main Subjects

H.3. Artificial Intelligence

References

[1] A. Argiris, K. J. Harrington, M. Tahara, et al. (2017). Evidence-based treatment options in recurrent and/or metastatic squamous cell carcinoma of the head and neck. Front Oncol., vol. 7, no. 72, [PMC free article] [PubMed] [Google Scholar]

[2] A. Argiris, M. V. Karamouzis, D. Raben, and R. L. Ferris, (2008). Head and neck cancer. Lancet, vol. 371, no. 9625, pp. 1695–1709.

[3] R. O.Alabi, M. Elmusrati, I. Sawazaki-Colone, L. P. Kowalski, C. Haglund, and Coletta, et al. (2019). Machine learning application for prediction of locoregional recurrences in early oral tongue cancer: a Web-based prognostic tool, VirchowsArchiv.

[4] J. A. Bonner, P. M. Harari, J. Giralt, R. B. Cohen, C. U. Jones, R. K. Sur, et al. (2010). Radiotherapy plus Cetuximab for Locoregionally Advanced Head and Neck Cancer: 5-year Survival Data from a phase 3 Randomised Trial, and Relation between Cetuximab-Induced Rash and Survival. The Lancet Oncology. vol. 11, no. 1, pp. 21–28.

[5] J. Bourhis, A. Le Maître, B. Baujat, H. Audry, and J. P. Pignon. (2007). Meta-Analysis of Chemotherapy in Head, Neck Cancer Collaborative Group, Meta-Analysis of Radiotherapy in Carcinoma of Head, Neck Collaborative Group, Meta-Analysis of Chemotherapy in Nasopharynx Carcinoma Collaborative Group Individual patients’ data meta-analyses in head and neck cancer. Curr. Opin. Oncol., vol. 19, pp. 188–194.

[6] F. Bray, et al. (2018). Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, vol. 6, no. 68, pp. 394.

[7] B. Brockstein, D. J. Haraf, A. W. Rademaker, M. S. Kies, K. M Stenson, F. Rosen, et al. (2004). Patterns of failure, prognostic factors and survival in locoregionally advanced head and neck cancer treated with concomitant chemoradiotherapy: a 9-year, 337-patient, multi-institutional experience. Annals of oncology, vol.15, pp. 1179–1186.

[8] H. Cai, X. Pang, D. Dong, Y. Ma, Y. Huang, X. Fan, et al. (2019). Molecular Decision Tree Algorithms Predict Individual Recurrence Pattern for Locally Advanced Nasopharyngeal Carcinoma. Journal Cancer, vol. 10, no. 15, pp. 3323-3332.

[9] E. E. Cohen, S. J. LaMonte, N. L. Erb, K. L.Beckman, N. Sadeghi, , K. A. Hutcheson, et al. (2016). American Cancer Society Head and Neck Cancer Survivorship Care Guideline. CA Cancer Journal of Clin., vol. 66, no. 3, pp. 203 – 239.

[10] T. R. Cooney, and M. G. Poulsen, (1999). Is routine follow-up useful after combinedmodality therapy for advanced head and neck cancer? Arch. Otolaryngol Head Neck Surg., vol. 125, no. 4, pp. 379 – 382.

[11] D. Du, et al. (2019). Machine Learning Methods for Optimal Radiomics-Based Differentiation. jnl of Molecular Imaging & Biology·.

[12] J. A. Cruz, and D. S. Wishart, (2006). Review: Applications of Machine Learning in Cancer Prediction and Prognosis. Cancer Informatics, vol. 2, pp. 59-74.

[13] A. Diamant, A. Chatterjee, M. Vallières, G. Shenouda, and J. Seuntjens, (2019). Deep learning in head & neck cancer outcome prediction, scientific reports, pp. 1-19 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6391436/.

[14] R. M. Dom, S. A. Kareem, R. Zain and B. Abidin, (2007). An Adaptive Fuzzy Regression Model for the Prediction of Dichotomous Response Variables. Paper presented at the Fifth International IEEE Conference on Computational Science and Applications.

[15] R. O. Duda, P. E. Hart, and D. G. Stork, (2001). Pattern classification (2nd edition). New York: Wiley.

[16] K. P. Exarchos, Y. Goletsis, and D. I. Fotiadis, (2012). Multiparametric decision support system for the prediction of oral cancer reoccurrence. IEEE Trans InfTechnol Biomed, vo. 16, no. 6, pp. 1127–34.

[17] J. Ferlay, I. Soerjomataram, R. Dikshit, S. Eser, C. Mathers, M. Rebelo, et al. (2015). Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012. International Journal of Cancer, vol. 136, no. 5, pp. 359–386.

[18] C. Gibbons, et al. (2017). Supervised machine learning algorithms can classify open-text feedback of doctor performance with human level accuracy. J. Med. Internet Res. vo. 19, no. 3.

[19] P. Giraud, P. Giraud, A. Gasnier, R. El Ayachy, S. Kreps, J. P. Foy, C. Durdux, F. Huguet, A. Burgun, and J. E. Bibault, (2019). Radiomics and Machine Learning for Radiotherapy in Head and Neck Cancers. Frontiers. Oncology. vol. 9, no. 174, pp. 9:174.

[20] W. J. Goodwin, (2000). Salvage surgery for patients with recurrent squamous cell carcinoma of the upper aerodigestive tract: when do the ends justify the means? Laryngoscope, vol. 110, no. 3 (Pt 2 Suppl 93), pp. 1–18.

[21] R. I. Haddad, and D. M. Shin, (2008). Recent advances in head and neck cancer. Natl. Engl. Journal for Med., vol. 359, pp. 1143–1154.

[22] A. Jemal, F. Bray, M. M. Center, J. Ferlay, E. Ward, and D. Forman, (2011). Global cancer statistics. CA Cancer J. Clin., vol. 61, no. 2, pp. 69–90.

[23] F. Kabir, and S. A. Ludwig, (2019), “Enhancing the Performance of Classification Using Super Learning”, Data-Enabled Discov. Appl., vol. 3, no. 5, pp. 2-13.

[24] H. Kaur, S. Batra, (2017). HPCC an Ensembled framework for the prediction of the onset of diabetes. International Conference on Signal Processing, Computing and Control.

[25] T. Kawazu, A. Kazuyuki, K. Yoshiura, E. Nakayama and S. Kanda, (2003). Application of Neural Networks to the Prediction of Lymph Node Metastasis in Oral Cancer. Oral Radiol, vol. 19, pp. 137-142.

[26] K. Kourou, T. P. Exarchosa, K. P. Exarchos, M. V. Karamouzis, and D. I. Fotiadis, (2015). Review: Machine learning applications in cancer prognosis and prediction. Computational and Structural Biotechnology Journal, vol. 13, pp. 8-17.

[27] H. Kwon, J. Park, and Y. Lee, (2019). Stacking Ensemble Technique for Classifying Breast Cancer. Jnl of Health Informatics Research, vol. 25, no. 4, pp. 283-288.

[28] L. Lavanya, and J. Chandra, (2019). Oral Cancer Analysis Using Machine Learning Techniques. International Journal of Engineering Research and Technology, vol. 12, no. 5, pp. 596-601.

[29] D. C. Li, H. C. Hsu, T. I. Tsai, T. J. Lu, and S. Hu, (2007a). A New Method to Help Diagnose Cancers for Small Sample Size. Expert Systems with Applications, vol. 33, pp. 420- 424.

[30] H. Li, D. Li, C. Zhang, and S. Nie, (2007b). An Application of Machine Learning in the Criterion Updating of Diagnosis Cancer. International Conference in Neural Networks and Brain 2005, vol. 1, pp. 187-190.

[31] S. Li, K. Wang, Z. Hou, J. Yang, W. Ren, S. Gao, et al. (2018). Use of Radiomics Combined with Machine Learning Method in the Recurrence Patterns After Intensity-Modulated Radiotherapy for Nasopharyngeal Carcinoma: A Preliminary Study. Journal Frontiers in Oncology.

[32] J. F. McCarthy, K. A. Marx, P. E. Hoffman, et al. (2004). Applications of machine learning and high-dimensional visualization in cancer detection, diagnosis, and management. Ann N Y AcadSci, vol. 1020, pp. 239-262.

[33] T. M. Mitchell, (2006). The discipline of machine learning. Carnegie Mellon University, School of Computer Science, Machine Learning Department.

[34] M. R. Posner, D. M. Hershock, C. R. Blajman, E. Mickiewicz, E. Winquist, V. Gorbounova, et al. (2007). Cisplatin and ﬂuorouracil alone or with docetaxel in head and neck cancer. Natl. Engl. Journal of Med., vol. 357, no. 17, pp. 1705–1715.

[35] V. S. H. Rao, and M. N. Kumar, (2011). A New Intelligence Based Approach for Computer-Aided Diagnosis of Dengue Fever. IEEE Transactions on Information Technology in Biomedicine, (In press).

[36] I. P. Ribeiro, F. Caramelo, L. Esteves, J. Menoita, F. Marques, L. Barroso, et al. (2017). Genomic predictive model for recurrence and metastasis development in head and neck squamous cell carcinoma patients. Scientific Report, pp. 1-8.

[37] P. Rosado, P. Lequerica-Fernández, L. Villallaín, I. Peña, F. Sanchez-Lasheras, and J. C. de Vicente, (2013). Survival model in oral squamous cell carcinoma based on clinicopathological parameters, molecular markers and support vector machines. Expert SystAppl, vol. 40, pp. 4770–4776.

[38] T. Silwattananusarn, W. Kanarkard, K. Tuamsuk, (2016). Enhanced classification accuracy for cardiotocogram data with ensemble feature selection and classifier ensemble. J. Comput. Commun. vol. 4, bo. 4, pp. 20.

[39] A. Singh, S. Goyal, Y. J. Rao, and M. Loew, (2019). Tumor Heterogeneity and Genomics to Predict Radiation Therapy Outcome for Head-and-Neck Cancer: A Machine Learning Approach. Radiation Oncology, vol. 105, no. 1, pp. 232-233.

[40] J. Su, Y. Zhang, H. Su, C. Zang, and W. Li, (2017). A recurrence model for laryngeal cancer based on SVM and gene function clustering. Acta Otolaryngol, vol. 137, no. 5, pp. 557‐562.

[41] Z. Tang, G. Wei, L. Zhang, and Z. Xu, (2019). Signature microRNAs and long noncoding RNAs in laryngeal cancer recurrence identified using a competing endogenous RNA netwoek. Molecular Medicine Reports, Spandidos publications, pp. 4806-4818.

[42] G. Tolstonog, and C. Simon, (2017). Trends in surgical research in head and neck cancer. Curr. Treat. Options Oncol., vol. 18, pp. 38.

[43] L. A Torre, F. Bray, R. L. Siegel, J. Ferlay, J. Lortet-Tieulent, and A. Jemal, (2015). Global cancer statistics, 2012. CA Cancer Journal Clin., vol. 65, no. 2, pp. 87–108.

[44] J. Vanerio, and P. Casas, (2017). Ensemble-learning approaches for network security and anomaly detection. Proceedings of the Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, ACM.

[45] J. B. Vermorken, E. Remenar, C. van Herpen, T. Gorlia, R. Mesia, M. Degardin, et al. (2007). Cisplatin, ﬂuorouracil, and docetaxel in unresectable head and neck cancer. Natl. Engl. Journal Med., vol. 357, no. 17, pp. 1695–1704.

[46] K. S. Viro, R. C. Paniello, and F. E. Johnson, (1998). Costs of posttreatment surveillance for patients with upper aerodigestive tract cancer. Arch. Otolaryngol Head Neck Surg., vol. 124, no. 5, pp. 564 – 572.

[47] L. Yalang, G. Jing, L. QI, and F. Wei, (2015). Ensemble Learning. pp. 484-504.

[48] B. Yag, Q. Guo, F. Wang, K. Cai, X. Bao, and J. A. Chu, (2017). 80‐gene set potentially predicts the relapse in laryngeal carcinoma optimized by support vector machine. Cancer Biomarkers, vol. 19, no. 1, pp. 65‐73.

[49] Yarey et al. (2017). Cancers of the Head & Neck: Does cncurrent chemoradiotherapy preceded by chemothrapy improve survival in locally advanced nasopharyngeal cancer patients? Experience from Ghana. BioMed Central, vol. 4, no. 2,1-7.

Journal of AI and Data Mining

Application of Stacked Ensemble Techniques in Head and Neck Squamous Cell Carcinoma Prognostic Feature Subsets

References

References

Volume 12, Issue 1
January 2024
Pages 67-81

Application of Stacked Ensemble Techniques in Head and Neck Squamous Cell Carcinoma Prognostic Feature Subsets

References

References

Volume 12, Issue 1January 2024Pages 67-81

Volume 12, Issue 1
January 2024
Pages 67-81