Gelişmiş Orofarengeal Kanser Prognozu: Yenilikçi Bir Toplululuk Makine Öğrenimi Yaklaşımı

Öz

Orofaringeal kanserli hastalarda hayatta kalma oranlarını tahmin etmek için makine öğrenimi algoritmalarının kullanılması bu çalışmanın ana odak noktasıdır. Kanser prognozunun doğasında olan karmaşıklık ve değişkenlik göz önüne alındığında, geleneksel öngörücü modeller genellikle doğruluk ve güvenilirlik açısından yetersiz kalmaktadır. Gaussian Naive Bayes, Rastgele Orman, Gradyan Arttırma, Doğrusal Destek Vektör Makinesi, Lojistik Regresyon ve K-En Yakın Komşular dahil olmak üzere, bu sorunların üstesinden gelmek için her biri veri analizinde kendi avantajları olan çeşitli makine öğrenimi yöntemlerini kullandık. Bu ayrı algoritmaları birleştiren bir topluluk modelinin geliştirilmesi stratejimizin anahtarıydı. Bu modelin genel tahmin gücü, tüm tekniklerin birleşik avantajlarından yararlanılarak artırılmıştır. Karşılaştırmalı analizimizin sonuçları, bireysel algoritmaların performansı farklılık gösterse de önerilen topluluk modelinin hepsinden daha iyi performans gösterdiğini, daha yüksek doğruluk, f1 puanı, kesinlik ve hatırlama elde ettiğini gösterdi. Çalışmanın bulguları, özellikle tıbbi teşhis için kanser prognozunun karmaşık alanında toplu makine öğrenimi modellerinin potansiyelini vurgulamaktadır. Topluluk modeli, birden fazla algoritmayı verimli bir şekilde birleştirerek orofaringeal kanserli hastalarda hayatta kalma sonuçlarını tahmin etmek için daha kapsamlı bir araç sunar. Bu yöntem sadece öngörü doğruluğunu arttırmakla kalmıyor, aynı zamanda hastalığın dinamiklerinin daha derinlemesine anlaşılmasını sağlayarak daha bireysel ve başarılı tedavi planlarının kapısını aralıyor.

Anahtar Kelimeler

• Veri Bilimi
• Orofaringeal Kanser
• Tıbbi Teşhis
• Makine Öğrenmesi

Advancing Oropharyngeal Cancer Prognosis: A Novel Ensemble Machine Learning Approach

Öz

The use of machine learning algorithms to forecast survival rates in patients with oropharyngeal cancer is the main focus of this study. Given the complexity and variability inherent in cancer prognosis, traditional predictive models often fall short in accuracy and reliability. We used a variety of machine learning methods, each with their own advantages in data analysis, to tackle these problems, including Gaussian Naive Bayes, Random Forest, Gradient Boosting, Linear Support Vector Machine, Logistic Regression, and K-Nearest Neighbors. The development of an ensemble model that combined these separate algorithms was the key to our strategy. The overall predictive power of this model is increased by utilizing the combined advantages of all the techniques. The results of our comparative analysis indicated that although the performance of the individual algorithms varied, the suggested ensemble model performed better than all of them, obtaining higher accuracy, f1-score, precision, and recall. The study's findings highlight the potential of ensemble machine learning models in the complex field of cancer prognosis in particular, for medical diagnostics. The ensemble model offers a more comprehensive tool for predicting survival outcomes in patients with oropharyngeal cancer by efficiently combining multiple algorithms. This method not only increases the predictive accuracy but also provides a deeper comprehension of the dynamics of the disease, opening the door to more individualized and successful treatment plans.

Anahtar Kelimeler

• Data Science
• Oropharyngeal Cancer
• Medical Diagnostics
• Machine Learning

Kaynakça

1. [1] L. Wei et al., “Artificial intelligence (AI) and machine learning (ML) in precision oncology: A review on enhancing discoverability through multiomics integration,” Br. J. Radiol., vol. 96, no. 1150, p. 20230211, 2023.
2. [2] J. Thagaard et al., “Pitfalls in machine learning‐based assessment of tumor‐infiltrating lymphocytes in breast cancer: A report of the International Immuno‐Oncology Biomarker Working Group on Breast Cancer,” J. Pathol., vol. 260, no. 5, pp. 498–513, 2023.
3. [3] S.-C. Lu, C. L. Swisher, C. Chung, D. Jaffray, and C. Sidey-Gibbons, “On the importance of interpretable machine learning predictions to inform clinical decision making in oncology,” Front. Oncol., vol. 13, p. 1129380, 2023.
4. [4] W. T. Hrinivich, T. Wang, and C. Wang, “Interpretable and explainable machine learning models in oncology,” Front. Oncol., vol. 13, p. 1184428, 2023.
5. [5] M. M. Allevato, J. D. Smith, M. J. Brenner, and S. B. Chinn, “Tumor-Derived Exosomes and the Role of Liquid Biopsy in Human Papillomavirus Oropharyngeal Squamous Cell Carcinoma,” Cancer J., vol. 29, no. 4, pp. 230–237, 2023.
6. [6] J. R. Crossley, L. L. Nelson, J. Chou, and J. H. Maxwell, “Distant metastases in human papillomavirus‐related oropharyngeal squamous cell carcinoma: Systematic review and meta‐analysis,” Head Neck, vol. 45, no. 1, pp. 275–282, 2023.
7. [7] P. A. Boot et al., “Magnetic resonance imaging based radiomics prediction of Human Papillomavirus infection status and overall survival in oropharyngeal squamous cell carcinoma,” Oral Oncol., vol. 137, p. 106307, 2023.
8. [8] J. F. Mills, N. P. Monaghan, S. A. Nguyen, J. Pang, A. A. Asarkar, and C.-A. O. Nathan, “Special Issue on the Epidemiology of Human Papilloma Virus-Associated Oropharyngeal Squamous Cell Carcinoma,” Cancers, vol. 15, no. 18, p. 4608, 2023.

9. [9] D. Ahn, J.-H. Kwak, G.-J. Lee, and J.-H. Sohn, “Prevalence and Characteristics of Human Papillomavirus Infection in Oropharyngeal Squamous Cell Papilloma,” Cancers, vol. 15, no. 3, p. 810, 2023.
10. [10] I. Mihaylov, M. Nisheva, and D. Vassilev, “Application of machine learning models for survival prognosis in breast cancer studies,” Information, vol. 10, no. 3, p. 93, 2019.
11. [11] K. Kourou, T. P. Exarchos, K. P. Exarchos, M. V. Karamouzis, and D. I. Fotiadis, “Machine learning applications in cancer prognosis and prediction,” Comput. Struct. Biotechnol. J., vol. 13, pp. 8–17, 2015.
12. [12] J. A. Cruz and D. S. Wishart, “Applications of machine learning in cancer prediction and prognosis,” Cancer Inform., vol. 2, p. 117693510600200030, 2006.
13. [13] W.-T. Tseng, W.-F. Chiang, S.-Y. Liu, J. Roan, and C.-N. Lin, “The application of data mining techniques to oral cancer prognosis,” J. Med. Syst., vol. 39, pp. 1–7, 2015.
14. [14] C. S. Chu, N. P. Lee, J. Adeoye, P. Thomson, and S. Choi, “Machine learning and treatment outcome prediction for oral cancer,” J. Oral Pathol. Med., vol. 49, no. 10, pp. 977–985, 2020.
15. [15] H. Patel, D. M. Vock, G. E. Marai, C. D. Fuller, A. S. Mohamed, and G. Canahuate, “Oropharyngeal cancer patient stratification using random forest based-learning over high-dimensional radiomic features,” Sci. Rep., vol. 11, no. 1, p. 14057, 2021.
16. [16] Y. Cheng et al., “Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study,” Diagnostics, vol. 11, no. 9, p. 1614, 2021.
17. [17] C. Molnar, Interpretable machine learning. Lulu. com, 2020.
18. [18] P. Lambin et al., “Radiomics: the bridge between medical imaging and personalized medicine,” Nat. Rev. Clin. Oncol., vol. 14, no. 12, pp. 749–762, 2017.
19. [19] P. Lambin et al., “Radiomics: extracting more information from medical images using advanced feature analysis,” Eur. J. Cancer, vol. 48, no. 4, pp. 441–446, 2012.
20. [20] V. Kumar et al., “Radiomics: the process and the challenges,” Magn. Reson. Imaging, vol. 30, no. 9, pp. 1234–1248, 2012.
21. [21] R. J. Gillies, P. E. Kinahan, and H. Hricak, “Radiomics: images are more than pictures, they are data,” Radiology, vol. 278, no. 2, pp. 563–577, 2016.
22. [22] E. M. Graboyes et al., “Association of treatment delays with survival for patients with head and neck cancer: a systematic review,” JAMA Otolaryngol. Neck Surg., vol. 145, no. 2, pp. 166–177, 2019.
23. [23] J. da S. Moro, M. C. Maroneze, T. M. Ardenghi, L. M. Barin, and C. C. Danesi, “Oral and oropharyngeal cancer: epidemiology and survival analysis,” Einstein Sao Paulo, vol. 16, 2018.
24. [24] M. Vedaraj, C. Anita, A. Muralidhar, V. Lavanya, K. Balasaranya, and P. Jagadeesan, “Early Prediction of Lung Cancer Using Gaussian Naive Bayes Classification Algorithm,” Int. J. Intell. Syst. Appl. Eng., vol. 11, no. 6s, pp. 838–848, 2023.
25. [25] J. Hu and S. Szymczak, “A review on longitudinal data analysis with random forest,” Brief. Bioinform., vol. 24, no. 2, p. bbad002, 2023.
26. [26] S. Priya, N. Karthikeyan, and D. Palanikkumar, “Pre Screening of Cervical Cancer Through Gradient Boosting Ensemble Learning Method.,” Intell. Autom. Soft Comput., vol. 35, no. 3, 2023.
27. [27] D. Keerthana, V. Venugopal, M. K. Nath, and M. Mishra, “Hybrid convolutional neural networks with SVM classifier for classification of skin cancer,” Biomed. Eng. Adv., vol. 5, p. 100069, 2023.
28. [28] T. Shibahara et al., “Deep learning generates custom-made logistic regression models for explaining how breast cancer subtypes are classified,” Plos One, vol. 18, no. 5, p. e0286072, 2023.
29. [29] M. Anand, A. Velu, and P. Whig, “Prediction of Loan Behaviour with Machine Learning Models for Secure Banking,” J. Comput. Sci. Eng. JCSE, vol. 3, no. 1, pp. 1–13, Feb. 2022, doi: 10.36596/jcse.v3i1.237.