Topluluk Öğrenme yöntemleri ile Renal Hücreli Karsinomun Tahmin Edilmesi

Year 2021, Volume: 7 Issue: 1, 104 - 114, 30.04.2021

Adem Doğaner Cemil Çolak Faruk Küçükdurmaz Caner Ölmez

https://doi.org/10.19127/mbsjohs.889492

Cited By: 2

Abstract

Giriş: Son yıllarda topluluk öğrenme yöntemleri kanser hastalıklarının erken teşhisi için yaygın bir kullanıma kavuşmuştur. Bu çalışmada, renal hücreli karsinomların erken teşhisi ve sınıflandırılması için yüksek performansa sahip topluluk öğrenme modelinin oluşturulması amaçlanmıştır.
Materyal ve Metot: Çalışmada, 140 renal hücreli karsinom hastası ve 140 renal hücreli karsinomu olmayan hastanın hemogram ve laboratuar verileri çalışmaya dahil edilmiştir. Veri setinde 27 predictor ve 1 bağımlı değişken yer almaktadır. Veriler restospektif olarak elde edilmiştir. Çalışmada makine öğrenme yöntemleri ve topluluk öğrenme yöntemlerinin sınıflandırma performansları karşılaştırılmıştır. Çalışmada IB1, IBk, Kstar, LWL, REPTree, Random Forest ve SMO sınıflayıcılarının yanısıra, boosting, bagging, voting ve stacking topluluk öğrenme yöntemlerinin sınıflandırma performansları karşılaştırılmıştır.
Bulgular: Makine öğrenme yöntemleri içerisinde en yüksek performansı REPTree sınıflayıcısı sağlamıştır (ACC=0.867). Topluluk öğrenme yöntemleri içerisinde en yüksek performansı Stacking topluluk öğrenme yöntemi Model 6’da sağlamıştır (ACC=0.906). Stacking topluluk öğrenme yöntemleri, boosting, voting, bagging topluluk yöntemlerine ve makine öğrenme yöntemlerine göre daha yüksek performans göstermiştir.
Sonuçlar: Stacking topluluk öğrenme yöntemleri renal hücreli karsinomların erken teşhisinde başarılı sonuçlar sağlamaktadır. Stacking topluluk öğrenme yöntemleri renal hücreli karsinomun teşhisi için mevcut yöntemlere bir alternatif olarak kullanılabilmektedir. Stacking topluluk öğrenme yönteminin sınıflandırma performansını dahada artırmak için veri setine ve değişken türlerine uygun meta sınıflayıcı seçilmesi önerilmektedir.

Keywords

Topluluk Öğrenme Yöntemi, Meta Sınıflayıcı, Renal Hücreli Karsinom, Erken Teşhis

Supporting Institution

Destekleyici Kurum Bulunmamaktadır.

Project Number

-

Prediction of Renal Cell Carcinoma Based on Ensemble Learning Methods

Abstract

Objective: In recent years, ensemble learning methods have gained widespread use for early diagnosis of cancer diseases. In this study, it is aimed to establish a high-performance ensemble learning model for early diagnosis and classification of renal cell carcinomas.
Methods: In the study, hemogram and laboratory data of 140 patients with renal cell carcinoma and 140 patients without renal cell carcinoma were included in the study. The data set includes 27 predictors and 1 dependent variable. The data were obtained retrospectively. In the study, classification performances of machine learning methods and ensemble learning methods were compared. In the study, classification performances of boosting, bagging, voting and stacking ensemble learning methods as well as IB1, IBk, Kstar, LWL, REPTree, Random Forest and SMO classifiers were compared.
Results: REPTree classifier provided the highest performance among machine learning methods (Accuracy = 0.867). Among the ensemble learning methods, the Stacking ensemble learning method provided the highest performance in Model 6 (Accuracy = 0.906). Stacking ensemble learning methods performed higher than boosting, voting, bagging ensemble methods and machine learning methods.
Conclusion: Stacking ensemble learning methods provide successful results in the early diagnosis of renal cell carcinomas. Stacking ensemble learning methods can be used as an alternative to existing methods for diagnosing renal cell carcinoma. In order to further increase the classification performance of the stacking ensemble learning method, it is recommended to choose a meta classifier suitable for the data set and variable types.

Keywords

Ensemble Learning Methods, Meta Classifier, Renal Cell Carcinoma, Early Diagnosis

Project Number

-

References

• 1. Gucer H. The relationship between cox-2 expression, microvessel density and various clinicopatologic parameters in clear cell type renal cell carcinoma. Thesis of Specialization in Medicine. Istanbul: Taksim Educational and Research. 2006.
• 2. Demirkıran ED. The relationship between tumor volume kidney volume ratio and prognostic factors in renal cell carcinoma. Thesis of Specialization in Medicine. Zonguldak: Bulent Ecevit University, Faculty of Medicine. 2019.
• 3. Capitanio U, Bensalah K, Bex A, Boorjian SA, Bray F, Coleman J, et al. Epidemiology of renal cell carcinoma. Eur Urol 2019 Jan 1;75(1):74-84.
• 4. Kim HL, Belldegrun AS, Freitas DG, Bui MH, Han KR, Dorey FJ, et al. Paraneoplastic signs and symptoms of renal cell carcinoma: implications for prognosis. J Urol 2003 Nov;170(5):1742-6.
• 5. Ficarra V, Prayer-Galetti T, Novella G, Bratti E, Maffei N, Dal Bianco M, et al. Incidental detection beyond pathological factors as prognostic predictor of renal cell carcinoma. Eur Urol 2003 Jun 1;43(6):663-9.
• 6. Tastekin E. The comparison of angiogenetic and prognostic factors in renal cell carcinomas. Thesis of Specialization in Medicine. Edirne: Trakya University Faculty of Medicine. 2019.
• 7. Eble JN, Togashi K, Pisani P. Renal Cell Carcinoma. In : Eble JN, Sauter G, Epstein JI, Sesterhenn IA. editors. World Health Organization Classification of Tumours. Pathology and genetics of Tumours of the urinary system and male genital organs IARC Press, 2004: 9-87.
• 8. Akman M, Genc Y, Ankarali H. Random Forests Methods and an Application in Health Science. Turkiye Klinikleri Journal Biostat 2011;3: 36-48.
• 9. Pesch B, Haerting J, Ranft U, Klimpel A, Oelschlägel B, Schill W. Occupational risk factors for renal cell carcinoma: agent-specific results from a case-control study in Germany. Int. J. Epidemiol 2000 Dec 1;29(6):1014-24.
• 10. Dietterich T. Overfitting and undercomputing in machine learning. ACM Comput Surv 1995 Sep 1;27(3):326-7.
• 11. Jabbar H, Khan DR. Methods to avoid over-fitting and under-fitting in supervised machine learning (comparative study). Comp Sci, Comm Instrum Devices 2015:163-72.
• 12. Lee H, Kim J, Kim S. Gaussian-Based SMOTE Algorithm for Solving Skewed Class Distributions. Int. J. Fuzzy Log. Intell 2017 Dec 25;17(4):229-34.
• 13. Zhang C, Ma Y. editors. Ensemble machine learning: methods and applications. Springer Science, Business Media, 2012.
• 14. Liu D, Shi T, DiDonato JA, Carpten JD, Zhu J, Duan ZH. Application of genetic algorithm/k-nearest neighbor method to the classification of renal cell carcinoma. In: Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, IEEE, 2004: 558-559. 15. Won Y, Song HJ, Kang TW, Kim JJ, Han BD, Lee SW. Pattern analysis of serum proteome distinguishes renal cell carcinoma from other urologic diseases and healthy persons. Proteomics 2003 Dec;3(12):2310-6.
• 16. Lee HS, Hong H, Jung DC, Park S, Kim J. Differentiation of fat‐poor angiomyolipoma from clear cell renal cell carcinoma in contrast‐enhanced MDCT images using quantitative feature classification. Med Phys 2017 Jul;44(7):3604-14. 17. Fuchs TJ, Wild PJ, Moch H, Buhmann JM. Computational pathology analysis of tissue microarrays predicts survival of renal clear cell carcinoma patients. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Berlin, Heidelberg, 2008: 1-8.
• 18. Lin F, Cui EM, Lei Y, Luo L ping. CT-based machine learning model to predict the Fuhrman nuclear grade of clear cell renal cell carcinoma. Abdom Radiol. 2019;44(7):2528-34.
• 19. Tabibu S, Vinod PK, Jawahar CV. Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images using deep learning. Sci Rep 2019 Jul 19;9(1):1-9.
• 20. Tan AC, Gilbert D. Ensemble machine learning on gene expression data for cancer classification. Appl Bioinformatics 2003, 2: S75–S83.
• 21. Luo ST, Cheng BW. Diagnosing breast masses in digital mammography using feature selection and ensemble methods. J Med Syst 2012 Apr;36(2):569-77.
• 22. Wang Y, Wang D, Geng N, Wang Y, Yin Y, Jin Y. Stacking-based ensemble learning of decision trees for interpretable prostate cancer detection. Appl Soft Comput 2019 Apr 1;77:188-204.
• 23. Onan A. On the performance of ensemble learning for automated diagnosis of breast cancer. In: Artificial Intelligence Perspectives and Applications, In Artificial Intelligence Perspectives and Applications 2015 (pp. 119-129). Springer, Cham.
• 24. Shayesteh SP, Alikhassi A, Fard Esfahani A, Miraie M, Geramifar P, Bitarafan-rajabi A, et al. Neo-adjuvant chemoradiotherapy response prediction using MRI based ensemble learning method in rectal cancer patients. Phys Medica. 2019 Jun 1;62:111-9.
• 25. Breunig MM, Kriegel HP, Ng RT, Sander J. LOF: identifying density-based local outliers. ACM Sigmod Rec 2000 May 16:93-104.
• 26. Lee J, Kang B, Kang SH. Integrating independent component analysis and local outlier factor for plant-wide process monitoring. J Process Control 2011 Aug 1;21(7):1011-21.
• 27. Weka Sourceforge. Class GridSearch. Accessed: 24 Nov 2019. Available from: https://weka.sourceforge.io/doc.stable/weka/classifiers/meta/GridSearch.html.
• 28. Multisearch weka package. Accessed: 24 Nov 2019. Available from: https://github.com/fracpete/multisearch-weka-package.
• 29. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH. The WEKA data mining software: an update. ACM SIGKDD explorations newsletter. 2009 Nov 16;11(1):10-8.
• 30. Team RC. R: A language and environment for statistical computing. Accessed: September 2019. Available from: www.R-project.org.
• 31. Witten IH, Frank E, Hall MA, Pal CJ. Data Mining: Practical machine learning tools and techniques, Morgan Kaufmann, 2016.
• 32. Breiman L. Random forests. Mach. Learn 2001 Oct;45(1):5-32.
• 33. Polikar R. Ensemble learning. In: Zhang C, Ma Y editors. Ensemble machine learning. Springer Science, Business Media, 2012: 1-34.
• 34. Zhou ZH. Ensemble methods: foundations and algorithms. Chapman and Hall/CRC, 2012.
• 35. Rokach L. Pattern classification using ensemble methods. World Scientific, 2010. 36. Freund Y, Schapire RE. Schapire R: Experiments with a new boosting algorithm. In: Thirteenth International Conference on ML, 1996 Jul 3 (Vol. 96, pp. 148-156).
• 37. Wolpert DH. Stacked generalization. Neural Netw 1992 Jan 1;5(2):241-59.
• 38. Ng EK, Fok SC, Peh YC, Ng FC, Sim LS. Computerized detection of breast cancer with artificial intelligence and thermograms. J. Med. Eng. Technol. 2002 Jan 1;26(4):152-7.
• 39. Zubi ZS, Saad RA. Using some data mining techniques for early diagnosis of lung cancer. In Proceedings of the 10th WSEAS international conference on Artificial intelligence Knowledge Engineering and Data Bases 2011 Feb 20 (pp. 32-37).
• 40. Giger ML. Computerized analysis of images in the detection and diagnosis of breast cancer. In Seminars in Ultrasound, CT and MRI 2004 Oct 1 (Vol. 25, No. 5, pp. 411-418). WB Saunders.
• 41. Abdel-Zaher AM, Eldeib AM. Breast cancer classification using deep belief networks. Expert Syst Appl 2016 Mar 15;46:139-44.
• 42. Jemal A, Bray F, Center MM, Ferlay J, Ward E, Forman D. Global cancer statistics. CA: Cancer J. Clin. 2011 Mar;61(2):69-90.
• 43. Singh NP, Bapi RS, Vinod PK. Machine learning models to predict the progression from early to late stages of papillary renal cell carcinoma. Comput. Biol. Med. 2018 Sep 1;100:92-9. 44. Kocak B, Yardimci AH, Bektas CT, Turkcanoglu MH, Erdim C, Yucetas U, et al. Textural differences between renal cell carcinoma subtypes: Machine learning-based quantitative computed tomography texture analysis with independent external validation. Eur. J. Radiol. 2018 Oct 1;107:149-57.
• 45. Jagga Z, Gupta D. Classification models for clear cell renal carcinoma stage progression, based on tumor RNAseq expression trained supervised machine learning algorithms. In BMC proceedings 2014 Oct (Vol. 8, No. 6, pp. 1-7). BioMed Central.
• 46. Bektas CT, Kocak B, Yardimci AH, Turkcanoglu MH, Yucetas U, Koca SB, Erdim C, Kilickesmez O. Clear cell renal cell carcinoma: machine learning-based quantitative computed tomography texture analysis for prediction of Fuhrman nuclear grade. Eur Radiol. 2019 Mar 2;29(3):1153-63.
• 47. Mohebian MR, Marateb HR, Mansourian M, Mañanas MA, Mokarian F. A hybrid computer-aided-diagnosis system for prediction of breast cancer recurrence (HPBCR) using optimized ensemble learning. Comput Struct Biotechnol J. 2017 Jan 1;15:75-85.
• 48. Hsieh SL, Hsieh SH, Cheng PH, Chen CH, Hsu KP, Lee IS, et al. Design ensemble machine learning model for breast cancer diagnosis. J Med Syst 2012 Oct;36(5):2841-7.
• 49. Cai Z, Xu D, Zhang Q, Zhang J, Ngai SM, Shao J. Classification of lung cancer using ensemble-based feature selection and machine learning methods. Mol Biosyst 2015;11(3):791-800.
• 50. Farahani FV, Ahmadi A, Zarandi MHF. Lung nodule diagnosis from CT images based on ensemble learning. In: 2015 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, 2015 Aug 12 (pp. 1-7). IEEE