Research Article
BibTex RIS Cite

Examination of Prostate Cancer Tumor Formation Using Machine Learning Algorithms

Year 2021, Issue: 29, 87 - 92, 01.12.2021
https://doi.org/10.31590/ejosat.1018897

Abstract

Machine learning is a type of artificial intelligence that extracts patterns from raw data using an algorithm or method. The focus of machine learning is to enable computer systems to learn from experience without being explicitly programmed or human intervention. Traffic alerts, social media, transportation, product recommendations, virtual personal assistants, autonomous cars, dynamic pricing, google translation, online video streaming, fraud detection and many other uses are also frequently used in diagnosis and treatment processes in the medical field. The medical results obtained can help experts in the field to improve the life quality of the patient and to follow the status of the disease. Prostate cancer ranks second in men after lung cancer. In the literature, it has been seen that Prostate Specific Antigen, Gleason score, androgen hormone and T stage prostate cancer are important inputs, but they are not sufficient. In this study, clinical data were obtained from the cBioPortal database, which is an open platform to explore multidimensional cancer genomic data. Data preprocessing was realized for to make the obtained data more understandable and processable. The performance of K-Nearest neighbors, Random trees, Gradient boosting, Support vector machine, Logistic regression, Naive Bayes, and Decision trees classification algorithms from machine learning algorithms was evaluated by estimating the tumor/no-tumor status in the follow-ups of patients with prostate cancer. In previous studies, it has been seen that the Random trees algorithm mostly performs better. However, among the seven classifiers that are frequently used in our study with clinical data, better results were obtained with the Gradient boosting algorithm with an accuracy of 85.37%. Results can be improved by selecting the best subset with feature selection in the clinical data we obtained without feature selection.

References

  • Auffenberg, G. B., Ghani, K. R., Ramani, S., Usoro, E., Denton, B., Rogers, C., ... & Collaborative, M. U. S. I. (2019). askMUSIC: leveraging a clinical registry to develop a new machine learning model to inform patients of prostate cancer treatments chosen by similar men. European urology, 75(6), 901-907.
  • Deng, K., Li, H., & Guan, Y. (2020). Treatment stratification of patients with metastatic castration-resistant prostate cancer by machine learning. Iscience, 23(2), 100804.
  • Eltanashi, S., & Atasoy, F. (2020). Proposed speaker recognition model using optimized feed forward neural network and hybrid time-mel speech feature. ICATCES 2020 Proceeding Book, 130-140.
  • Gao, J., Aksoy, B. A., Dogrusoz, U., Dresdner, G., Gross, B., Sumer, S. O., Sun, Y., Jacobsen, A., Sinha, R., Larsson, E., Cerami, E., Sander, C., & Schultz, N. (2013).
  • Ge, P., Gao, F., & Chen, G. (2015, August). Predictive models for prostate cancer based on logistic regression and artificial neural network. In 2015 IEEE International Conference on Mechatronics and Automation (ICMA) (pp. 1472-1477). IEEE.
  • Goldenberg, S. L., Nir, G., & Salcudean, S. E. (2019). A new era: artificial intelligence and machine learning in prostate cancer. Nature Reviews Urology, 16(7), 391-403.
  • Grossman, Robert L., Heath, Allison P., Ferretti, Vincent, Varmus, Harold E., Lowy, Douglas R., Kibbe, Warren A., Staudt, Louis M. (2016). Toward a Shared Vision for Cancer Genomic Data. New England Journal of Medicine 375:12, 1109-1112
  • Hurwitz, J., & Kirsch, D. (2018). Machine learning for dummies. IBM Limited Edition, 75. Integrative Analysis of Complex Cancer Genomics and clinical profiles using the cBioPortal. Science Signaling, 6(269). https://doi.org/10.1126/scisignal.2004088
  • Introduction to Machine Learning The Wikipedia Guide (p. 427). (2015). https://www.datascienceassn.org/sites/default/files/Introduction to Machine Learning.pdf
  • Karunamuni, R. A., Huynh‐Le, M. P., Fan, C. C., Thompson, W., Eeles, R. A., Kote‐Jarai, Z., ... & Practical Consortium. (2021). African‐specific improvement of a polygenic hazard score for age at diagnosis of prostate cancer. International Journal of Cancer, 148(1), 99-105.
  • Kaur, I., Doja, M. N., & Ahmad, T. (2020). Time-range based sequential mining for survival prediction in prostate cancer. Journal of Biomedical Informatics, 110, 103550.
  • Kızılkaya, Y. M., & Oğuzlar, A. (2018). Bazı denetimli öğrenme algori̇tmalarının R programlama dili i̇le kıyaslanması. Dergi Karadeniz, 37(37), 90–98. https://doi.org/10.17498/kdeniz.405746
  • Lasheras, J. E. S., Lasheras, F. S., Donquiles, C. G., Tardón, A., Castaño-Vinyals, G., Palazuelos, C., ... & de Cos Juez, F. J. (2021). Hybrid algorithm for the classification of prostate cancer patients of the MCC-Spain study based on support vector machines and genetic algorithms. Neurocomputing, 452, 386-394.
  • Lee, S. J., Yu, S. H., Kim, Y., Kim, J. K., Hong, J. H., Kim, C. S., ... & Choi, I. Y. (2020). Prediction system for prostate cancer recurrence using machine learning. Applied Sciences, 10(4), 1333.
  • Machine learning with python tutorial in PDF. (n.d.). Retrieved September 28, 2021, from https://www.tutorialspoint.com/machine_learning_with_python/machine_learning_with_python_pdf_version.htm.
  • Murtojärvi, M., Halkola, A. S., Airola, A., Laajala, T. D., Mirtti, T., Aittokallio, T., & Pahikkala, T. (2020). Cost-effective survival prediction for patients with advanced prostate cancer using clinical trial and real-world hospital registry datasets. International journal of medical informatics, 133, 104014.
  • Nitta, S., Tsutsumi, M., Sakka, S., Endo, T., Hashimoto, K., Hasegawa, M., Hayashi, T., Kawai K., & Nishiyama, H. (2019). Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity. Prostate international, 7(3), 114-118.
  • Regnier-Coudert, O., McCall, J., Lothian, R., Lam, T., McClinton, S., & N’Dow, J. (2012). Machine learning for improved pathological staging of prostate cancer: a performance comparison on a range of classifiers. Artificial intelligence in medicine, 55(1), 25-35.
  • SEER (n.d.). Surveillance, epidemiology, and end results program. Retrieved October 1, 2021, from https://seer.cancer.gov/. Shalev, S. & David, B. (2014). Understanding machine learning: From theory to algorithms. Cambridge: Cambridge University Press, pp. 258-267.
  • Smiti, A. (2020). When machine learning meets medical world: Current status and future challenges. Computer Science Review, 37, 100280.
  • Srivenkatesh, M. (2020). Prediction of prostate cancer using machine learning algorithms. Int. J. Recent Technol. Eng., vol. 8, no. 5, pp. 5353–5362.
  • Syed, K., Sleeman, W., Soni, P., Hagan, M., Palta, J., Kapoor, R., & Ghosh, P. (2021). Machine-learning models for multicenter prostate cancer treatment plans. Journal of Computational Biology, 28(2), 166-184.
  • Tasdelen, A., & Sen, B. (2021). A hybrid CNN-LSTM model for pre-miRNA classification. Scientific Reports, 11(1), 1-9. U.S. National Library of Medicine. (n.d.). National Center for Biotechnology Information. Retrieved October 1, 2021, from https://www.ncbi.nlm.nih.gov/.
  • Weinstein, J. N., Collisson, E. A., Mills, G. B., Shaw, K. R., Ozenberger, B. A., Ellrott, K., Shmulevich, I., Sander, C., & Stuart, J. M. (2013). The cancer genome Atlas Pan-Cancer Analysis Project. Nature Genetics, 45(10), 1113–1120. https://doi.org/10.1038/ng.2764
  • Wen, H., Li, S., Li, W., Li, J., & Yin, C. (2018, December). Comparision of four machine learning techniques for the prediction of prostate cancer survivability. In 2018 15th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) (pp. 112-116). IEEE.
  • Wikipedia contributors. (2021, October 17). Gradient boosting. Wikipedia. https://en.wikipedia.org/wiki/Gradient_boosting.
  • Xiao, L. H., Chen, P. R., Gou, Z. P., Li, Y. Z., Li, M., Xiang, L. C., & Feng, P. (2017). Prostate cancer prediction using the random forest algorithm that takes into account transrectal ultrasound findings, age, and serum levels of prostate-specific antigen. Asian journal of andrology, 19(5), 586.

Makine Öğrenmesi Algoritmaları Kullanılarak Prostat Kanseri Tümör Oluşumunun İncelenmesi

Year 2021, Issue: 29, 87 - 92, 01.12.2021
https://doi.org/10.31590/ejosat.1018897

Abstract

Makine öğrenmesi, bir algoritma veya yöntem kullanarak ham verilerden kalıpları çıkaran bir yapay zeka türüdür. Makine öğrenmesinin temel odak noktası, bilgisayar sistemlerinin açıkça programlanmadan veya insan müdahalesi olmadan deneyimlerden öğrenmesine olanak sağlamaktır. Trafik uyarıları, sosyal medya, ulaşım, ürün önerileri, sanal kişisel asistanlar, otonom arabalar, dinamik ücretlendirme, google çeviri, çevrimiçi video akışı, dolandırıcılık tespiti ve daha birçok kullanım alanı olmakla beraber tıp alanında teşhis ve tedavi süreçlerinde de sıklıkla kullanılmaktadır. Elde edilen tıbbi sonuçlar hastanın yaşam kalitesini arttırmak ve hastalığın durumunu takip etmek için alanında uzman kişilere yardımcı olabilmektedir. İnsanlar için çok çeşitli hastalıklar olmakla birlikte kanser yüksek riskli hastalıkların başında gelmektedir. Prostat kanseri, akciğer kanserinden sonra erkeklerde ikinci sırada yer almaktadır. Yapılan literatür araştırmalarında Prostat Spesifik Antijen, Gleason Skor, Androjen Hormonu ve T Aşaması prostat kanser tespitinde önemli girdiler olmakla beraber yeterli olmadıkları görülmüştür. Bu çalışmada çok boyutlu kanser genomik verilerini keşfetmek için açık bir platform olan cBioPortal veritabanından klinik veriler elde edilmiştir. Elde edilen verilerin daha anlaşılır ve işlenebilir hale getirilmesi için veri ön işleme işlemi gerçekleştirilmiştir. Prostat kanseri olan hasta takiplerinde tümörlü/tümörsüz durumu tahmin edilerek makine öğrenmesi algoritmalarından K-En yakın komşular, Rassal ağaçlar, Gradyan artırma, Destek vektör makinesi, Lojistik regresyon, Naive bayes ve Karar ağaçları sınıflandırma algoritmalarının performansı değerlendirilmiştir. Yapılan önceki çalışmalarda çoğunlukla Rassal ağaçlar algoritmasının daha iyi performans gösterdiği görülmüştür. Ancak klinik verilerle yaptığımız çalışmada sıklıkla kullanılan yedi sınıflandırıcı arasında Gradyan artırma algoritması ile %85.37 doğrulukla daha iyi sonuçlar elde edilmiştir. Özellik seçimi yapılmadan elde ettiğimiz klinik verilerde özellik seçimi ile en iyi alt kümenin seçilmesi işlemi yapılarak sonuçlar iyileştirilebilir.

References

  • Auffenberg, G. B., Ghani, K. R., Ramani, S., Usoro, E., Denton, B., Rogers, C., ... & Collaborative, M. U. S. I. (2019). askMUSIC: leveraging a clinical registry to develop a new machine learning model to inform patients of prostate cancer treatments chosen by similar men. European urology, 75(6), 901-907.
  • Deng, K., Li, H., & Guan, Y. (2020). Treatment stratification of patients with metastatic castration-resistant prostate cancer by machine learning. Iscience, 23(2), 100804.
  • Eltanashi, S., & Atasoy, F. (2020). Proposed speaker recognition model using optimized feed forward neural network and hybrid time-mel speech feature. ICATCES 2020 Proceeding Book, 130-140.
  • Gao, J., Aksoy, B. A., Dogrusoz, U., Dresdner, G., Gross, B., Sumer, S. O., Sun, Y., Jacobsen, A., Sinha, R., Larsson, E., Cerami, E., Sander, C., & Schultz, N. (2013).
  • Ge, P., Gao, F., & Chen, G. (2015, August). Predictive models for prostate cancer based on logistic regression and artificial neural network. In 2015 IEEE International Conference on Mechatronics and Automation (ICMA) (pp. 1472-1477). IEEE.
  • Goldenberg, S. L., Nir, G., & Salcudean, S. E. (2019). A new era: artificial intelligence and machine learning in prostate cancer. Nature Reviews Urology, 16(7), 391-403.
  • Grossman, Robert L., Heath, Allison P., Ferretti, Vincent, Varmus, Harold E., Lowy, Douglas R., Kibbe, Warren A., Staudt, Louis M. (2016). Toward a Shared Vision for Cancer Genomic Data. New England Journal of Medicine 375:12, 1109-1112
  • Hurwitz, J., & Kirsch, D. (2018). Machine learning for dummies. IBM Limited Edition, 75. Integrative Analysis of Complex Cancer Genomics and clinical profiles using the cBioPortal. Science Signaling, 6(269). https://doi.org/10.1126/scisignal.2004088
  • Introduction to Machine Learning The Wikipedia Guide (p. 427). (2015). https://www.datascienceassn.org/sites/default/files/Introduction to Machine Learning.pdf
  • Karunamuni, R. A., Huynh‐Le, M. P., Fan, C. C., Thompson, W., Eeles, R. A., Kote‐Jarai, Z., ... & Practical Consortium. (2021). African‐specific improvement of a polygenic hazard score for age at diagnosis of prostate cancer. International Journal of Cancer, 148(1), 99-105.
  • Kaur, I., Doja, M. N., & Ahmad, T. (2020). Time-range based sequential mining for survival prediction in prostate cancer. Journal of Biomedical Informatics, 110, 103550.
  • Kızılkaya, Y. M., & Oğuzlar, A. (2018). Bazı denetimli öğrenme algori̇tmalarının R programlama dili i̇le kıyaslanması. Dergi Karadeniz, 37(37), 90–98. https://doi.org/10.17498/kdeniz.405746
  • Lasheras, J. E. S., Lasheras, F. S., Donquiles, C. G., Tardón, A., Castaño-Vinyals, G., Palazuelos, C., ... & de Cos Juez, F. J. (2021). Hybrid algorithm for the classification of prostate cancer patients of the MCC-Spain study based on support vector machines and genetic algorithms. Neurocomputing, 452, 386-394.
  • Lee, S. J., Yu, S. H., Kim, Y., Kim, J. K., Hong, J. H., Kim, C. S., ... & Choi, I. Y. (2020). Prediction system for prostate cancer recurrence using machine learning. Applied Sciences, 10(4), 1333.
  • Machine learning with python tutorial in PDF. (n.d.). Retrieved September 28, 2021, from https://www.tutorialspoint.com/machine_learning_with_python/machine_learning_with_python_pdf_version.htm.
  • Murtojärvi, M., Halkola, A. S., Airola, A., Laajala, T. D., Mirtti, T., Aittokallio, T., & Pahikkala, T. (2020). Cost-effective survival prediction for patients with advanced prostate cancer using clinical trial and real-world hospital registry datasets. International journal of medical informatics, 133, 104014.
  • Nitta, S., Tsutsumi, M., Sakka, S., Endo, T., Hashimoto, K., Hasegawa, M., Hayashi, T., Kawai K., & Nishiyama, H. (2019). Machine learning methods can more efficiently predict prostate cancer compared with prostate-specific antigen density and prostate-specific antigen velocity. Prostate international, 7(3), 114-118.
  • Regnier-Coudert, O., McCall, J., Lothian, R., Lam, T., McClinton, S., & N’Dow, J. (2012). Machine learning for improved pathological staging of prostate cancer: a performance comparison on a range of classifiers. Artificial intelligence in medicine, 55(1), 25-35.
  • SEER (n.d.). Surveillance, epidemiology, and end results program. Retrieved October 1, 2021, from https://seer.cancer.gov/. Shalev, S. & David, B. (2014). Understanding machine learning: From theory to algorithms. Cambridge: Cambridge University Press, pp. 258-267.
  • Smiti, A. (2020). When machine learning meets medical world: Current status and future challenges. Computer Science Review, 37, 100280.
  • Srivenkatesh, M. (2020). Prediction of prostate cancer using machine learning algorithms. Int. J. Recent Technol. Eng., vol. 8, no. 5, pp. 5353–5362.
  • Syed, K., Sleeman, W., Soni, P., Hagan, M., Palta, J., Kapoor, R., & Ghosh, P. (2021). Machine-learning models for multicenter prostate cancer treatment plans. Journal of Computational Biology, 28(2), 166-184.
  • Tasdelen, A., & Sen, B. (2021). A hybrid CNN-LSTM model for pre-miRNA classification. Scientific Reports, 11(1), 1-9. U.S. National Library of Medicine. (n.d.). National Center for Biotechnology Information. Retrieved October 1, 2021, from https://www.ncbi.nlm.nih.gov/.
  • Weinstein, J. N., Collisson, E. A., Mills, G. B., Shaw, K. R., Ozenberger, B. A., Ellrott, K., Shmulevich, I., Sander, C., & Stuart, J. M. (2013). The cancer genome Atlas Pan-Cancer Analysis Project. Nature Genetics, 45(10), 1113–1120. https://doi.org/10.1038/ng.2764
  • Wen, H., Li, S., Li, W., Li, J., & Yin, C. (2018, December). Comparision of four machine learning techniques for the prediction of prostate cancer survivability. In 2018 15th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) (pp. 112-116). IEEE.
  • Wikipedia contributors. (2021, October 17). Gradient boosting. Wikipedia. https://en.wikipedia.org/wiki/Gradient_boosting.
  • Xiao, L. H., Chen, P. R., Gou, Z. P., Li, Y. Z., Li, M., Xiang, L. C., & Feng, P. (2017). Prostate cancer prediction using the random forest algorithm that takes into account transrectal ultrasound findings, age, and serum levels of prostate-specific antigen. Asian journal of andrology, 19(5), 586.
There are 27 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Nesrin Aydın Atasoy 0000-0002-7188-0020

Ahmet Demiröz 0000-0001-5739-896X

Early Pub Date December 15, 2021
Publication Date December 1, 2021
Published in Issue Year 2021 Issue: 29

Cite

APA Aydın Atasoy, N., & Demiröz, A. (2021). Makine Öğrenmesi Algoritmaları Kullanılarak Prostat Kanseri Tümör Oluşumunun İncelenmesi. Avrupa Bilim Ve Teknoloji Dergisi(29), 87-92. https://doi.org/10.31590/ejosat.1018897