Meme Kanseri Tanısı İçin Özniteliklerin Öneminin Değerlendirilmesi Üzerine Bir Çalışma

Abstract

En yaygın kanser türlerinden biri olan meme kanseri kadınları etkileyen ölümcül bir hastalıktır. Önerilen çalışmada, Wisconsin meme kanseri veriseti üzerinde öznitelik seçimine dayalı Özyinelemeli Özellik Seçimi metodu kullanılarak özniteliklerin önemliliği araştırılmış ve sonrasında Rastele Orman ve Lojistik Regresyon sınıflandırıcı algoritmaları kullanılarak makine öğrenmeleri gerçekleştirilmiştir. Eğitim ve test aşamalarını içeren öğrenme süreci 5 katlı çapraz doğrulama tekniği kullanılarak gerçekleştirilmiştir. Deneysel çalışmalar, Rastgele Orman algoritması kullanılarak en iyi sınıflandırma başarısı ( %98 doğruluk) elde edildiğini göstermiştir.

Keywords

• Meme kanseri risk tahmini,özniteliklerin önemliliği,Özyinelemeli Özellik Eleme,Rastgele Orman,Lojistik Regresyon

A Study on Assessing the Importance of Attributes for Breast Cancer Diagnosis

Abstract

Breast cancer, one of the most common types of cancer, is a deadly disease affecting women. The importance of attributes was investigated by using the Recursive Feature Selection based on feature selection on Wisconsin breast cancer dataset, and then the machine learnings were performed by utilizing Random Forest and Logistic Regression classifier algorithms in the proposed study. The learning process involving training and testing phases was performed by utilizing the 5-fold cross-validation technique. Experimental studies showed that the best classification performance (98% accuracy) was achieved by applying the Random Forest algorithm.

Keywords

• Logistic Regression,Breast cancer risk prediction,importance of attributes,Recursive Feature Elimination,Random Forest

References

1. Breast cancer basics, http://www.webmd.com/breast-cancer/guide/understanding-breast-cancer-basics, Accessed 20 June 2017.
2. El-Akkad S.M., Amer M.H., Lin G.S., Sabbah R.S., Godwin J.T., Pattern of cancer in Saudi Arabs referred to King Faisal Specialist Hospital, Cancer 58, 1172–1178, 1986.
3. Siegel R.L., Miller K.D., Jemal A., Cancer statistics, CA Cancer J Clin 67, 7-30, 2017. Papageorgiou E.I., Subramanian J., Karmegam A., Papandrianos N., A risk management model for familial breastcancer: A new application using Fuzzy CognitiveMap method, Comput Methods Programs Biomed 122, 123–135, 2015.
4. Lope V., Martín M., Castelló A., Casla S., Ruiz A., Baena-Cañada J.M., Casas A.M., Calvo L., Bermejo B., Muñoz M., Ramos M., de Juan-Ferré A., Jara C., Antón A., Jimeno M.Á., Lluch A., Antolín S., García-Sáenz J.Á., Estévez P., Arriola-Arellano E., Gavilá J., Pérez-Gómez B., Carrasco E., Pollán M., GEICAM, the Spanish Breast Cancer Group, Physical activity and breast cancer risk by pathological subtype, Gynecologic Oncology 144, 577–585, 2017.
5. Guyon, I., Weston, J., Barnhill, S. and Vapnik, V. Gene selection for cancer classification using support vector machines, Mach Learn 46, 389-422, 2002.
6. Hosmer, D. W. and Lemeshow, S. "Applied logistic regression, 2nd ed.", Wiley Series in Probability and Statistics, Canada, 2000.
7. Breiman, L. Random forests, Mach Learn 45, 5-32, 2001.
8. Globocan 2012: Estimated Cancer Incidince, Mortaliyty and Prevalence Worldwide 2012, http://globocan.iarc.fr/Pages/fact_sheets_cancer.aspx. Accessed 20 June 2017.

9. Powell M., Jamshidian F., Cheyne K., Nititham J., Prebil L.A., Ereman R., Assessing Breast Cancer Risk Models in Marin County, a Population With High Rates of Delayed Childbirth, Clinical Breast Cancer 14, 212-220, 2014. Costantino J.P., Gail M.H., Pee D., Anderson S., Redmond C.K., Benichou J., Wieand H.S., Validation studies for models projecting the risk of invasive and total breast cancer incidence, J Natl Cancer Inst 91, 1541-1548, 1999.
10. Parmigiani G., Berry D., Aguilar O., Determining carrier probabilities for breast cancer-susceptibility genes BRCA1 and BRCA2. Am J Hum Genet 62, 145-58, 1998.
11. Tyrer J., Duffy S.W., Cuzick J., A breast cancer prediction model incorporating familial and personal risk factors. Stat Med 23, 1111-1130, 2004.
12. Al Diab A., Qureshi S., Al Saleh K.A., AlQahtani F.H., Aleem A., AlSaif A., Qureshi V.F., Qureshi M.R., Studies on the methods of diagnosis and biomarkers used in early detection of breast cancer in the Kingdom of Saudi Arabia, World Journal of Medical Sciences 8, 36-47, 2013.
13. Alharbi A., Tchier F., Using a genetic-fuzzy algorithm as a computer aided diagnosis tool on Saudi Arabian breast cancer database, Mathematical Biosciences 286, 39–48, 2017.
14. Porto-Mascarenhas E.C., Assad D.X., Chardin H., Gozal D., Luca Canto G.D., Acevedo A.C., Guerra E.N.S., Salivary biomarkers in the diagnosis of breast cancer: A review, Critical Reviews in Oncology/Hematology 110, 62–73, 2017.
15. Ramalho M., Fontes F., Ruano L., Pereira S., Lunet N., Cognitive impairment in the first year after breast cancer diagnosis: A prospective cohort study, Breast 32, 173-178, 2017.
16. Peters M.L., Garber J.E., Tung N., Managing hereditary breast cancer risk in women with and without ovarian cancer, Gynecologic Oncology 146, 205–214, 2017.
17. Pudkasam S., Tangalakis K., Chinlumprasert N., Apostolopoulos V., Stojanovska L., Breast cancer and exercise: The role of adiposity and immune markers, Maturitas, In Press, Corrected Proof, 2017.
18. Cimpean A.M., Tamma R., Ruggieri S., Nico B., Toma A., Ribatti D., Mast cells in breast cancer angiogenesis, Critical Reviews in Oncology/Hematology 115, 23–26, 2017.
19. Almutlaq B.A., Almuazzi R.F., Almuhayfir A.A., Alfouzan A.M., Alshammari B.T., AlAnzi H.S., Ahmed H.G., Breast cancer in Saudi Arabia and its possible risk factors, Journal of Cancer Policy 12, 83–89, 2017.
20. Lukong K.E., Understanding breast cancer - The long and winding road, BBA Clinical 7, 64–77, 2017.
21. Coleman C., Early Detection and Screening for Breast Cancer, Seminars in Oncology Nursing 33, 141–155, 2017.
22. Baratloo A., Hosseini M., Negida A. and Ashal GE., Part 1: Simple Definition and Calculation of Accuracy, Sensitivity and Specificity. Emerg (Tehran) 3, 48-49, 2015.