Evaluation of Feature Selection Techniques for Breast Cancer Risk Prediction
Open Access
- 12 October 2021
- journal article
- research article
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 18 (20) , 10670
Abstract
This study evaluates several feature ranking techniques together with some classifiers based on machine learning to identify relevant factors regarding the probability of contracting breast cancer and improve the performance of risk prediction models for breast cancer in a healthy population. The dataset with 919 cases and 946 controls comes from the MCC-Spain study and includes only environmental and genetic features. Breast cancer is a major public health problem. Our aim is to analyze which factors in the cancer risk prediction model are the most important for breast cancer prediction. Likewise, quantifying the stability of feature selection methods becomes essential before trying to gain insight into the data. This paper assesses several feature selection algorithms in terms of performance for a set of predictive models. Furthermore, their robustness is quantified to analyze both the similarity between the feature selection rankings and their own stability. The ranking provided by the SVM-RFE approach leads to the best performance in terms of the area under the ROC curve (AUC) metric. Top-47 ranked features obtained with this approach fed to the Logistic Regression classifier achieve an AUC = 0.616. This means an improvement of 5.8% in comparison with the full feature set. Furthermore, the SVM-RFE ranking technique turned out to be highly stable (as well as Random Forest), whereas relief and the wrapper approaches are quite unstable. This study demonstrates that the stability and performance of the model should be studied together as Random Forest and SVM-RFE turned out to be the most stable algorithms, but in terms of model performance SVM-RFE outperforms Random Forest.Keywords
Funding Information
- Spanish Ministry Council (Accion Transversal del Cancer)
- Instituto de Salud Carlos III (PI08/1770, PI08/0533, PI08/1359, PS09/00773, PS09/01286, PS09/01903, PS09/02078, PS09/01662, PI11/01403, PI11/01889, PI11/00226, PI11/01810, PI11/02213, PI12/00488, PI12/00265, PI12/01270, PI12/00715, PI12/00150)
- Fundación Marqués de Valdecilla (API 10/09)
- International Cancer Genome Consortium (LE22A10-2)
- Consejería de Salud y Familias, Junta de Andalucía (PI-0571)
- Conselleria de Sanitat Universal i Salut Pública (AP 061/10)
- RecerCaixa (2010ACUP 00310)
- Regional Government of the Basque Country (FOOD-CT- 2006-036224- HIWATE)
- Fundación Científica Asociación Española Contra el Cáncer (-)
- Generalitat de Catalunya (2009SGR1489)
This publication has 60 references indexed in Scilit:
- Dual association between polyphenol intake and breast cancer risk according to alcohol consumption level: a prospective cohort studyBreast Cancer Research and Treatment, 2012
- A review of feature selection methods on synthetic dataKnowledge and Information Systems, 2012
- Review On Feature Selection Techniques And The Impact Of Svm For Cancer Classification Using Gene Expression ProfileInternational Journal of Computer Science & Engineering Survey, 2011
- Oral Contraceptive Use and Breast Cancer: A Prospective Study of Young WomenCancer Epidemiology, Biomarkers & Prevention, 2010
- LDA (Linear Discriminant Analysis)2009
- Algebraic stability indicators for ranked lists in molecular profilingBioinformatics, 2007
- Physical Activity and Breast CancerEpidemiology, 2007
- Stability of feature selection algorithms: a study on high-dimensional spacesKnowledge and Information Systems, 2006
- Alcohol Intake, Type of Beverage, and Risk of Breast Cancer in Pre‐ and Postmenopausal WomenAlcohol, Clinical and Experimental Research, 2004
- LIII. On lines and planes of closest fit to systems of points in spaceJournal of Computers in Education, 1901