Applying Under-Sampling Techniques and Cost-Sensitive Learning Methods on Risk Assessment of Breast Cancer
- 25 February 2015
- journal article
- Published by Springer Nature in Journal of Medical Systems
- Vol. 39 (4) , 1-13
Abstract
Breast cancer is one of the most common cause of cancer mortality. Early detection through mammography screening could significantly reduce mortality from breast cancer. However, most of screening methods may consume large amount of resources. We propose a computational model, which is solely based on personal health information, for breast cancer risk assessment. Our model can be served as a pre-screening program in the low-cost setting. In our study, the data set, consisting of 3976 records, is collected from Taipei City Hospital starting from 2008.1.1 to 2008.12.31. Based on the dataset, we first apply the sampling techniques and dimension reduction method to preprocess the testing data. Then, we construct various kinds of classifiers (including basic classifiers, ensemble methods, and cost-sensitive methods) to predict the risk. The cost-sensitive method with random forest classifier is able to achieve recall (or sensitivity) as 100 %. At the recall of 100 %, the precision (positive predictive value, PPV), and specificity of cost-sensitive method with random forest classifier was 2.9 % and 14.87 %, respectively. In our study, we build a breast cancer risk assessment model by using the data mining techniques. Our model has the potential to be served as an assisting tool in the breast cancer screening.Keywords
This publication has 13 references indexed in Scilit:
- Latent semantic analysisWIREs Cognitive Science, 2013
- Cancer statistics, 2013CA: A Cancer Journal for Clinicians, 2013
- Multi-state Markov models in cancer screening evaluation: a brief review and case studyStatistical Methods in Medical Research, 2010
- Pattern classification with missing data: a reviewNeural Computing and Applications, 2009
- Combined Screening With Ultrasound and Mammography vs Mammography Alone in Women at Elevated Risk of Breast CancerJAMA, 2008
- A systematic review of the effectiveness of magnetic resonance imaging (MRI) as an addition to mammography and ultrasound in screening young women at high risk of breast cancerEuropean Journal of Cancer, 2007
- An introduction to ROC analysisPattern Recognition Letters, 2006
- On combining classifiersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Stacked generalizationNeural Networks, 1992
- Indexing by latent semantic analysisJournal of the American Society for Information Science, 1990