Diagnóstico de cáncer de mama usando el tamaño del efecto d de Cohen como selector de características

Breast cancer is a tumor that begins to grow in the milk ducts or lobules and can become lethal iftreatment is not administered in time. According to the World Health Organization (WHO), there were approximately2.3 million cases of breast cancer in 2020. Furthermore, breast cancer can affect anyone, particularlywomen over 50 years old. Therefore, it is crucial to have early diagnostic techniques. We propose a novel methodbased on Cohen’s d for feature selection in this context. Cohen’s d is a statistical concept that quantifies thestrength of the relationship between two populations on a numeric scale. The central idea is to utilize Cohen’s deffect size as a feature selector to reduce the dimensionality of the data and enhance the predictors through a MachineLearning (ML) classifier model for diagnosing breast cancer. For experimental purposes, the Breast CancerWisconsin database was used. This proposed feature selector is compared with two classical methods: LearningVector Quantization (LVQ) and Recursive Feature Elimination (RFE). A random evaluation of the features ofeach selector was conducted 100 times using a Support Vector Machine (SVM) classifier, resulting in the followingaverage outcomes: Cohen’s d based feature selector showed 0.96 sensitivity and 0.97 specificity, RFE basedfeature selector exhibited 0.95 sensitivity and 0.98 specificity, and LVQ based feature selector demonstrated 0.91sensitivity and 0.96 specificity. These promising results indicate that the proposed methodology utilizing Cohen’sd may be a valuable feature selector and sheds light on the long-standing research into breast cancer detection.