ENHANCING EARLY BREAST CANCER PREDICTION: A COMPARATIVE STUDY OF MACHINE LEARNING MODELS ON CLINICAL ACCURACY AND INTERPRETABILITY

Abstract

The purpose of this research is to evaluate and compare several machine learning models according to their accuracy, considering their generalization capability and their ability to provide clinical explanations. Primary data was acquired from 150 case (cancer patients) and 80 control (cancer-free) respondents from cancer treatment centers. Multilayer perceptron (MLP) and logistic regression algorithms performed better than the traditional methods in predicting breast cancer incidence. The above results are meant to speed up the process of early cancer prediction and show AI experts new ways AI is being used in health care.