Prototype to estimate breast cancer suspicion in a hospital of the Mexican public health system

Abstract

Breast cancer is a public health problem because it is the type of cancer with the highest incidence and mortality in women. X-ray studies of the breasts, mammograms, represent one of the main tools used by doctors for the early detection of this disease. In this work, it is proposed to mitigate this problem using a system prototype for estimating the suspicion of breast cancer from the risk factors. The system prototype includes a gradient boosting decision tree model for cancer risk prediction and a web system that can be used in hospitals to speed up the consultation of breast cancer patients. The prototype was validated with stress tests, black box tests, white box tests and Iadov techniques for the satisfaction of end users. The results obtained lead us to conclude that the prototype can be incorporated into the daily consultations of Mexican hospitals as a support tool in the early detection of breast cancer, contributing to the decrease in the death rate caused by this disease in Mexico.