Prediction of Malignant Breast Cancer Cases Using Ensemble Machine Learning: A Case Study of Pesticides Prone Area

Cancer of the female breast is one of the leading types of cancers worldwide. This paper presents a case study of Malwa Belt in India that has witnessed the proliferation in the overall mortality rate due to breast cancer. The paper researches mortality aspect of the disease and its association with the various risk parameters including demographic characteristics, percentage of pesticides residue present in the water and soil, life style of the women in the affected area, water intake, and the amount of pesticide exposure to the patient. The levels of organochlorine pesticides like DDT and its metabolites and isomers of HCH in blood, tumor and surrounding adipose are estimated. Additionally, an extent of exposure of the subjects to environmental pollutants like heavy metals (Lead, Copper, Iron, Zinc, Calcium, Selenium, and Chromium etc.)are also examined. For the obtained experimental data, an efficient ensemble machine learning based framework called Bagoost is proposed to predict the risk of breast cancer in Malwa women. The performance of the proposed machine learning model results in an accuracy of 98.21 percent, when empirically tested using K-fold cross validation over the real time data of malignant and benign cases and is established to be efficacious than the existing approaches.