Breast cancer :Early diagnosis by using artificial intelligence
Navita Panwar, Kapil D. Sethi · 2022
Despite several epochal medical breakthroughs, the very mention of word ‘Cancer’ is enough to send shivers down the spine of anyone. It still remains a leading marauding menace for the whole mankind. Among the various forms of cancers plaguing humans, breast cancer is very common form of cancer resulting in huge number of fatalities especially among the women. Its detection in early stages remains a bright glimmer of hope which increases the chances of its cure exponentially. Use of technology involving artificial intelligence for disease detection is a very recent phenomenon but it has unleashed revolutionary changes in detection and cure of many fatal diseases including breast cancer. This study utilizes three classifiers i.e. Support vector, KNN and Naïve Bayes for detection of breast cancer with an appropriate features selection method that selects only the features with high impact and culls out the others not so significant factors. The Wisconsin Diagnosis Breast Cancer data set has been employed as a training and testing set for this study to make a comparative analysis of performance of the various ML algorithms on the pedestal of accuracy and precision. The empirical values so obtained and the results deduced therefrom prove that the Support Vector classifier approach is most successful technique for detection of breast cancer with an accuracy of 98.24 %.