Revolutionizing Breast Cancer Diagnosis: Insights from KNN and SVM Models in Machine Learning
Charan Vemula, Pujitha Chavva, Usha Battu, Satwika Vemulapalli, K V Prasad, Sathish Kumar Kannaiah · 2024
We propose to carry out a complete assessment of the machine learning approaches associated to the hard work of breast cancer diagnosis with the aid of this research project. We exhibit the prediction skills of two popular algorithms, K-Nearest Neighbours (KNN) and Support Vector Machine (SVM), by closely investigating the Breast Cancer Wisconsin dataset. Our work applies rigorous cross-validation approaches in an attempt to penetrate the challenging area of model evaluation. Our objective is to uncover the precise relationship between diagnostic efficacy and computational complexity. Extensive investigation has revealed that KNN and SVM models have the potential to recognise minute patterns that may contribute to the appearance of breast cancer. Consequently, we supply crucial information that helps healthcare practitioners categorise disorders. Our findings not only highlight the outstanding prediction capacities of these models, but also indicate to their potential as crucial support systems for treatment tools that have the potential to transform the way breast cancer is identified and treated.