Automated Machine Learning for Breast Cancer Diagnosis Using TPOT

Breast cancer is a major global health issue, emphasizing the need for accurate diagnostic tools to improve patient outcomes. This paper presents an approach that utilizes Automated Machine Learning (AutoML), specifically the Tree-based Pipeline Optimization Tool (TPOT) Classifier, to streamline the model selection and so that optimizing breast cancer diagnosis process. The objective of the work is to develop a robust predictive model that classifies tumors as benign or malignant based on features derived from medical imaging data. The final model, a Random Forest Classifier, achieved an important accuracy score of 96.49%, demonstrating its effectiveness and reliability in clinical settings. Comprehensive evaluation metrics, including confusion matrix analysis and Receiver Operating Characteristic (ROC) curve assessment, validate the model's performance, highlighting its potential for enhancing breast cancer diagnosis.