Early Detection of Breast Cancer Recurrence using Machine Learning for Improved Patient Outcomes

Breast Cancer is most significant disease of death for women in the world, early identification is very essential. In order to enhance the precision and dependability of Breast Cancer recurrences diagnosis, this study investigates the application of several machine learning techniques, such as Support Vector Machine, Genetic techniques, and Voting Classifier. The prior goal of the proposed recurrence diagnosis model is to combine Voting Classifier with Genetic algorithm to overcome the challenges with machine learning algorithm prediction. The hybrid model (GA+VC) can improve performance through a collective decision-making process. Hyperparameters such as kernel functions for SVM are optimized to maximize model performance. In this paper, the study explores the Sand cat swarm optimization (SCSO) with SVM gives higher accuracy in recurrence diagnosis. The result obtained indicate that recurrence model gives higher accuracy of 90%. The results with the optimization SCSO with SVM providing insights into the trade-off between detecting true positives (malignant cases) and minimizing false positives.