Implementing Artificial Intelligence Algorithms for Predicting Survival Rates in Breast Cancer Patients
Abstract
Breast cancer ranks as the most prevalent cancer type among women worldwide, being the second highest cause of female mortality among all cancer types. Accurately predicting the survival rate of breast cancer patients is a critical concern for cancer researchers. Machine Learning (ML) has garnered considerable attention for its potential to provide precise results, yet its methodologies and predictive performance remain debatable. This paper focuses on employing ML algorithms to predict Haberman's Breast Cancer Survival study. Specifically, two different ML approaches, namely Multilayer Perceptron (MLP) and Support Vector Machine (SVM) models, are explored for Breast Cancer Survival prognosis. The classification performance of abnormal and normal Breast Cancer Survival patients is assessed across various metrics including training and testing accuracy, precision, and recall. The objective of this systematic review is to identify and critically evaluate current studies regarding the application of ML in predicting the 5-year survival rate of breast cancer. Test results on Haberman's Breast Cancer Survival dataset demonstrate the effectiveness of the proposed MLP approach, achieving an accuracy of 97.54%.
Keywords
Download Options
Introduction
Breast cancer ranks as the second most lethal disease after Lung Cancer, accounting for the highest mortality rate among all cancers. Approximately 12% of new cancer cases worldwide are attributed to breast cancer, with women constituting nearly 25% of these cases [5]. Individuals typically consult an oncologist upon noticing any signs or symptoms of the disease, who may conduct various diagnostic tests such as mammograms, MRI scans, ultrasound, X-rays, and tissue biopsies to detect breast cancer. Sentinel lymph node biopsy is commonly performed to identify cancerous cells in lymph nodes. AI techniques are also employed to classify cancers as benign or malignant, aiding in early detection to improve patient prognosis and survival rates [1].
Survival, defined as the period a patient survives after cancer diagnosis, is crucial for standardizing reporting and assessing survivability. The 5-year threshold is significant for monitoring survival rates, with previous studies using this timeframe to determine survival outcomes [7]. Breast cancer exhibits considerable variability in survival rates between individuals, making accurate prediction of survival essential for guiding clinical treatment decisions, avoiding unnecessary interventions, reducing financial costs, and facilitating palliative and hospice care. Consequently, predicting survival has become a major focus of breast cancer research, enabling patients to receive timely and appropriate interventions while avoiding unnecessary treatments for benign cancers."
Conclusion
This paper investigates anomalies using two AI algorithms. Our initial findings indicate that the MLP algorithm achieves higher classification accuracy in detecting various abnormalities compared to SVM models. The results demonstrate that MLP is the most suitable approach for data-driven anomaly detection compared to other methods such as SVM.