PREEMPTIVE DIAGNOSIS OF PROSTATE CANCER AND BREAST CANCER USING COMPUTATIONAL INTELLIGENCE

The preemptive detection of breast and prostate cancer is critical to improving survival rates, particularly in regions with limited access to advanced healthcare. Conventional diagnostic methods are often invasive, costly, and inaccessible, creating barriers to early detection. This project sets out to address these challenges by designing a machine learning based predictive system capable of identifying individuals at risk using structured questionnaire data. The key objective is to develop a non-invasive, affordable, and scalable model that can support early cancer screening in resource-constrained environments. The methodology involved collecting questionnaire-based data that captured demographic information, family history, lifestyle factors, and self-reported health indicators. The dataset was preprocessed, and selected machine learning algorithms including Support Vector Machine (SVM), Logistic Regression, K-Nearest Neighbor (KNN), and Random Forest were trained and tested. The models were evaluated using performance metrics such as accuracy, precision, recall, F1-score, and ROC-AUC to determine their predictive effectiveness. The results revealed that the Random Forest classifier outperformed the other models, achieving the highest overall accuracy and balanced performance across evaluation metrics. This demonstrates that ensemble methods are more effective in capturing complex interactions among risk factors. Logistic Regression, SVM, and KNN also performed well, showing that machine learning models can be reliably applied to structured questionnaire data for risk prediction. In conclusion, this study demonstrates that computational intelligence can serve as a valuable tool for preemptive cancer diagnosis in low-resource settings. The findings highlight the potential for machine learning based systems to complement traditional screening approaches and improve timely intervention. It is recommended that future research validate these models with larger datasets from multiple hospitals and incorporate explainability techniques to enhance clinical trust and adoption.