Integrating Socio-Clinical Factors and IoT Biometrics for Early Breast Cancer Risk Prediction Using Machine Learning Models | IJCSE Volume 9 – Issue 6 | IJCSE-V9I6P11

Breast cancer is one of the most serious health problems faced by women across the world, particularly in developing countries such as India. Early detection through Breast Self-Examination (BSE) can help reduce mortality and improve treatment outcomes. This study focuses on combining socio-economic and clinical data with stochastic and machine learning models to predict breast cancer risk among women. Data were collected from 500 participants through structured interviews conducted in private medical colleges in Chennai. Parameters such as age, BSE (Breast Self-Examination) frequency, and presence of lumps, pain level, skin changes, nipple discharge, and IoT-based health indicators were analyzed. The dataset was preprocessed and evaluated using Logistic Regression and Random Forest models. Logistic Regression achieved 100% accuracy, while Random Forest achieved 96% accuracy in classifying breast cancer risk levels as low, moderate, or high. Confusion matrices and ROC-AUC analyses confirmed strong predictive performance. The results demonstrate that integrating BSE awareness with computational modeling improves early detection and clinical decision-making. The study highlights that even simple statistical models can provide reliable predictions when applied to well-structured healthcare data, promoting preventive awareness and timely medical referral among women.

This study highlights the importance of Breast Self-Examination (BSE) as a simple and effective method for early detection of breast abnormalities. By combining socio-economic and clinical data with stochastic and machine learning techniques, the research successfully developed predictive models that classify breast cancer risk with high accuracy. Logistic Regression achieved perfect accuracy, showing that the dataset followed a clear linear pattern, while Random Forest demonstrated strong performance in handling complex relationships between features. These results confirm that mathematical and stochastic models can provide valuable insights for preventive health analysis without the need for advanced artificial intelligence systems. The integration of BSE awareness, clinical examination, and computational modeling can support healthcare professionals in identifying high-risk individuals at an early stage. Overall, the study emphasizes that public health education, regular self-examination, and simple predictive tools can together reduce the burden of breast cancer and enhance women’s health outcomes in India and beyond.

1.Kandasamy, G., Almaghaslah, D., Almanasef, M., & Alamri, R. D. A. (2024). Knowledge, attitude, and practice towards breast self-examination among women: a web-based community study. Frontiers in Public Health, 12, 1450082. 2.Yildirim, H., & Yildirim, S. (2022). A different approach to breast self-examination training. Global Medical Journal, 14(1), E202236. https://ifnmujournal.com/gmj/article/view/E202236 3.Francks, L., Murray, A., & Wilson, E. (2023). Barriers and facilitators to breast self-examination in women under 50 in an international context: A qualitative systematic review. International Journal of Health Promotion and Education, 1–18. 4.Dechasa, D. B., Asfaw, H., & Abdisa, L. (2022). Practice of breast self-examination and associated factors among female health professionals working in public hospitals of Harari Regional State, Eastern Ethiopia. Frontiers in Oncology, 12, 1002111. 5.Jalloul, R. (2023). A Review of Machine Learning Techniques for the Detection of Breast Cancer. Journal of Cancer Research & Clinical Oncology. 6.Li, C. (2023). A Systematic Review of Application Progress on Machine Learning Models in Breast Cancer Diagnosis. Journal of Cancer Research & Clinical Oncology. 7.Rabiei, R. (2022). Prediction of Breast Cancer using Machine Learning Approaches. Journal of Cancer Research & Clinical Oncology. 8.Jafari, A. (2024). Machine-learning methods in detecting breast cancer and defining its type. Journal of Cancer Research & Clinical Oncology. 9.Islam, T. (2024). Predictive modeling for breast cancer classification in the Bangladeshi population. Scientific Reports. 10.Chen, T. (2024). Using an innovative method for breast cancer diagnosis. Journal of Cancer Research & Clinical Oncology. 11.Lee, S. (2006). A stochastic model for predicting the mortality of breast cancer. Journal of the National Cancer Institute Monographs. 12.Martinez, R. G. (2023). Deep learning algorithms for the early detection of breast cancer. Journal of Cancer Research & Clinical Oncology. https://www.sciencedirect.com/science/article/pii/S2352914823001636 13.Siah, K. W. (2019). Machine-learning and stochastic tumor growth models for predicting breast cancer outcomes. Clinical Cancer Investigation Journal. 14.Rahman, M. A. (2025). Advancements in Breast Cancer Detection: A Review of Global Trends, Risk Factors, Imaging Modalities, Machine Learning, and Deep Learning Approaches. BioMedInformatics. 15.Ahmed, K. A. (2025). Advancing breast cancer prediction: Comparative analysis of machine learning algorithms. PLOS ONE. 16.Gurmessa, D. K. (2024). Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images. BMJ Health & Care Informatics. Ghasemi, A. (2024). Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review.

Call for Paper (Hub) Fast Paper Publication IJCSE Indexing & Databases Submit Manuscript Call for Paper: Sep–Oct 2025 Call for Paper: Publish Research