Enhancing breast cancer screening with machine learning predictive models
Ajatray Swagat Bhuyan, Deepika Sharma, Komalpreet Saini · 2025
Breast cancer is still a major global health issue that necessitates novel strategies for improved screening accuracy and early detection. The research paper enhancing breast cancer screening with machine learning predictive models is summarized in this abstract. Machine learning (ML) has become more well-known as a game-changing technology in the medical industry in recent years. The goal of this research is to improve predictive models for mammography interpretation in order to advance breast cancer screening. This study explores the potential for ML models to support current screening procedures by utilizing a diverse dataset that includes mammographic images, patient histories, and histopathological data. The research methodoogy includes feature engineering, the selection and optimization of ML algorithms, and a thorough evaluation of the models using well-established performance metrics like sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). Preliminary findings show promising improvements in the accuracy of breast cancer screening, with ML models consistently outperforming traditional techniques. The paper highlights the transformative potential of ML-driven breast cancer screening and discusses the clinical implications of these findings. With this paradigm shift, improved patient outcomes, earlier.