Machine Learning in Breast Cancer Diagnosis: A Review of Logistic Regression and Related Methods

Abstract

: Breast cancer is routinely encountered in screening programs and continues to impose a heavy burden on health systems. Shifting diagnosis toward earlier stages is the primary driver of mortality reduction in screening, yet traditional diagnostic pathways — mammography interpretation, ultrasound/MRI assessment, and biopsy — can be expensive, invasive, and vulnerable to human error. Machine learning (ML) is used to prioritize borderline cases and to assign calibrated malignancy risk for expedited review. Among many algorithms, logistic regression (LR) stands out for its simplicity, computational efficiency, and interpretability, which are critical for clinical acceptance. This review synthesizes recent work on breast tumor classification with an emphasis on LR and compares it with Support Vector Machines (SVM), Decision Trees (DT), XGBoost, and Neural Networks (NN). This paper summarizes common datasets and metrics, highlight reported performance ranges, and discuss practical challenges — including interpretability, privacy, dataset shift, and external validation. This paper concludes with suggestions for future research on explainable AI, multi‑modal feature fusion, and privacy‑preserving learning pipelines that are suitable for real‑world healthcare deployments.