Comparison of Machine Learning Models for Classificationof Breast Cancer Risk Based on Clinical Data

Background: Breast cancer (BC) is a major global health concern with rising incidence and mortality rates in many developingcountries. Effective BC risk assessment models are crucial for prevention and early detection. While the Gail model, a traditionallogistic regression-based model, has been broadly used, its predictive performance may be limited by its linear assumptions. Withthe rapid advancement of artificial intelligence (AI) in medical sciences, various complex machine learning algorithms havebeen developed for risk prediction, including for BC.Aims: This study aims to compare the quality of AI-based models with the traditional Gail model in assessing BC risk using apopulation dataset. It also evaluates the performance of these models in predicting BC risk.Methods and Results: This study involved 942 newly diagnosed BC patients and 975 healthy controls at the Cancer Institutein IKH hospital Complex, Tehran. Ten classification algorithms were applied to the dataset. The accuracy, sensitivity, precision,and feature importance in the machine learning algorithms were assessed and compared to previous studies for evaluation. Thestudy found that AI algorithms alone did not significantly improve predictability compared to the Gail model. However, the im-portance of variables varied significantly among the AI algorithms. Understanding feature importance and interactions is crucialin AI modeling in order to enhance accuracy and identify critical risk factors.Conclusion: This study concluded that, in BC risk prediction, incorporating specific risk factors, such as genetic and image-related variables, may be necessary to further enhance accuracy in BC risk prediction models. Furthermore, it is crucial to ad-dress modeling issues in models with a restricted number of features for future research.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work isproperly cited.© 2025 The Author(s). Cancer Reports published by Wiley Periodicals LLC.Abbreviations: BC, breast cancer; BCRAT, breast cancer risk assessment tool; DT, decision tree; IARC, International Agency for Research on Cancer; KNN, k-nearest neighbor; LR, logisticregression; ML, machine learning; RF, random forest; SVM, support vector machine.