Artificial Intelligence in Breast Cancer Survival Prediction: A Comprehensive Systematic Review and Meta-Analysis Publisher



Javanmard Z¹ ; Zarean Shahraki S² ; Safari K³ ; Omidi A⁴ ; Raoufi S⁵ ; Rajabi M⁶ ; Akbari ME⁷ ; Aria M⁷ Show Affiliations
Source: Frontiers in Oncology Published:2024

Abstract

Background: Breast cancer (BC), as a leading cause of cancer mortality in women, demands robust prediction models for early diagnosis and personalized treatment. Artificial Intelligence (AI) and Machine Learning (ML) algorithms offer promising solutions for automated survival prediction, driving this study’s systematic review and meta-analysis. Methods: Three online databases (Web of Science, PubMed, and Scopus) were comprehensively searched (January 2016-August 2023) using key terms (“Breast Cancer”, “Survival Prediction”, and “Machine Learning”) and their synonyms. Original articles applying ML algorithms for BC survival prediction using clinical data were included. The quality of studies was assessed via the Qiao Quality Assessment tool. Results: Amongst 140 identified articles, 32 met the eligibility criteria. Analyzed ML methods achieved a mean validation accuracy of 89.73%. Hybrid models, combining traditional and modern ML techniques, were mostly considered to predict survival rates (40.62%). Supervised learning was the dominant ML paradigm (75%). Common ML methodologies included pre-processing, feature extraction, dimensionality reduction, and classification. Deep Learning (DL), particularly Convolutional Neural Networks (CNNs), emerged as the preferred modern algorithm within these methodologies. Notably, 81.25% of studies relied on internal validation, primarily using K-fold cross-validation and train/test split strategies. Conclusion: The findings underscore the significant potential of AI-based algorithms in enhancing the accuracy of BC survival predictions. However, to ensure the robustness and generalizability of these predictive models, future research should emphasize the importance of rigorous external validation. Such endeavors will not only validate the efficacy of these models across diverse populations but also pave the way for their integration into clinical practice, ultimately contributing to personalized patient care and improved survival outcomes. Systematic Review Registration: https://www.crd.york.ac.uk/prospero/, identifier CRD42024513350. Copyright © 2025 Javanmard, Zarean Shahraki, Safari, Omidi, Raoufi, Rajabi, Akbari and Aria.