Predicting breast cancer-specific survival in metaplastic breast cancer patients using machine learning algorithms

Yufan Feng; Natasha McGuire; Alexandra Walton; AP-MBC Consortium; Stephen Fox; Antonella Papa; Sunil R Lakhani; Amy E McCart Reed

doi:10.1016/j.jpi.2023.100329

Predicting breast cancer-specific survival in metaplastic breast cancer patients using machine learning algorithms

J Pathol Inform. 2023 Aug 8:14:100329. doi: 10.1016/j.jpi.2023.100329. eCollection 2023.

Authors

Yufan Feng¹, Natasha McGuire¹, Alexandra Walton^{1

2}; AP-MBC Consortium; Stephen Fox³, Antonella Papa⁴, Sunil R Lakhani^{1

2}, Amy E McCart Reed¹

Affiliations

¹ UQ Centre for Clinical Research, Faculty of Medicine, The University of Queensland, Brisbane 4029, Australia.
² Pathology Queensland, The Royal Brisbane and Women's Hospital, Brisbane 4029, Australia.
³ Peter MacCallum Cancer Centre and University of Melbourne, Melbourne 3000, Australia.
⁴ Monash Biomedicine Discovery Institute, Monash University, Melbourne 3800, Australia.

Abstract

Metaplastic breast cancer (MpBC) is a rare and aggressive subtype of breast cancer, with data emerging on prognostic factors and survival prediction. This study aimed to develop machine learning models to predict breast cancer-specific survival (BCSS) in MpBC patients, utilizing a dataset of 160 patients with clinical, pathological, and biological variables. An in-depth variable selection process was carried out using gain ratio and correlation-based methods, resulting in 10 variables for model estimation. Five models (decision tree with bagging; logistic regression; multilayer perceptron; naïve Bayes; and, random forest algorithms) were evaluated using 10-fold cross-validation. Despite the constraints posed by the absence of therapeutic information, the random forest model exhibited the highest performance in predicting BCSS, with an ROC area of 0.808. This study emphasizes the potential of machine learning algorithms in predicting prognosis for complex and heterogeneous cancer subtypes using clinical datasets, and their potential to contribute to patient management. Further research that incorporates additional variables, such as treatment response, and more advanced machine learning techniques will likely enhance the predictive power of MpBC prognostic models.

Keywords: Breast cancer; Breast cancer-specific survival (BCSS); Machine learning algorithms; Metaplastic breast cancer (MpBC); Predictive models; Random forest.