Abstract
Accurate prediction of the individualized survival benefit of adjuvant therapy is key to making informed therapeutic decisions for patients with early invasive breast cancer. Machine learning technologies can enable accurate prognostication of patient outcomes under different treatment options by modelling complex interactions between risk factors in a data-driven fashion. Here, we use an automated and interpretable machine learning algorithm to develop a breast cancer prognostication and treatment benefit prediction model—Adjutorium—using data from large-scale cohorts of nearly one million women captured in the national cancer registries of the United Kingdom and the United States. We trained and internally validated the Adjutorium model on 395,862 patients from the UK National Cancer Registration and Analysis Service (NCRAS), and then externally validated the model among 571,635 patients from the US Surveillance, Epidemiology, and End Results (SEER) programme. Adjutorium exhibited significantly improved accuracy compared to the major prognostic tool in current clinical use (PREDICT v2.1) in both internal and external validation. Importantly, our model substantially improved accuracy in specific subgroups known to be under-served by existing models. Adjutorium is currently implemented as a web-based decision support tool ( https://vanderschaar-lab.com/adjutorium/ ) to aid decisions on adjuvant therapy in women with early breast cancer, and can be publicly accessed by patients and clinicians worldwide. Methods are available to support clinical decisions regarding adjuvant therapies in breast cancer, but they have limitations in accuracy, generalizability and interpretability. Alaa et al. present an automated machine learning model of breast cancer that predicts patient survival and adjuvant treatment benefit to guide personalized therapeutic decisions.
Highlights
Accurate prediction of the individualized survival benefit of adjuvant therapy is key to making informed therapeutic decisions for patients with early invasive breast cancer
The improvements in accuracy achieved by Adjutorium were even more significant in predicting breast cancer-specific mortality, with an area under receiver operating characteristic curve25 (AUC-ROC) of 0.825 for 10-year outcomes, compared with
Improvements were greater in subgroups that are poorly served by current prognostic tools; the accuracy gains achieved by Adjutorium relative to PREDICT v2.1 were higher in elderly patients, patients with estrogen receptor (ER) negative and human epidermal growth factor receptor 2 (HER2) negative breast cancer
Summary
Adjutorium predicted 10-year all-cause mortality with an AUC-ROC accuracy of 0.815 (95% CI: 0.813-0.817), compared with 0.777 (95% CI: 0.768-0.772) by PREDICT v2.1, and 0.775 (95% CI: 0.773-0.777) by the Cox PH model. Improvements were greater in subgroups that are poorly served by current prognostic tools; the accuracy gains achieved by Adjutorium relative to PREDICT v2.1 were higher in elderly patients (age > 65 yrs at diagnosis), patients with ER negative and HER2 negative breast cancer This is likely due to the fact that our machine learning-based risk equation captured nuanced interactions and non-linear patterns that were not incorporated in existing prognostic tools (Fig. 2(c)). 21,164 patients (in the internal validation cohort) with complete data on all variables, the AUC-ROC accuracy of Adjutorium with respect to 10-year breast cancer-specific mortality was 0.811 (95% CI: 0.0.808-0.814), and 0.783 (95% CI: 0.780-0.786) for PREDICT v2.1.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
