A deep-learning-based clinical risk stratification for overall survival in adolescent and young adult women with breast cancer

Objective The objective of this study is to construct a novel clinical risk stratification for overall survival (OS) prediction in adolescent and young adult (AYA) women with breast cancer. Method From the Surveillance, Epidemiology, and End Results (SEER) database, AYA women with primary breast cancer diagnosed from 2010 to 2018 were included in our study. A deep learning algorithm, referred to as DeepSurv, was used to construct a prognostic predictive model based on 19 variables, including demographic and clinical information. Harrell’s C-index, the receiver operating characteristic (ROC) curve, and calibration plots were adopted to comprehensively assess the predictive performance of the prognostic predictive model. Then, a novel clinical risk stratification was constructed based on the total risk score derived from the prognostic predictive model. The Kaplan–Meier method was used to plot survival curves for patients with different death risks, using the log-rank test to compared the survival disparities. Decision curve analyses (DCAs) were adopted to evaluate the clinical utility of the prognostic predictive model. Results Among 14,243 AYA women with breast cancer finally included in this study, 10,213 (71.7%) were White and the median (interquartile range, IQR) age was 36 (32–38) years. The prognostic predictive model based on DeepSurv presented high C-indices in both the training cohort [0.831 (95% CI 0.819–0.843)] and the test cohort [0.791 (95% CI 0.764–0.818)]. Similar results were observed in ROC curves. The excellent agreement between the predicted and actual OS at 3 and 5 years were both achieved in the calibration plots. The obvious survival disparities were observed according to the clinical risk stratification based on the total risk score derived from the prognostic predictive model. DCAs also showed that the risk stratification possessed a significant positive net benefit in the practical ranges of threshold probabilities. Lastly, a user-friendly Web-based calculator was generated to visualize the prognostic predictive model. Conclusion A prognostic predictive model with sufficient prediction accuracy was construct for predicting OS of AYA women with breast cancer. Given its public accessibility and easy-to-use operation, the clinical risk stratification based on the total risk score derived from the prognostic predictive model may help clinicians to make better-individualized management.