Incorporation of emergent symptoms and genetic covariates improves prediction of aromatase inhibitor therapy discontinuation

Objectives Early discontinuation is common among breast cancer patients taking aromatase inhibitors (AIs). Although several predictors have been identified, it is unclear how to simultaneously consider multiple risk factors for an individual. We sought to develop a tool for prediction of AI discontinuation and to explore how predictive value of risk factors changes with time.Materials and Methods Survival machine learning was used to predict time-to-discontinuation of AIs in 181 women who enrolled in a prospective cohort. Models were evaluated via time-dependent area under the curve (AUC), c-index, and integrated Brier score. Feature importance was analysis was conducted via Shapley Additive Explanations (SHAP) and time-dependence of their predictive value was analyzed by time-dependent AUC. Personalized survival curves were constructed for risk communication.Results The best-performing model incorporated genetic risk factors and changes in patient-reported outcomes, achieving mean time-dependent AUC of 0.66, and AUC of 0.72 and 0.67 at 6- and 12-month cutoffs, respectively. The most significant features included variants in ESR1 and emergent symptoms. Predictive value of genetic risk factors was highest in the first year of treatment. Decrease in physical function was the strongest independent predictor at follow-up.Discussion and Conclusion Incorporation of genomic and 3-month follow-up data improved the ability of the models to identify the individuals at risk of AI discontinuation. Genetic risk factors were particularly important for predicting early discontinuers. This study provides insight into the complex nature of AI discontinuation and highlights the importance of incorporating genetic risk factors and emergent symptoms into prediction models. Despite their effectiveness in treating early-stage breast cancer, aromatase inhibitors (AIs) often cause severe side effects that result in treatment discontinuation and worse outcomes. While several genetic and clinical predictors of discontinuation have been identified, it remains unclear how to simultaneously consider multiple risk factors for an individual. In this study, we developed a survival machine learning model to predict discontinuation in patients initiating AI therapy and to explore how the predictive value of risk factors changes with time. To assess the importance of genetic markers and emergent symptoms for prediction, we compared models that incorporated these risk factors with those that excluded them. Our results indicated that the incorporation of genetics improved the prediction of discontinuation within the first 6-12 months of treatment, with genetic factors emerging as the most important predictors of discontinuation at baseline. On the contrary, genetics did not contribute as much to the overall model performance when incorporating toxicity that developed in the first 3 months, and emergent symptoms became the most important predictors of discontinuation. Together, our findings demonstrate the importance of incorporating genetic risk factors and emergent symptoms into AI discontinuation prediction models.