From Real-World Data to Causally Interpretable Models: A Bayesian Network to Predict Cardiovascular Diseases in Adolescents and Young Adults with Breast Cancer.

Simple Summary: Cardiovascular diseases are among the most frequent, although rare, long-term sequalae in adolescents and young adult survivors of breast cancer. However, no dedicated tool exists to help clinicians with planning personalized follow-up strategies for these patients. To make up for this lack, in this work, we developed a Bayesian network, an artificial intelligence model, to predict the 5-year risk for cardiovascular diseases in these patients, leveraging real-world data from two different cohorts. The model showed a very good ability to identify patients at risk and select those that should be prioritized because they are at higher risk, making it useful for guiding clinicians in everyday practice. Finally, the methodological approach proposed in this work is particularly interesting for all researchers who aim at developing causally interpretable tools, also dealing with real-world data and their biases. Background: In the last decades, the increasing number of adolescent and young adult (AYA) survivors of breast cancer (BC) has highlighted the cardiotoxic role of cancer therapies, making cardiovascular diseases (CVDs) among the most frequent, although rare, long-term sequalae. Leveraging innovative artificial intelligence (AI) tools and real-world data (RWD), we aimed to develop a causally interpretable model to identify young BC survivors at risk of developing CVDs. Methods: We designed and trained a Bayesian network (BN), an AI model, making use of expert knowledge and data from population-based (1036 patients) and clinical (339 patient) cohorts of female AYA (i.e., aged 18 to 39 years) 1-year survivors of BC, diagnosed in 2009–2019. The performance achieved by the BN model was validated against standard classification metrics, and two clinical applications were proposed. Results: The model showed a very good classification performance and a clear causal semantic. According to the predictions made by the model, focusing on the 25% of AYA BC survivors at higher risk of developing CVDs, we could identify 81% of the patients who would actually develop it. Moreover, a desktop-based app was implemented to calculate the individual patient's risk. Conclusions: In this study, we developed the first causal model for predicting the CVD risk in AYA survivors of BC, also proposing an innovative AI approach that could be useful for all researchers dealing with RWD. The model could be pivotal for clinicians who aim to plan personalized follow-up strategies for AYA BC survivors. [ABSTRACT FROM AUTHOR]