Clinical time-to-event prediction enhanced by incorporating compatible related outcomes

Accurate time-to-event (TTE) prediction of clinical outcomes from personal biomedical data is essential for precision medicine. It has become increasingly common that clinical datasets contain information for multiple related patient outcomes from comorbid diseases or multifaceted endpoints of a single disease. Various TTE models have been developed to handle competing risks that are related to mutually exclusive events. However, clinical outcomes are often non-competing and can occur at the same time or sequentially. Here we develop TTE prediction models with the capacity of incorporating compatible related clinical outcomes. We test our method on real and synthetic data and find that the incorporation of related auxiliary clinical outcomes can: 1) significantly improve the TTE prediction performance of conventional Cox model while maintaining its interpretability; 2) further improve the performance of the state-of-the-art deep learning based models. While the auxiliary outcomes are utilized for model training, the model deployment is not limited by the availability of the auxiliary outcome data because the auxiliary outcome information is not required for the prediction of the primary outcome once the model is trained.Author summary: The disease outcome of a patient is often characterized by the occurrence of important clinical events such as stroke, heart failure, cancer progression, and death. Prediction of the time to the occurrence of such clinical events is critical for disease prognosis and therapeutic decision. However, accurate time-to-event prediction is a long-standing challenge due to inadequate data and modeling tools. In recent years, the rapid advance in biomedical data collection and artificial intelligence has provided a solid foundation for more sophisticated and accurate time-to-event prediction models. In this work, we develop a machine learning method to incorporate information from related clinical outcomes to improve the accuracy of time-to-event prediction. This method can improve the performance of different time-to-event prediction models including the conventional regression based model and the state-of-the-art deep learning based model. We expect that this new method can be broadly used for complex prognosis problems involving comorbidities and multifaceted disease endpoints.