MENSA: A Multi-Event Network for Survival Analysis with Trajectory-based Likelihood Estimation

We introduce MENSA, a novel deep learning model for multi-event survival analysis, which predicts the time until an instance experiences multiple distinct events based on its features. MENSA learns a shared representation of the input features while capturing the complex dependence structures between events. In practice, it optimizes the sum of the traditional negative log-likelihood across events and a novel trajectory-based likelihood, which encourages the model to learn the temporal order in which events occur. Experiments on real-world clinical datasets demonstrate that MENSA improves risk and time-to-event prediction compared to state-of-the-art models across single-event, competing-risk, and multi-event settings. Moreover, MENSA achieves this with fewer parameters and lower computational cost (FLOPs) than several deep learning baselines, particularly in high-dimensional feature spaces (more than 100 features).
View on arXiv@article{lillelund2025_2409.06525, title={ MENSA: A Multi-Event Network for Survival Analysis with Trajectory-based Likelihood Estimation }, author={ Christian Marius Lillelund and Ali Hossein Gharari Foomani and Weijie Sun and Shi-ang Qi and Russell Greiner }, journal={arXiv preprint arXiv:2409.06525}, year={ 2025 } }