Ensemble Machine Learning and Statistical Procedures for Dynamic Predictions of Time-to-Event Outcomes

2026-02-23

AI Summary

This study addresses the challenge of model selection in dynamic time-to-event prediction—such as risk assessment for liver failure—by systematically extending the Super Learner ensemble learning framework to the setting of dynamic survival analysis. The proposed approach integrates joint modeling, landmarking, and a diverse set of machine learning algorithms, combining them through optimal weighted averaging based on cross-validation and a survival-adapted loss function (e.g., squared error loss tailored to censored data). Evaluated on data from patients with primary biliary cholangitis, the method demonstrates predictive performance that is at least as accurate as any individual candidate model, while substantially enhancing both flexibility and robustness in dynamic risk prediction.

Technology Category

• Machine Learning: Ensemble Methods
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Dynamic predictions for longitudinal and time-to-event outcomes have become a versatile tool in precision medicine. Our work is motivated by the application of dynamic predictions in the decision-making process for primary biliary cholangitis patients. For these patients, serial biomarker measurements (e.g., bilirubin and alkaline phosphatase levels) are routinely collected to inform treating physicians of the risk of liver failure and guide clinical decision-making. Two popular statistical approaches to derive dynamic predictions are joint modelling and landmarking. However, recently, machine learning techniques have also been proposed. Each approach has its merits, and no single method exists to outperform all others. Consequently, obtaining the best possible survival estimates is challenging. Therefore, we extend the Super Learner framework to combine dynamic predictions from different models and procedures. Super Learner is an ensemble learning technique that allows users to combine different prediction algorithms to improve predictive accuracy and flexibility. It uses cross-validation and different objective functions of performance (e.g., squared loss) that suit specific applications to build the optimally weighted combination of predictions from a library of candidate algorithms. In our work, we pay special attention to appropriate objective functions for Super Learner to obtain the most optimal weighted combination of dynamic predictions. In our primary biliary cholangitis application, Super Learner presented unique benefits due to its ability to flexibly combine outputs from a diverse set of models with varying assumptions for equal or better predictive performance than any model fit separately.

Problem

• dynamic prediction
• time-to-event
• ensemble learning
• Super Learner
• precision medicine

Innovation

• Super Learner
• ensemble learning
• dynamic prediction
• time-to-event
• joint modelling