Dynamic Prediction in Mixture Cure Models: A Model-Based Landmarking Approach

2025-09-23

AI Summary

Existing dynamic prediction methods—such as last-observation-carried-forward (LOCF)—suffer from substantial information loss when summarizing longitudinal covariates in mixture cure models, fail to correct for measurement error, and rely on outdated observations, leading to biased predictions. To address these limitations, we propose a novel dynamic prediction framework that incorporates subject-specific random effects, estimated via linear mixed models, as time-varying covariates within a Cox proportional hazards mixture cure model—enabling real-time, longitudinal-data-driven prognostic updates. Our approach innovatively integrates the landmarking strategy with the mixture cure model, preserving longitudinal information while simultaneously correcting for measurement error. Simulation studies demonstrate that the proposed method consistently outperforms LOCF across varying cure fractions, sample sizes, and model misspecifications. Furthermore, analysis of real-world kidney transplant data confirms its superior predictive accuracy and practical utility.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Mixed Discrete/Continuous Search
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Mixture cure models are widely used in survival analysis when a portion of patients is considered cured and is no longer at risk for the event of interest. In clinical settings, dynamic survival prediction is particularly important to refine prognosis by incorporating updated patient information over time. Landmarking methods have emerged as a flexible approach for this purpose, as they allow to summarize longitudinal covariates up to a given landmark time and to use these summaries in subsequent prediction. For mixture cure models, the only landmarking strategy available in the literature relies on the last observation carried forward (LOCF) method to summarize longitudinal dynamics up to the landmark time. However, LOCF discards most of the longitudinal information, does not correct for measurement error, and may rely on outdated values if observation times are far apart. To overcome these limitations, we propose a sequential approach that integrates model-based landmarking within a mixture cure model. Initially, longitudinal covariates are modeled using (generalized) linear mixed models, from which individual-specific random effects are predicted. The predicted random effects are then incorporated as covariates into a Cox proportional hazards cure model. We investigated the performance of the proposed approach under different cure fractions, sample sizes, and longitudinal data structures through an extensive simulation study. The results show that the model-based strategy provides more refined predictions compared to LOCF, even when the model is misspecified in favour of the LOCF approach. Finally, we illustrate our method using a real-world dataset on renal transplant patients.

Problem

• Improving dynamic survival prediction for patients with potential cure status
• Overcoming limitations of LOCF method in summarizing longitudinal covariate data
• Developing model-based landmarking approach for mixture cure survival models

Innovation

• Model-based landmarking integrates longitudinal mixed models
• Predicted random effects enhance Cox cure model covariates
• Sequential approach overcomes LOCF limitations in survival prediction