March 3, 2026Open Access

Improving Survival Models in Health Care by Balancing Imbalanced Cohorts: A Novel Approach

Key Points

Model performance improves with targeted rebalancing of training data across risk strata.
Increased predictive reliability is crucial for effective clinical decision-making in oncology.
The approach is practical and model-agnostic, addressing imbalanced cohorts effectively.
It highlights the need for better methods in predictive reliability across various risk levels.

Abstract

Our findings suggest that survival model performance in observational oncology cohorts can be meaningfully improved through targeted rebalancing of the training data across prognostic risk strata. This approach offers a practical and model-agnostic complement to existing methods, especially in applications where predictive reliability across the full risk continuum is critical to downstream clinical decisions.

Improving Survival Models in Health Care by Balancing Imbalanced Cohorts: A Novel Approach

Key Points

Abstract

Cite This Study