Robust Mitigation of Age-Dependent Confounding Effects via Sample-Difficulty Decorrelation
Quick Take
A new framework mitigates age-dependent confounding in medical image classification without losing diagnostic information.
Key Points
- Targets spurious age-linked trends instead of enforcing age invariance.
- Uses Huber weighted affinity weights for robust decorrelation.
- Demonstrated effectiveness across two radiology datasets.
📖 Reader Mode
~2 min readAbstract:Age dependent performance disparities in medical image classification often arise because age acts as a confounder, linking imaging morphology with disease prevalence. In practice, disparities can manifest as overdiagnosis at ages where disease prevalence is higher and underdiagnosis at ages where prevalence is lower, and can worsen under train test shifts in the age distribution. Conventional mitigation approaches that enforce strict age invariance may suppress diagnostically meaningful information encoded in age. We therefore propose a robust framework that mitigates the effects of age-dependent confounding by targeting spurious age linked trends rather than enforcing invariance. Following a warm-up phase, we characterize sample difficulty and model its age-dependent trends in a label-conditioned manner. We decorrelate age from dominant age difficulty trends using robust, Huber weighted affinity weights, attenuating confounding-driven shortcuts while preserving clinically meaningful, nonlinear age information. We further introduce an Age Coverage Score that scales the decorrelation penalty by minibatch age variance to ensure stable optimization under limited age diversity. Across two radiology datasets, our approach reduces age dependent true and false positive disparities with minimal AUC impact and remains robust to increasing train test age distribution shifts.
| Comments: | 10 Pages, 3 Figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.19230 [cs.CV] |
| (or arXiv:2605.19230v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.19230 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: NIkhil Cherian Kurian [view email]
[v1]
Tue, 19 May 2026 01:01:40 UTC (1,354 KB)
— Originally published at arxiv.org
More from arXiv cs.CV
See more →GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
GeoSym127K introduces a scalable neuro-symbolic framework for enhanced geometric reasoning in multimodal models.