September 03, 2026 Webinar
Correcting Systematic Prediction Bias in Biological Age Estimation and the Resulting Bias in Inference with Predicted Outcomes
Shuo Chen, PhD
Abstract:
Machine learning (ML)– and artificial intelligence (AI)–based aging clocks are increasingly used to quantify physiological and molecular aging from omics and medical imaging data as distinct from chronological age. Here, we characterize a fundamental but underappreciated statistical limitation of commonly used ML/AI regression models: systematic prediction bias and its propagation to downstream association estimates. This issue can be more challenging when the true biological age is latent during ML/AI model training. We demonstrate that systematic prediction bias can distort, and in some cases reverse, downstream association analyses that use aging clocks as ML/AI-predicted outcomes. For example, it can produce spurious associations suggesting that older predicted brain age is linked to better cognitive performance, or that older epigenetic age is associated with better kidney function. To address this problem, we introduce a principled and broadly applicable ML/AI regression framework based on constrained optimization, yielding better calibrated aging-clock estimates and valid downstream inference.
Short Bio:
Shuo is a MPower professor of biostatistics from U of Maryland School of Medicine, with several secondary appointments at U of Maryland, School of Public Health, College of Computer, Mathematical, and Natural Sciences, Institute of Health Computing, and Maryland Psychiatric Research Center and others. Shuo obtained his Ph.D. from Emory University and has a broad interest in biostatistics and other quantitative methods and their applications in biomedical research.
Hope to see you at the webinar!