Is It You or Your Environment? A Bayesian Inference Framework for Genomically-Anchored Personalized Physiological Interpretation

The paper introduces a Bayesian inference framework that utilizes an individual's genomic profile as a personalized anchor to address the cold-start problem in personalized health AI systems. By initializing a Bayesian belief state based on genomic data, the model distinguishes between environmental and constitutional physiological variations, allowing for more accurate interpretations of physiological measurements over time. This approach, which incorporates dynamic decay of priors and evidence-graded genomic anchors, is significant for practitioners as it enhances the reliability of physiological interpretations in health AI by leveraging genetic information from the outset, reducing reliance on extensive behavioral data.