Population-aware Hierarchical Bayesian Domain Adaptation

TL;DR

This paper introduces a population-aware hierarchical Bayesian domain adaptation method that leverages population attributes and multiple data sources to improve health prediction accuracy across diverse datasets.

Contribution

It presents a novel multi-source hierarchical Bayesian framework that incorporates population attributes into domain adaptation for health data prediction.

Findings

Enhanced prediction accuracy with largely unlabelled target data

Effective utilization of population and domain invariant information

Improved generalization across diverse health datasets

Abstract

Population attributes are essential in health for understanding who the data represents and precision medicine efforts. Even within disease infection labels, patients can exhibit significant variability; "fever" may mean something different when reported in a doctor's office versus from an online app, precluding directly learning across different datasets for the same prediction task. This problem falls into the domain adaptation paradigm. However, research in this area has to-date not considered who generates the data; symptoms reported by a woman versus a man, for example, could also have different implications. We propose a novel population-aware domain adaptation approach by formulating the domain adaptation task as a multi-source hierarchical Bayesian framework. The model improves prediction in the case of largely unlabelled target data by harnessing both domain and population invariant information.