FairTune: A Bias-Aware Fine-Tuning Framework Towards Fair Heart Rate Prediction from PPG

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Panchumarthi, Lovely Yeswanth, Kataria, Saurabh, Wu, Yi, Hu, Xiao, Fedorov, Alex, Kwak, Hyunjung Gloria
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912595637698560
author Panchumarthi, Lovely Yeswanth
Kataria, Saurabh
Wu, Yi
Hu, Xiao
Fedorov, Alex
Kwak, Hyunjung Gloria
author_facet Panchumarthi, Lovely Yeswanth
Kataria, Saurabh
Wu, Yi
Hu, Xiao
Fedorov, Alex
Kwak, Hyunjung Gloria
contents Foundation models pretrained on physiological data such as photoplethysmography (PPG) signals are increasingly used to improve heart rate (HR) prediction across diverse settings. Fine-tuning these models for local deployment is often seen as a practical and scalable strategy. However, its impact on demographic fairness particularly under domain shifts remains underexplored. We fine-tune PPG-GPT a transformer-based foundation model pretrained on intensive care unit (ICU) data across three heterogeneous datasets (ICU, wearable, smartphone) and systematically evaluate the effects on HR prediction accuracy and gender fairness. While fine-tuning substantially reduces mean absolute error (up to 80%), it can simultaneously widen fairness gaps, especially in larger models and under significant distributional characteristics shifts. To address this, we introduce FairTune, a bias-aware fine-tuning framework in which we benchmark three mitigation strategies: class weighting based on inverse group frequency (IF), Group Distributionally Robust Optimization (GroupDRO), and adversarial debiasing (ADV). We find that IF and GroupDRO significantly reduce fairness gaps without compromising accuracy, with effectiveness varying by deployment domain. Representation analyses further reveal that mitigation techniques reshape internal embeddings to reduce demographic clustering. Our findings highlight that fairness does not emerge as a natural byproduct of fine-tuning and that explicit mitigation is essential for equitable deployment of physiological foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16491
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FairTune: A Bias-Aware Fine-Tuning Framework Towards Fair Heart Rate Prediction from PPG
Panchumarthi, Lovely Yeswanth
Kataria, Saurabh
Wu, Yi
Hu, Xiao
Fedorov, Alex
Kwak, Hyunjung Gloria
Machine Learning
Computational Engineering, Finance, and Science
Foundation models pretrained on physiological data such as photoplethysmography (PPG) signals are increasingly used to improve heart rate (HR) prediction across diverse settings. Fine-tuning these models for local deployment is often seen as a practical and scalable strategy. However, its impact on demographic fairness particularly under domain shifts remains underexplored. We fine-tune PPG-GPT a transformer-based foundation model pretrained on intensive care unit (ICU) data across three heterogeneous datasets (ICU, wearable, smartphone) and systematically evaluate the effects on HR prediction accuracy and gender fairness. While fine-tuning substantially reduces mean absolute error (up to 80%), it can simultaneously widen fairness gaps, especially in larger models and under significant distributional characteristics shifts. To address this, we introduce FairTune, a bias-aware fine-tuning framework in which we benchmark three mitigation strategies: class weighting based on inverse group frequency (IF), Group Distributionally Robust Optimization (GroupDRO), and adversarial debiasing (ADV). We find that IF and GroupDRO significantly reduce fairness gaps without compromising accuracy, with effectiveness varying by deployment domain. Representation analyses further reveal that mitigation techniques reshape internal embeddings to reduce demographic clustering. Our findings highlight that fairness does not emerge as a natural byproduct of fine-tuning and that explicit mitigation is essential for equitable deployment of physiological foundation models.
title FairTune: A Bias-Aware Fine-Tuning Framework Towards Fair Heart Rate Prediction from PPG
topic Machine Learning
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2509.16491