Turning Silver into Gold: Domain Adaptation with Noisy Labels for Wearable Cardio-Respiratory Fitness Prediction

TL;DR

This paper introduces UDAMA, a novel domain adaptation model that leverages noisy wearable sensor data to improve the prediction of cardio-respiratory fitness, addressing the challenge of limited high-quality labels.

Contribution

The paper presents a new framework combining unsupervised domain adaptation and adversarial training to utilize noisy data for better clinical model performance.

Findings

Achieves a correlation of 0.665 in VO2max prediction.

Effectively leverages silver-standard data to enhance gold-standard model accuracy.

Demonstrates scalable fitness estimation using wearable sensors.

Abstract

Deep learning models have shown great promise in various healthcare applications. However, most models are developed and validated on small-scale datasets, as collecting high-quality (gold-standard) labels for health applications is often costly and time-consuming. As a result, these models may suffer from overfitting and not generalize well to unseen data. At the same time, an extensive amount of data with imprecise labels (silver-standard) is starting to be generally available, as collected from inexpensive wearables like accelerometers and electrocardiography sensors. These currently underutilized datasets and labels can be leveraged to produce more accurate clinical models. In this work, we propose UDAMA, a novel model with two key components: Unsupervised Domain Adaptation and Multi-discriminator Adversarial training, which leverage noisy data from source domain (the silver-standard dataset) to improve gold-standard modeling. We validate our framework on the challenging task of predicting lab-measured maximal oxygen consumption (VO$_{2}$max), the benchmark metric of cardio-respiratory fitness, using free-living wearable sensor data from two cohort studies as inputs. Our experiments show that the proposed framework achieves the best performance of corr = 0.665 $\pm$ 0.04, paving the way for accurate fitness estimation at scale.