Weighted Temporal Decay Loss for Learning Wearable PPG Data with Sparse Clinical Labels

TL;DR

This paper introduces a weighted temporal decay loss function for training wearable PPG-based health models, improving accuracy with sparse labels and providing interpretability of biomarker temporal sensitivity.

Contribution

It proposes a biomarker-specific decay weighting strategy for loss functions, enhancing PPG health monitoring models trained with limited clinical labels.

Findings

Achieves higher AUPRC scores on smartwatch PPG data.

Linear decay function is most robust across biomarkers.

Decay rates offer interpretable insights into biomarker temporal relevance.

Abstract

Advances in wearable computing and AI have increased interest in leveraging PPG for health monitoring over the past decade. One of the biggest challenges in developing health algorithms based on such biosignals is the sparsity of clinical labels, which makes biosignals temporally distant from lab draws less reliable for supervision. To address this problem, we introduce a simple training strategy that learns a biomarker-specific decay of sample weight over the time gap between a segment and its ground truth label and uses this weight in the loss with a regularizer to prevent trivial solutions. On smartwatch PPG from 450 participants across 10 biomarkers, the approach improves over baselines. In the subject-wise setting, the proposed approach averages 0.715 AUPRC, compared to 0.674 for a fine-tuned self-supervised baseline and 0.626 for a feature-based Random Forest. A comparison of four decay families shows that a simple linear decay function is most robust on average. Beyond accuracy, the learned decay rates summarize how quickly each biomarker's PPG evidence becomes stale, providing an interpretable view of temporal sensitivity.