PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputation

TL;DR

PulseImpute introduces a new benchmark for imputing missing data in pulsative physiological signals from wearable sensors, addressing a key challenge in mobile health monitoring and enabling better health interventions.

Contribution

It presents the first large-scale pulsative signal imputation benchmark with realistic missingness models, baselines, and a novel transformer-based architecture.

Findings

Baseline models perform variably on pulsative signals.

The transformer-based model exploits pulsative signal structure effectively.

PulseImpute facilitates progress in pulsative signal imputation research.

Abstract

The promise of Mobile Health (mHealth) is the ability to use wearable sensors to monitor participant physiology at high frequencies during daily life to enable temporally-precise health interventions. However, a major challenge is frequent missing data. Despite a rich imputation literature, existing techniques are ineffective for the pulsative signals which comprise many mHealth applications, and a lack of available datasets has stymied progress. We address this gap with PulseImpute, the first large-scale pulsative signal imputation challenge which includes realistic mHealth missingness models, an extensive set of baselines, and clinically-relevant downstream tasks. Our baseline models include a novel transformer-based architecture designed to exploit the structure of pulsative signals. We hope that PulseImpute will enable the ML community to tackle this significant and challenging task.