PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputation
This addresses a critical data gap for researchers and practitioners in mobile health, enabling better imputation methods for pulsative signals, though it is incremental as it builds on existing imputation literature by focusing on a specific signal type.
The paper tackles the problem of missing data in pulsative physiological signals from mobile health wearables by introducing PulseImpute, a benchmark task with realistic missingness models and baselines, resulting in the first large-scale challenge for this domain.
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.