PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputation
Maxwell A. Xu1, Alexander Moreno1,2, Supriya Nagesh1, V. Burak Aydemir1, David W. Wetter3, Santosh Kumar4, James M. Rehg1
1 Georgia Tech, 2 Luminous Computing, 3 University of Utah, 4 University of Memphis


Paper
Code
Poster
Slides


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.


Challenge Information

Standard
Imputation
Datasets
Existing
mHealth
Datasets
ECG
Imputation
Datasets
Our
PulseImpute
Challenge
mHealth
Pulsative Signals
Publicly
Available Data
Realistic
Missingness
Directly Evals
Missingness
Comprehensive
Benchmarks
Downstream
Tasks
Prior Work compared to PulseImpute Challenge

PulseImpute
Tasks
Signal Type
and Origin
Total Size Length Missingness Downstream
Task
ECG
Imputation
and Cardiac
Multi-label
Classification
ECG Signals
from PTB-XL
21,837
Signals from
18,885
Patients
10 Sec at
100 Hz
Simulated
Extended
Loss,
Simulated
Transient
Loss
Classifying
Form,
Rhythm, or
Diagnosis
Labels
(Macro-AUC)
ECG
Imputation
and
Heartbeat
Detection
ECG Signals
Curated from
MIMIC-III
Waveform
440,953
Signals from
32,930
Patients
5 Min at
100 Hz
102,201
Extracted
ECG mHealth
Field Study
Patterns
Detecting
R Peaks
(F1-Score)
PPG
Imputation
and
Heartbeat
Detection
PPG Signals
Curated from
MIMIC-III
Waveform
151,738
Signals from
18,210
Patients
5 Min at
100 Hz
425
Extracted
PPG mHealth
Field Study
Patterns
Detecting
Systolic Peaks
(F1-Score)
Details on Specific PulseImpute Challenge Tasks





Our Bottleneck Dilated Convolution (BDC) Transformer

Self-attention's pairwise comparisons can compare waveshapes across quasiperiods.
We can effeciently increase local context
via the BDC self-attention module.


BDC exploits quasiperiodicity by attending to similar shapes.


Results



Conclusion

PulseImpute is a novel imputation challenge for pulsative mHealth signals. Prior work time-series imputation work fails in our setting, but our BDC Transformer demonstrates the potential of exploiting signal structure. Pulsative signal imputation over long gaps as well as reconstruction of features tied to Diagnosis are key unsolved mHealth challenges, and we hope that our challenge can drive future work in this critical and unique challenge.


Citation

@inproceedings{xupulseimpute,
  title={PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputation},
  author={Xu, Maxwell and Moreno, Alexander and Nagesh, Supriya and Aydemir, Varol Burak and Wetter, David W and Kumar, Santosh and Rehg, James Matthew},
  booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track}
}