Generalizable deep learning for photoplethysmography-based blood pressure estimation -- A Benchmarking Study

TL;DR

This benchmarking study evaluates the generalizability of deep learning models for PPG-based blood pressure estimation across multiple datasets, highlighting the challenges and proposing simple domain adaptation methods to improve out-of-distribution performance.

Contribution

The paper provides a comprehensive benchmarking of five deep learning models on in-distribution and out-of-distribution datasets, emphasizing the importance of generalization and proposing domain adaptation techniques.

Findings

Best model achieved MAEs of 9.4/6.0 mmHg in-distribution

Out-of-distribution MAEs ranged from 15.0 to 25.1 mmHg (SBP)

Sample-based domain adaptation improved performance

Abstract

Photoplethysmography (PPG)-based blood pressure (BP) estimation represents a promising alternative to cuff-based BP measurements. Recently, an increasing number of deep learning models have been proposed to infer BP from the raw PPG waveform. However, these models have been predominantly evaluated on in-distribution test sets, which immediately raises the question of the generalizability of these models to external datasets. To investigate this question, we trained five deep learning models on the recently released PulseDB dataset, provided in-distribution benchmarking results on this dataset, and then assessed out-of-distribution performance on several external datasets. The best model (XResNet1d101) achieved in-distribution MAEs of 9.4 and 6.0 mmHg for systolic and diastolic BP respectively on PulseDB (with subject-specific calibration), and 14.0 and 8.5 mmHg respectively without calibration. Equivalent MAEs on external test datasets without calibration ranged from 15.0 to 25.1 mmHg (SBP) and 7.0 to 10.4 mmHg (DBP). Our results indicate that the performance is strongly influenced by the differences in BP distributions between datasets. We investigated a simple way of improving performance through sample-based domain adaptation and put forward recommendations for training models with good generalization properties. With this work, we hope to educate more researchers for the importance and challenges of out-of-distribution generalization.