Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 May 13;42(4):10.1088/1361-6579/abf1b0.
doi: 10.1088/1361-6579/abf1b0.

Transfer learning from ECG to PPG for improved sleep staging from wrist-worn wearables

Qiao Li  1 , Qichen Li  1 , Ayse S Cakmak  1   2 , Giulia Da Poian  1   3 , Donald L Bliwise  4 , Viola Vaccarino  5 , Amit J Shah  5 , Gari D Clifford  1   6
Affiliations

Transfer learning from ECG to PPG for improved sleep staging from wrist-worn wearables

Qiao Li et al. Physiol Meas. .

Abstract

Objective.To develop a sleep staging method from wrist-worn accelerometry and the photoplethysmogram (PPG) by leveraging transfer learning from a large electrocardiogram (ECG) database.Approach.In previous work, we developed a deep convolutional neural network for sleep staging from ECG using the cross-spectrogram of ECG-derived respiration and instantaneous beat intervals, heart rate variability metrics, spectral characteristics, and signal quality measures derived from 5793 subjects in Sleep Heart Health Study (SHHS). We updated the weights of this model by transfer learning using PPG data derived from the Empatica E4 wristwatch worn by 105 subjects in the 'Emory Twin Study Follow-up' (ETSF) database, for whom overnight polysomnographic (PSG) scoring was available. The relative performance of PPG, and actigraphy (Act), plus combinations of these two signals, with and without transfer learning was assessed.Main results.The performance of our model with transfer learning showed higher accuracy (1-9 percentage points) and Cohen's Kappa (0.01-0.13) than those without transfer learning for every classification category. Statistically significant, though relatively small, incremental differences in accuracy occurred for every classification category as tested with the McNemar test. The out-of-sample classification performance using features from PPG and actigraphy for four-class classification was Accuracy (Acc) = 68.62% and Kappa = 0.44. For two-class classification, the performance was Acc = 81.49% and Kappa = 0.58.Significance.We proposed a combined PPG and actigraphy-based sleep stage classification approach using transfer learning from a large ECG sleep database. Results demonstrate that the transfer learning approach improves estimates of sleep state. The use of automated beat detectors and quality metrics means human over-reading is not required, and the approach can be scaled for large cross-sectional or longitudinal studies using wrist-worn devices for sleep staging.

Keywords: electrocardiogram; photoplethysmogram; sleep stage classification; transfer learning; wrist-worn devices.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
The 10-fold cross-validation approach to train, validate and test the transfer learning model.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Aktaruzzaman M, Migliorini M, Tenhunen M, Himanen S-L, Bianchi AM and Sassi R (2015). The addition of entropy-based regularity parameters improves sleep stage classification based on heart rate variability, Medical & biological engineering & computing 53(5): 415–425. - PubMed
    1. Aktaruzzaman M, Rivolta MW, Karmacharya R, Scarabottolo N, Pugnetti L, Garegnani M, Bovi G, Scalera G, Ferrarin M and Sassi R (2017). Performance comparison between wrist and chest actigraphy in combination with heart rate variability for sleep classification, Computers in Biology and Medicine 89: 212–221. - PubMed
    1. Beattie Z, Oyang Y, Statan A, Ghoreyshi A, Pantelopoulos A, Russell A and Heneghan C (2017). Estimation of sleep stages in a healthy adult population from optical plethysmography and accelerometer signals, Physiological measurement 38(11): 1968–1979. - PubMed
    1. Berry KJ and Mielke PW Jr (1988). A generalization of cohen’s kappa agreement measure to interval measurement and multiple raters, Educational and Psychological Measurement 48(4): 921–933.
    1. Borazio M, Berlin E, Kücükyildiz N, Scholl P and Van Laerhoven K (2014). Towards benchmarked sleep detection with wrist-worn sensing units, IEEE International Conference on Healthcare Informatics, IEEE, Verona, Italy, pp. 125–134.

Publication types

LinkOut - more resources