Nonlinear dynamics analysis of heart rate variability signals to detect sleep disordered breathing in children

Physics-Informed Transfer Learning to Enhance Sleep Staging

OBJECTIVE

At-home sleep staging using wearable medical sensors poses a viable alternative to in-hospital polysomnography due to its lower cost and lower disruption to the daily lives of patients, especially in the case of long-term monitoring. Machine learning with wearables however is difficult due to the paucity of data from wearable sensors, making automation a challenge. Transfer learning from hospital polysomnograms can boost performance, but is still hindered by differences between wearable and in-hospital EEG resulting in part from differing electrode placement. We improve transfer learning performance by using electrophysiological models of a human head to generate synthetic EEG resembling EEG from a wearable sensor.

METHODS

The data generation method utilizes Low-Resolution Electromagnetic Tomography Analysis (LORETA). Real EEG from standard in- hospital recordings is first mapped to point currents within the brain using LORETA, after which the point currents are used to estimate EEG that would have been recorded using a wearable sensor at any given point on the head.

RESULTS

Augmenting source datasets with synthetic data statistically significantly boosted accuracy on a wearable sleep staging task from 80.8% to 81.3% on average, depending on the transfer learning parameters and data sources.

CONCLUSION

Machine learning performance can be improved using data synthesized using physical models.

SIGNIFICANCE

Our approach represents a new form of transfer learning and demonstrates that incorporating domain knowledge of electrophysiological modeling can improve machine learning results for sleep staging tasks. We expect this approach to be particularly useful for EEG data which is hard to collect, or which is obtained using unusual electrode configurations.

Comparison of deep transfer learning algorithms and transferability measures for wearable sleep staging

Background

Obtaining medical data using wearable sensors is a potential replacement for in-hospital monitoring, but the lack of data for such sensors poses a challenge for development. One solution is using in-hospital recordings to boost performance via transfer learning. While there are many possible transfer learning algorithms, few have been tested in the domain of EEG-based sleep staging. Furthermore, there are few ways for determining which transfer learning method will work best besides exhaustive testing. Measures of transferability do exist, but are typically used for selection of pre-trained models rather than algorithms and few have been tested on medical signals. We tested several supervised transfer learning algorithms on a sleep staging task using a single channel of EEG (AF7-Fpz) captured from an in-home commercial system.

Results

Two neural networks—one bespoke and another state-of-art open-source architecture—were pre-trained on one of six source datasets comprising 11,561 subjects undergoing clinical polysomnograms (PSGs), then re-trained on a target dataset of 75 full-night recordings from 24 subjects. Several transferability measures were then tested to determine which is most effective for assessing performance on unseen target data. Performance on the target dataset was improved using transfer learning, with re-training the head layers being the most effective in the majority of cases (up to 63.9% of cases). Transferability measures generally provided significant correlations with accuracy (up to \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$r = -0.53$$\end{document}r=-0.53).

Conclusion

Re-training the head layers provided the largest performance boost. Transferability measures are useful indicators of transfer learning effectiveness.

Co-ordination of brain and heart oscillations during non-rapid eye movement sleep

Oscillatory activities of the brain and heart show a strong variation across wakefulness and sleep. Separate lines of research indicate that non‐rapid eye movement (NREM) sleep is characterised by electroencephalographic slow oscillations (SO), sleep spindles, and phase–amplitude coupling of these oscillations (SO–spindle coupling), as well as an increase in high‐frequency heart rate variability (HF‐HRV), reflecting enhanced parasympathetic activity. The present study aimed to investigate further the potential coordination between brain and heart oscillations during NREM sleep. Data were derived from one sleep laboratory night with polysomnographic monitoring in 45 healthy participants (22 male, 23 female; mean age 37 years). The associations between the strength (modulation index [MI]) and phase direction of SO–spindle coupling (circular measure) and HF‐HRV during NREM sleep were investigated using linear modelling. First, a significant SO–spindle coupling (MI) was observed for all participants during NREM sleep, with spindle peaks preferentially occurring during the SO upstate (phase direction). Second, linear model analyses of NREM sleep showed a significant relationship between the MI and HF‐HRV (F = 20.1, r² = 0.30, p < 0.001) and a tentative circular‐linear correlation between phase direction and HF‐HRV (F = 3.07, r² = 0.12, p = 0.056). We demonstrated a co‐ordination between SO–spindle phase–amplitude coupling and HF‐HRV during NREM sleep, presumably related to parallel central nervous and peripheral vegetative arousal systems regulation. Further investigating the fine‐graded co‐ordination of brain and heart oscillations might improve our understanding of the links between sleep and cardiovascular health.