Causal Analysis of Physiological Sleep Data Using Granger Causality and Score-Based Structure Learning
Abstract
:1. Introduction
1.1. Granger Causality
1.2. Optimisation Method (DYNOTEARS)
2. Materials and Methods
2.1. Data
2.2. Granger Causality
2.2.1. Windowing
2.2.2. Model Order Selection
2.3. DYNOTEARS
Selection of Hyperparameters
2.4. Comparison with Underlying Features
3. Results
3.1. Overall Graph Structure
3.2. Impact of Waist Girth
4. Discussion
4.1. Comparison of Methods
4.2. Limitations
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
AIC | Akaike Information Criterion |
AICc | Corrected Akaike Information Criterion |
CPAP | Continuous positive air pressure |
DBN | Dynamic Bayesian network |
(MV)GC | (Multivariate) Granger causality |
NSRR | National Sleep Research Resource |
VAR | Vector autoregression |
WSC | Wisconsin Sleep Cohort |
References
- Punjabi, N.M. The epidemiology of adult obstructive sleep apnea. Proc. Am. Thorac. Soc. 2008, 5, 136–143. [Google Scholar] [CrossRef] [PubMed]
- Rundo, J.V.; Downey, R., III. Polysomnography. Handb. Clin. Neurol. 2019, 160, 381–392. [Google Scholar] [PubMed]
- Pearl, J.; Glymour, M.; Jewell, N.P. Causal Inference in Statistics: A Primer; John Wiley & Sons: Hoboken, NJ, USA, 2016. [Google Scholar]
- Pearl, J. Causality; Cambridge University Press: Cambridge, UK, 2009. [Google Scholar]
- Granger, C.W. Investigating causal relations by econometric models and cross-spectral methods. Econom. J. Econom. Soc. 1969, 37, 424–438. [Google Scholar] [CrossRef]
- Barnett, L.; Seth, A.K. The MVGC multivariate Granger causality toolbox: A new approach to Granger-causal inference. J. Neurosci. Methods 2014, 223, 50–68. [Google Scholar] [CrossRef]
- Salem, V.; Silva, L.D.; Suba, K.; Georgiadou, E.; Neda Mousavy Gharavy, S.; Akhtar, N.; Martin-Alonso, A.; Gaboriau, D.C.; Rothery, S.M.; Stylianides, T.; et al. Leader β-cells coordinate Ca2+ dynamics across pancreatic islets in vivo. Nat. Metab. 2019, 1, 615–629. [Google Scholar] [CrossRef]
- Orjuela-Cañón, A.D.; Cerquera, A.; Freund, J.A.; Juliá-Serdá, G.; Ravelo-García, A.G. Sleep apnea: Tracking effects of a first session of CPAP therapy by means of Granger causality. Comput. Methods Programs Biomed. 2020, 187, 105235. [Google Scholar] [CrossRef]
- Benjamini, Y.; Yekutieli, D. The control of the false discovery rate in multiple testing under dependency. Ann. Stat. 2001, 29, 1165–1188. [Google Scholar] [CrossRef]
- Faes, L.; Marinazzo, D.; Jurysta, F.; Nollo, G. Granger causality analysis of sleep brain-heart interactions. In Proceedings of the 2014 8th Conference of the European Study Group on Cardiovascular Oscillations (ESGCO), Trento, Italy, 25–28 May 2014; pp. 5–6. [Google Scholar]
- Günther, M.; Kantelhardt, J.W.; Bartsch, R.P. The reconstruction of causal networks in physiology. Front. Netw. Physiol. 2022, 2, 893743. [Google Scholar] [CrossRef]
- Pizzi, R.; Rutigliano, T.; Musumeci, M.; Pregnolato, M. Using Granger Causality to assess the interaction between brain areas during different consciousness states. Int. J. Biol. Biomed. Eng. 2016, 10, 241–247. [Google Scholar]
- Abdalbari, H.; Durrani, M.; Pancholi, S.; Patel, N.; Nasuto, S.J.; Nicolaou, N. Brain and brain-heart Granger causality during wakefulness and sleep. Front. Neurosci. 2022, 16, 927111. [Google Scholar] [CrossRef]
- Zheng, X.; Aragam, B.; Ravikumar, P.K.; Xing, E.P. Dags with NO TEARS: Continuous optimization for structure learning. Adv. Neural Inf. Process. Syst. 2018, 31, 1–12. [Google Scholar]
- Pamfil, R.; Sriwattanaworachai, N.; Desai, S.; Pilgerstorfer, P.; Georgatzis, K.; Beaumont, P.; Aragam, B. DYNOTEARS: Structure learning from time-series data. In Proceedings of the International Conference on Artificial Intelligence and Statistics, Online, 26–28 August 2020; pp. 1595–1605. [Google Scholar]
- Valentin, S.; Bramley, N.R.; Lucas, C.G. Discovering Common Hidden Causes in Sequences of Events. Comput. Brain Behav. 2022, 6, 377–399. [Google Scholar] [CrossRef]
- Howard, R.P.M.; Kunze, L. Evaluating temporal observation-based causal discovery techniques applied to road driver behaviour. In Proceedings of the Conference on Causal Learning and Reasoning, Tübingen, Germany, 11–14 April 2023; pp. 473–498. [Google Scholar]
- Young, T.; Palta, M.; Dempsey, J.; Peppard, P.E.; Nieto, F.J.; Hla, K.M. Burden of sleep apnea: Rationale, design, and major findings of the Wisconsin Sleep Cohort study. WMJ Off. Publ. State Med. Soc. Wis. 2009, 108, 246. [Google Scholar]
- Zhang, G.Q.; Cui, L.; Mueller, R.; Tao, S.; Kim, M.; Rueschman, M.; Mariani, S.; Mobley, D.; Redline, S. The National Sleep Research Resource: Towards a sleep data commons. J. Am. Med. Inform. Assoc. 2018, 25, 1351–1358. [Google Scholar] [CrossRef] [PubMed]
- National Sleep Research Resource. Montage and Sampling Rate Information. Available online: https://sleepdata.org/datasets/wsc/pages/montage-and-sampling-rate-information.md (accessed on 17 April 2023).
- Lütkepohl, H. New Introduction to Multiple Time Series Analysis; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2005. [Google Scholar]
- Textor, J.; Van der Zander, B.; Gilthorpe, M.S.; Liśkiewicz, M.; Ellison, G.T. Robust causal inference using directed acyclic graphs: The R package ‘dagitty’. Int. J. Epidemiol. 2016, 45, 1887–1894. [Google Scholar] [CrossRef] [PubMed]
- Ramesh, J.; Keeran, N.; Sagahyroon, A.; Aloul, F. Towards validating the effectiveness of obstructive sleep apnea classification from electronic health records using machine learning. Healthcare 2021, 9, 1450. [Google Scholar] [CrossRef]
- Olesen, A.N.; Jørgen Jennum, P.; Mignot, E.; Sorensen, H.B.D. Automatic sleep stage classification with deep residual networks in a mixed-cohort setting. Sleep 2021, 44, zsaa161. [Google Scholar] [CrossRef]
- Dean, E. Effect of body position on pulmonary function. Phys. Ther. 1985, 65, 613–618. [Google Scholar] [CrossRef]
- Nakano, H.; Ikeda, T.; Hayashi, M.; Ohshima, E.; Onizuka, A. Effects of Body Position on Snoring in Apneic and Nonapneic Snorers. Sleep 2003, 26, 169–172. [Google Scholar] [CrossRef]
- Koutsourelakis, I.; Perraki, E.; Zakynthinos, G.; Minaritzoglou, A.; Vagiakis, E.; Zakynthinos, S. Clinical and polysomnographic determinants of snoring. J. Sleep Res. 2012, 21, 693–699. [Google Scholar] [CrossRef]
- Lin, A.; Liu, K.K.; Bartsch, R.P.; Ivanov, P.C. Delay-correlation landscape reveals characteristic time delays of brain rhythms and heart interactions. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 2016, 374, 20150182. [Google Scholar] [CrossRef]
Abbreviation | Name in Dataset | Definition |
---|---|---|
EOG_1 | E1 | Left electrooculogram (EOG) |
EOG_2 | E2 | Right electrooculogram (EOG) |
EEG_LC | C3_M2 | Left central electroencephalogram (EEG) |
EEG_LO | O1_M2 | Left occipital electroencephalogram (EEG) |
EMG_Leg | lleg_r | Linked left and right leg electromyogram (EMG) |
Snore | snore | Snore |
ECG | ECG | Electrocardiogram (ECG) |
Nasal_Pressure | nas_pres | Nasal pressure |
Position | position | Position |
Blood_Oxygen | spo2 | Blood oxygen |
2000–2009 | Post–2009 | |||
---|---|---|---|---|
Variable | Sampling Rate (Hz) | Hardware Filter (Hz) | Sampling Rate (Hz) | Hardware Filter (Hz) |
EOG_1 | 100 | Low Pass 30 | 200 | Low Pass 35 |
EOG_2 | 100 | Low Pass 30 | 200 | Low Pass 35 |
EEG_LC | 100 | Low Pass 30 | 200 | Low Pass 35 |
EEG_LO | 100 | Low Pass 30 | 200 | Low Pass 35 |
EMG_Leg | 100 | Low Pass 30 | 200 | Low Pass 70 |
Snore | 100 | Low Pass 30 | 200 | Low Pass 70 |
ECG | 100 | Low Pass 30 | 200 | Low Pass 35 |
Nasal_Pressure | 100 | Low Pass 30 | 200 | Low Pass 15 |
Position | 100 | - | 200 | - |
Blood_Oxygen | 100 | - | 200 | - |
Variable | Category | Frequency | Percent |
---|---|---|---|
Sex | Male | 98 | 49.0% |
Female | 102 | 51.0% | |
Age | 30 < x ≤ 40 | 2 | 1.0% |
40 < x ≤ 50 | 31 | 15.5% | |
50 < x ≤ 60 | 83 | 41.5% | |
60 < x ≤ 70 | 71 | 35.5% | |
70 < x ≤ 80 | 13 | 6.5% | |
BMI | 10 < x ≤ 20 | 7 | 3.5% |
20 < x ≤ 30 | 93 | 46.5% | |
30 < x ≤ 40 | 73 | 36.5% | |
40 < x ≤ 50 | 17 | 8.5% | |
50 < x ≤ 60 | 9 | 4.5% | |
60 < x ≤ 70 | 1 | 0.5% | |
Race | Asian | 1 | 0.5% |
Black | 3 | 1.5% | |
Hispanic | 1 | 0.5% | |
Native American | 0 | 0.0% | |
White | 195 | 97.5% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Thomas, A.; Niranjan, M.; Legg, J. Causal Analysis of Physiological Sleep Data Using Granger Causality and Score-Based Structure Learning. Sensors 2023, 23, 9455. https://doi.org/10.3390/s23239455
Thomas A, Niranjan M, Legg J. Causal Analysis of Physiological Sleep Data Using Granger Causality and Score-Based Structure Learning. Sensors. 2023; 23(23):9455. https://doi.org/10.3390/s23239455
Chicago/Turabian StyleThomas, Alex, Mahesan Niranjan, and Julian Legg. 2023. "Causal Analysis of Physiological Sleep Data Using Granger Causality and Score-Based Structure Learning" Sensors 23, no. 23: 9455. https://doi.org/10.3390/s23239455