MODELING OF CIRCADIAN RHYTHMS USING HYBRID TIME SERIES MODEL, POLYNOMIAL REGRESSION, NNAR, AND BAYESIAN-ARIMA TIME SERIES FORECASTING METHODS
Keywords:
circadian rhythm, hybrid model, polynomial regression, NNAR, Bayesian ARIMA, predictive accuracyDOI:
https://doi.org/10.17654/0973514325021Abstract
Circadian rhythms, characterized by their high periodicity, are ideally suited for time series statistical modeling. This study comparatively analyzes four approaches: TBATS (a hybrid time series model), polynomial regression, neural network autoregression, and a Bayesian formulation of the (autoregressive integrated moving average) ARIMA model for modeling and forecasting 24-hour core body temperature fluctuations. Hourly temperature data were evaluated using root mean square error (RMSE) as the primary accuracy criterion. The hybrid model (TBATS), which incorporates Box-Cox transformation, trend smoothing, trigonometric seasonal decomposition, and (autoregressive moving average) ARMA errors, captured long-term rhythmicity and short-term autocorrelation with high fidelity. A fourth-order polynomial regression provided a flexible exploratory fit but showed signs of overfitting, especially near temporal extremes. The Bayesian ARIMA model accounted for the autocorrelation structure while providing credible intervals for parameter uncertainty, but struggled to effectively capture circadian periodicity. NNAR and TBATS outperformed both alternatives in terms of predictive performance and fit to the biological characteristics of the data. Incorporating Bayesian inference improved the model’s interpretability and enabled the integration of prior knowledge, making it particularly valuable in clinical and experimental settings. These results highlight the need to adapt the model structure to the characteristics of biological time series and support the use of hybrid and probabilistic models in circadian rhythm research. Future studies should explore the model’s generalizability across multi-day cycles, evaluate performance in populations with circadian disruptions, and consider the inclusion of covariates such as light exposure or sleep-wake cycles to improve biological interpretability and prediction accuracy.
Received: May 10, 2025
Accepted: June 14, 2025
References
T. Akerstedt, Shift work and disturbed sleep/wakefulness, Occupational Medicine 53(2) (2003), 89-94. https://doi.org/10.1093/occmed/kqg046.
A. M. Almarashi and K. Khan, Bayesian structural time series, Nanoscience and Nanotechnology Letters 12(1) (2020), 54-61.
A. M. Almarashi, R. S. Alqurashi, A. F. Alshammari, A. H. Almalki and K. Khan, Modelling mean and volatility of cement stocks: a case study of Saudi cement company, Adv. Appl. Stat. 91(1) (2024), 99-109.
I. Bandin et al., Time series analysis of circadian rhythms, Chronobiology International 32(4) (2015), 411-427.
G. E. P. Box and G. M. Jenkins, Time Series Analysis: Forecasting and Control, Holden-Day, 1976.
S. Chattopadhyay et al., Machine learning for circadian rhythm analysis: a review, Bioinformatics Advances 1(1) (2021), 1-12.
https://doi.org/10.1093/bioadv/vbab012.
X. Yao, B. L. Heidebrecht, J. Chen and J. J. Tyson, Mathematical analysis of robustness of oscillations in models of the mammalian circadian clock, PLoS Computational Biology 18(3) (2022), e1008340.
A. Christen et al., Bayesforecast: Bayesian Time Series Forecasting with Stan [R package], 2023. Retrieved from https://cran.r-project.org/packagebayesforecast.
G. Cornelissen, Cosinor-based rhythmometry, Theoretical Biology and Medical Modelling 11(1) (2014), 1-24.
A. M. De Livera et al., Forecasting time series with complex seasonal patterns using exponential smoothing, J. Amer. Statist. Assoc. 106(496) (2011), 1513-1527.
C. Dibner et al., Circadian rhythms in health and disease: molecular mechanisms and therapeutic potential, Nature Reviews Endocrinology 19(2) (2023), 123-135. https://doi.org/10.1038/s41574-022-00761-9.
J. F. Duffy, K. M. Zitting and C. A. Czeisler, The case for monitoring sleep and circadian rhythms in clinical research, Clinical and Translational Medicine (2015). doi:10.1186/s40169-015-0040-4.
A. Gelman, J. B. Carlin, H. S. Stern, D. B. Dunson, A. Vehtari and D. B. Rubin, Bayesian Data Analysis, 3rd ed., Chapman and Hall/CRC, 2013.
J. Geweke, Bayesian comparison of econometric models, J. Econometrics 68(1) (1994), 1-36.
C. F. Gauss, Theory of the Motion of the Heavenly Bodies Moving about the Sun in Conic Sections (trans. C. H. Davis), Dover Publications, New York (Original work published 1809), 1963.
R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed., OTexts, 2021.
A. Kumar and R. Patel, Interpretability challenges in neural networks for clinical time series, Journal of Medical Systems 47(5) (2023), 1-12.
H. Lee and S. Kim, Neural networks for sleep-wake cycle prediction, Sleep Medicine 89 (2023), 45-53.
A.-M. Legendre, Nouvelles methodes pour la determination des orbites des cometes, F. Didot, Paris, 1805.
X. Li et al., Hybrid TBATS-LSTM for multiday temperature forecasting, IEEE Journal of Biomedical and Health Informatics 26(8) (2022), 3901-3910.
E. N. C. Manoogian et al., Circadian rhythms, time-restricted feeding, and precision health, Science 378(6625) (2022), 1190-1197.
https://doi.org/10.1126/science.abo3509.
D. C. Montgomery, E. A. Peck and G. G. Vining, Introduction to Linear Regression Analysis, 5th ed., Wiley, 2012.
M. C. Moore-Ede et al., The Clocks That Time Us, Harvard University Press, 1982.
T. Nguyen et al., Challenges in circadian rhythm modeling, Frontiers in Physiology 14 (2023), 1122334.
C. Perez-Vega, R. A. Domingo, S. Tripathi, A. Ramos-Fresnedo, S. Kashyap, A. Quinones-Hinojosa and R. G. Tawk, Influence of glucose levels on clinical outcome after mechanical thrombectomy for large-vessel occlusion: a systematic review and meta-analysis, Journal of Neurointerventional Surgery 14(1) (2022). neurintsurg-2021-017771. Doi: 10.1136/neurintsurg-2021-017771.
C. S. Pittendrigh, Temporal organization: reflections of a Darwinian clock-watcher, Annual Review of Physiology 55(1) (1993), 16-54.
M. Plummer, N. Best, K. Cowles and K. Vines, CODA: convergence diagnosis and output analysis for MCMC, R News 6(1) (2006), 7-11.
R. Refinetti, Circadian Physiology, 3rd ed., CRC Press, 2016.
A. Reinberg et al., Biological time series analysis, Chronobiology International 33(8) (2016), 909-924.
P. Rodriguez et al., Hybrid models for health time series, Artificial Intelligence in Medicine 128 (2022), 102456.
S. L. Scott and H. R. Varian, Predicting the present with Bayesian structural time series, International Journal of Mathematical Modelling and Numerical Optimisation 5(1-2) (2014), 4-23.
V. Singh and R. Kumar, Overfitting in polynomial regression: a case study, J. Appl. Stat. 48(7) (2021), 1234-1249.
S. Taylor and B. Letham, Neural forecasting in biomedicine, IEEE Transactions on Biomedical Engineering 70(4) (2023), 1210-1221.
L. Wang et al., TBATS for multi-seasonal health data, Stat. Med. 39(28) (2020), 4123-4140.
K. P. Wright, Jr., C. A. Lowry and M. K. Lebourgeois, Circadian and wakefulness-sleep modulation of cognition in humans, Frontiers in Molecular Neuroscience 6 (2013), 1-10. https://doi.org/10.3389/fnmol.2013.00124.
Yahya Almarhabi and Abdullah M. Almarashi, Multi-model approach for modelling circadian rhythm physiological parameters, JP Journal of Biostatistics 25(1) (2025), 53-78.
G. Zhang, B. E. Patuwo and M. Y. Hu, Forecasting with artificial neural networks: the state of the art, International Journal of Forecasting 14(1) (1998), 35-62.
Q. Zhang et al., Machine learning in physiological forecasting, Computers in Biology and Medicine 141 (2022), 105112.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 PUSHPA PUBLISHING HOUSE, PRAYAGRAJ, INDIA
This work is licensed under a Creative Commons Attribution 4.0 International License.
_________________________
Attribution: Credit Pushpa Publishing House as the original publisher, including title and author(s) if applicable.
Non-Commercial Use: For non-commercial purposes only. No commercial activities without explicit permission.
No Derivatives: Modifying or creating derivative works not allowed without written permission.
Contact Puspha Publishing House for more info or permissions.
Journal Impact Factor: 
Publication count: 330
Google h-index: 10
Downloads: 87500+