The Multi-Dimensional Impact of Sleep Profile on Cognitive and Emotional Regulation Performance
DOI:
https://doi.org/10.70112/ajeat-2026.15.1.4363Keywords:
Sleep Deprivation, Cognitive Performance, Emotion Regulation, Machine Learning, Random Forest, Psychomotor VigilanceAbstract
Sleep is critical for maintaining optimal cognitive and emotional functioning, yet the multidimensional relationships between sleep profiles and distinct cognitive-emotional outcomes remain incompletely characterized. While sleep deprivation impairs attention and vigilance, effects on executive control and emotion regulation are heterogeneous and context-dependent. Machine learning offers transformative potential for identifying complex, non-linear patterns between integrated sleep measures and behavioral outcomes. A dataset of 60 participants (23 female, 37 male; mean age 29.5 years) was analyzed using ridge regression and Random Forest models to predict cognitive and emotional performance from sleep characteristics and lifestyle variables. Sleep dimensions included Sleep Hours, Sleep Quality Score, and Daytime Sleepiness. Outcomes measured executive control (Stroop Task Reaction Time), working memory (N-Back Accuracy), sustained attention (Psychomotor Vigilance Task Reaction Time), and emotion regulation (Emotion Regulation Score). After outlier removal (n = 58), features were standardized, and models were trained on 80% of the data with performance evaluated on a 20% test set using root mean squared error (RMSE), R², and mean absolute error (MAE). Ridge regression and Random Forest demonstrated outcome-dependent predictive utility. Stroop Task Reaction Time showed minimal predictive power (R² = -0.001 to 0.009), indicating that executive control is relatively resilient to measured sleep and lifestyle factors. Conversely, Psychomotor Vigilance Task Reaction Time demonstrated robust prediction (R² = 0.78), and Emotion Regulation Score showed the strongest predictive power (R² = 0.86). Daytime Sleepiness and Physical Activity Level emerged as consistent feature importance across outcomes, with Age significantly predicting vigilance performance. Weak correlations (mean |r| < 0.15) between sleep dimensions and executive control suggest compensatory neural recruitment preserves behavioral performance despite sleep variations. Sleep's impact on cognitive and emotional regulation is domain-specific: vigilance and emotion regulation show strong predictability from sleep and lifestyle variables, whereas executive control demonstrates surprising resilience. Physical activity level emerges as a potent predictor of emotion regulation, potentially eclipsing the direct effects of sleep. Future investigations employing objective polysomnographic assessment and longitudinal designs are warranted to elucidate mechanistic sleep-behavior dynamics.
References
[1] C. M. Morin et al., "Estimation of the global prevalence and burden of insomnia," Sleep Medicine Reviews, vol. 75, p. 101845, 2025.
[2] J. E. Ashton et al., "Memory control deficits in the sleep-deprived human brain," PNAS, vol. 121, no. 1, p. e2400743122, 2024.
[3] D. R. Hillman and L. C. Lack, "The economic cost of inadequate sleep," Sleep, vol. 41, no. 8, p. zsy083, 2018.
[4] R. C. Kessler et al., "Insomnia and the performance of US workers: Results from the America Insomnia Survey," Sleep, vol. 34, no. 9, pp. 1161-1171, 2011.
[5] M. P. Walker, Why we sleep: Unlocking the power of sleep and dreams. Scribner, 2017.
[6] J. S. Durmer and D. F. Dinges, "Neurocognitive consequences of sleep deprivation," Seminars in Neurology, vol. 25, no. 1, pp. 117-129, 2005.
[7] H. Lee et al., "The impact of total sleep deprivation on cognitive functions," Psychiatry and Clinical Neurosciences, vol. 57, no. 5, pp. 490-496, 2003.
[8] B. Rasch and J. Born, "About sleep’s role in memory," Physiological Reviews, vol. 93, no. 2, pp. 681-766, 2013.
[9] C. A. Palmer and C. A. Alfano, "Sleep and emotion regulation: An organizing, integrative review," Sleep Medicine Reviews, vol. 31, pp. 6-16, 2017.
[10] S. S. Yoo et al., "The human emotional brain without sleep—A prefrontal amygdala disconnect," Current Biology, vol. 17, no. 20, pp. R877-R878, 2007.
[11] T. Hastie, R. Tibshirani, and J. Friedman, The elements of statistical learning: Data mining, inference, and prediction, 2nd ed. Springer, 2009.
[12] L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5-32, 2001.
[13] S. W. Cain et al., "One night of sleep deprivation affects reaction time, but not interference or facilitation in a Stroop task," Brain and Cognition, vol. 76, no. 1, pp. 37-42, 2011.
[14] K. Morokuma et al., "A deep learning model for predicting sleep quality using multimodal wearable data," IEEE Access, vol. 11, pp. 45123-45135, 2023.
[15] Y. Zhang et al., "Deep learning-based identification of depression and anxiety from sleep quality parameters," Journal of Affective Disorders, vol. 345, pp. 210-220, 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Centre for Research and Innovation
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
