Abstract
Stress is a social problem affecting society in different ways. Obtaining an accurate diagnosis of stress is complex because the symptoms of stress are very similar to the symptoms of many other illnesses. Some studies have used wearable sensors for psychophysiological signal acquisition and artificial intelligence approaches for automatic stress pattern detection. Nevertheless, the literature does not present specific group analyses among different participants’ characterizations. This work evaluates the impact of the allostatic load on Machine Learning models considering clinical patients compared to non-clinical patients. We created and used a new dataset that uses a stress-inducing protocol based on repetitive negative thoughts. This dataset contains 27 participants with clinical and non-clinical profiles. The acquired data are electrocardiogram, respiration patterns, electrodermal activity, weight, height, and Body Mass Index. The classifier that showed the best results was Random Forest. The model using only non-clinical participants obtained 94.54% accuracy against 92.08% of clinical ones. Results obtained with all participants had slight improvement, with 92.72%. Comparing clinical and non-clinical patients showed an accuracy mean difference of 2.5%, indicating aspects of the impact of the allostatic load on the model generalization for people outside the dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ghaderi, A., Frounchi, J., Farnam, A.: Machine learning-based signal processing using physiological signals for stress detection. In: 22nd Iranian Conference on Biomedical Engineering (ICBME 2015), pp. 25–27 (2015)
Pinge, A., et al.: A comparative study between ECG-based and PPG-based heart rate monitors for stress detection. In: 14th International Conference on COMmunication Systems and NETworkS (COMSNETS) (2022)
Carreiras, C., et al.: BioSPPy: biosignal processing in Python (2015)
Centers for Disease Control and Prevention, U.S., “Body Mass Index (BMI)" (2020)
O’Connor, D.B., Thayer, J.F., Vedhara, K.: Stress and health: a review of psychobiological processes. Annu. Rev. Psychol 72, 663–688 (2021)
Dias, D., Cunha, J.P.S.: Wearable health devices-vital sign monitoring. Syst. Technol. Sens. 18, 2414 (2018)
Mauss, D., Jarczok, M.N.: The streamlined allostatic load index is associated with perceived stress in life - findings from the MIDUS study. Int. J. Biol. Stress 24, 404–412 (2021)
Whelan, E., et al.: Evaluating measures of allostatic load in adolescents: a systematic review. Psychoneuroendocrinology 131, 105324 (2021)
Giannakakis, G., et al.: Review on psychological stress detection using biosignals. IEEE Trans. J. 13(1), 440–460 (2019)
Parker, H.W., et al.: Allostatic load and mortality: a systematic review and meta-analysis. Am. J. Prev. Med. (2022)
Chalmers, J.A., et al.: Worry is associated with robust reductions in heart rate variability: a transdiagnostic study of anxiety psychopathology. BMC Psychol. 4, 1–9 (2016)
Früh, J., et al.: Variation of vital signs with potential to influence the performance of qSOFA scoring in the Ethiopian general population at different altitudes of residency: a multisite cross-sectional study. Plos One 19, 1–13 (2021)
Can, J.Y.S., Arnrich, B., Ersoy, C.: Stress detection in daily life scenarios using smart phones and wearable sensors: a survey. J. Biomed. Inform. 92, 103139 (2019)
Guidi, J., et al.: Allostatic load and its impact on health: a systematic review. Psychother. Psychosom. 90, 11–27 (2021)
Kelly, K.M.: Examining the effect of perseverative thinking on physiological activation in response to stress. Honors Theses (2018)
Carnevali, L., et al.: Heart rate variability mediates the link between rumination and depressive symptoms: a longitudinal study. Int. J. Psychophysiol. 131, 131–138 (2018)
Han, L., et al.: Detecting work-related stress with a wearable device. Comput. Ind. 90, 42–49 (2017)
Jacobsen, M., et al.: Wearable technology: a promising opportunity to improve inpatient psychiatry safety and outcomes. J. Diabetes Sci. Technol. 15, 34–43 (2021)
Ahuja, R., Banga, A.: Mental stress detection in university students using machine learning algorithms. Procedia Comput. Sci. 152, 349–353 (2021)
Corrigan, S.L., et al.: Monitoring stress and allostatic load in first responders and tactical operators using heart rate variability: a systematic review. BMC Public Health 21, 1701 (2021). https://doi.org/10.1186/s12889-021-11595-x
Doan, S.N.: Allostatic load: developmental and conceptual considerations in a multi-system physiological indicator of chronic stress exposure. Dev. Psychobiol. 63(5), 825–836 (2021)
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 3rd edn. Pearson - Prentice Hall, Hoboken (2009)
Suganthi, V., Punithavalli, M.: A review of deep learning and machine learning methods for analyzing Covid-19 Stress. Int. J. Innovative Sci. Res. Technol. (2022)
Acknowledgement
We acknowledge Fapergs for supporting this work by means of Grant PQG, 5/2019.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
da Rosa Fröhlich, W., Rigo, S.J., Bez, M.R., de Oliveira, D.R., Zibetti, M.R. (2022). The Impact of Allostatic Load on Machine Learning Models. In: Bicharra Garcia, A.C., Ferro, M., Rodríguez Ribón, J.C. (eds) Advances in Artificial Intelligence – IBERAMIA 2022. IBERAMIA 2022. Lecture Notes in Computer Science(), vol 13788. Springer, Cham. https://doi.org/10.1007/978-3-031-22419-5_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-22419-5_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22418-8
Online ISBN: 978-3-031-22419-5
eBook Packages: Computer ScienceComputer Science (R0)