Prediction of central nervous system oxygen toxicity symptoms using electrodermal activity and machine learning

• Autorzy: Hossain Md Billal , Golzari Kia , Kong Youngsun , Derrick Bruce J. , Moon Richard E. , Natoli Michael J. , Ellis M. Claire , Winstead-Derlega Christopher , Gonzalez Sara I. , Allen Christopher M. , Makowski Mathew S. , Keuski Brian M. , Freiberger John J. , Posada-Quintero Hugo F. , Chon Ki H.

Identyfikatory

DOI

10.1016/j.bbe.2024.03.004

• Języki publikacji: EN

Abstrakty

EN

Objective: Breathing elevated oxygen partial pressures (PO2) prior to SCUBA diving increases the risk of developing central nervous system oxygen toxicity (CNS-OT), which could impair performance or result in seizure and subsequent drowning. We aimed to study the dynamics of electrodermal activity (EDA) while breathing elevated PO₂ in the hyperbaric environment (HBO₂) as a possible means to predict impending CNS-OT. To this end, we used machine learning to automatically detect and predict the onset of symptoms associated with CNS-OT in humans by using features derived from EDA in both time and frequency domains. Methods: We collected electrodermal activity (EDA) data from forty-nine exposures to HBO₂ while subjects were undergoing cognitive load and exercise in a hyperbaric oxygen chamber. Four independent experts were present during the experiment to monitor and classify any symptoms associated with hyperbaric oxygen toxicity. We computed a highly sensitive time varying spectral EDA index, named TVSymp, and extracted informative features from skin conductance responses (SCRs). Machine learning algorithms were trained and validated for classifying features from SCRs and TVSymp as CNS-OT related or non-CNS-OT related. Machine learning models were validated using a subject-independent leave one subject out (LOSO) validation scheme. Results: Our machine learning model was able to classify EDA dynamics related to CNS-OT with 100 % sensitivity and 84 % specificity via LOSO validation. Moreover, the median prediction time for CNS-OT symptoms was ~ 250 s preceding the occurrence of actual symptoms. Significance: This study shows that EDA can potentially be used for early prediction of CNS-OT in divers with a high sensitivity and sufficient prediction time for countermeasures. While the study results are promising, independent validation datasets are warranted to confirm the findings. However, the current results are well corroborated in an animal study, which consistently showed seizure prediction time of 2 min prior to seizure.

Słowa kluczowe

EN

seizure prediction; oxygen toxicity; electrodermal activity; machine learning

PL

przewidywanie napadu; toksyczność tlenowa; aktywność elektrodermalna; uczenie maszynowe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2024
• Tom: Vol. 44, no. 2
• Strony: 304--311
• Opis fizyczny: Bibliogr. 43 poz., rys., tab., wykr.

Twórcy

autor

Hossain Md Billal

• Department of Biomedical Engineering, University of Connecticut, Storrs, CT, USA

autor

Golzari Kia

• Department of Biomedical Engineering, University of Connecticut, Storrs, CT, USA

autor

Kong Youngsun

• Department of Biomedical Engineering, University of Connecticut, Storrs, CT, USA

autor

Derrick Bruce J.

• Division of Emergency Medicine, Duke University, Durham, NC, USA
• Department of Anesthesiology, Duke University, Durham, NC, USA

autor

Moon Richard E.

• Division of Emergency Medicine, Duke University, Durham, NC, USA
• Department of Anesthesiology, Duke University, Durham, NC, USA

autor

Natoli Michael J.

• Division of Emergency Medicine, Duke University, Durham, NC, USA

autor

Ellis M. Claire

• Division of Emergency Medicine, Duke University, Durham, NC, USA
• Department of Anesthesiology, Duke University, Durham, NC, USA

autor

Winstead-Derlega Christopher

• Division of Emergency Medicine, Duke University, Durham, NC, USA
• Department of Anesthesiology, Duke University, Durham, NC, USA

autor

Gonzalez Sara I.

• Division of Emergency Medicine, Duke University, Durham, NC, USA

autor

Allen Christopher M.

• Division of Emergency Medicine, Duke University, Durham, NC, USA
• Department of Anesthesiology, Duke University, Durham, NC, USA

autor

Makowski Mathew S.

• Division of Emergency Medicine, Duke University, Durham, NC, USA
• Department of Anesthesiology, Duke University, Durham, NC, USA

autor

Keuski Brian M.

• United States Navy, USA

autor

Freiberger John J.

• Department of Anesthesiology, Duke University, Durham, NC, USA

autor

Posada-Quintero Hugo F.

• Department of Biomedical Engineering, University of Connecticut, Storrs, CT, USA

autor

Chon Ki H.

• Department of Biomedical Engineering, University of Connecticut, Storrs, CT 06269, USA

Bibliografia

• [1] Pace N, Strajman E, Walker EL. Acceleration of Carbon monoxide elimination in man by high pressure oxygen. Sci 1950;111:652-4. https://doi.org/10.1126/ science.111.2894.652.
• [2] United States: Defense Department: Navy Department: Naval Sea Systems Command, United States: Naval Sea Systems Command,. U.S. Navy Diving Manual. Revision 7. Defense Department; 2016.
• [3] Thom SR. Hyperbaric oxygen - its mechanisms and efficacy. Plast Reconstr Surg 2011;127:131S-S141. https://doi.org/10.1097/PRS.0b013e3181fbe2bf.
• [4] Kranke P, Bennett MH, James M-M-S, Schnabel A, Debus SE, Weibel S. Hyperbaric oxygen therapy for chronic wounds. Cochrane Database Syst Rev 2015. https://doi. org/10.1002/14651858.CD004123.pub4.
• [5] Ortega MA, Fraile-Martinez O, García-Montero C, Callejón-Peláez E, Sáez MA, Álvarez-Mon MA, García-Honduvilla N, Monserrat J, Álvarez-Mon M, Bujan J, Canals ML. A General Overview on the Hyperbaric Oxygen Therapy: Applications, Mechanisms and Translational Opportunities. Medicina (Kaunas). 2021 Aug 24;57 (9):864. doi: 10.3390/medicina57090864. PMID: 34577787; PMCID: PMC8465921.
• [6] Manning, Edward P. “Central Nervous System Oxygen Toxicity and Hyperbaric Oxygen Seizures.” Aerospace Medicine and Human Performance 87, no. 5 (May 1, 2016): 477-86. https://doi.org/10.3357/AMHP.4463.2016.
• [7] Plafki C, Peters P, Almeling M, Welslau W, Busch R. Complications and side effects of hyperbaric oxygen therapy. Aviat Space Environ Med 2000;71:119-24.
• [8] Jenkinson SG. Oxygen toxicity. New Horiz 1993;1:504-11.
• [9] Wannamaker BB. Autonomic nervous system and epilepsy. Epilepsia 1985;26: S31-9. https://doi.org/10.1111/j.1528-1157.1985.tb05722.x.
• [10] Freeman R, Chapleau MW. Chapter 7 - testing the autonomic nervous system. In: Said G, Krarup C, editors. Handbook of Clinical Neurology, vol. 115. Elsevier; 2013. p. 115-36. https://doi.org/10.1016/B978-0-444-52902-2.00007-2.
• [11] Hernandez J, Morris RR, Picard RW. Call center stress recognition with person-specific models. In: D’Mello S, Graesser A, Schuller B, Martin J-C, editors. Affective Computing and Intelligent Interaction. Berlin, Heidelberg: Springer; 2011. p. 125-34. https://doi.org/10.1007/978-3-642-24600-5_16.
• [12] Gjoreski M, Gjoreski H, Luštrek M, Gams M. Continuous stress detection using a wrist device: in laboratory and real life. Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct, New York, NY, USA: Association for Computing Machinery; 2016 1185 93. DOI: 10.1145/2968219.2968306.
• [13] Healey J, Nachman L, Subramanian S, Shahabdeen J, Morris M. Out of the lab and into the fray: Towards modeling emotion in everyday life. In: Floréen P, Krüger A, Spasojevic M, editors. Pervasive Computing. Berlin, Heidelberg: Springer; 2010. p. 156-73. https://doi.org/10.1007/978-3-642-12654-3_10.
• [14] Setz C, Arnrich B, Schumm J, Marca RL, Tröster G, Ehlert U. Discriminating stress from cognitive load using a Wearable EDA Device. IEEE Trans Inf Technol Biomed 2010;14:410-7. https://doi.org/10.1109/TITB.2009.2036164.
• [15] Momin A, Bhattacharya S, Sanyal S, Chakraborty P. Visual attention, mental stress and gender: a study using physiological signals. IEEE Access 2020;8:165973-88. https://doi.org/10.1109/ACCESS.2020.3022727.
• [16] Kong Y, Posada-Quintero HF, Chon KH. Pain Detection using a Smartphone in Real Time*. 2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC), 2020 4526 9. DOI: 10.1109/ EMBC44109.2020.9176077.
• [17] Kong Y, Posada-Quintero H, Chon K. Sensitive physiological indices of pain based on differential characteristics of electrodermal activity. IEEE Trans Biomed Eng 2021:1. https://doi.org/10.1109/TBME.2021.3065218.
• [18] Prince EB, Kim ES, Wall CA, Gisin E, Goodwin MS, Simmons ES, et al. The relationship between autism symptoms and arousal level in toddlers with autism spectrum disorder, as measured by electrodermal activity. Autism 2017;21:504-8. https://doi.org/10.1177/1362361316648816.
• [19] Schupak BM, Parasher RK, Zipp GP. Reliability of electrodermal activity: quantifying sensory processing in children with autism. Am J Occup Ther 2016;70: 1-6. https://doi.org/10.5014/ajot.2016.018291.
• [20] Wendt J, Lotze M, Weike AI, Hosten N, Hamm AO. Brain activation and defensive response mobilization during sustained exposure to phobia-related and other affective pictures in spider phobia. Psychophysiology 2008;45:205-15. https://doi. org/10.1111/j.1469-8986.2007.00620.x.
• [21] Kim AY, Jang EH, Kim S, Choi KW, Jeon HJ, Yu HY, et al. Automatic detection of major depressive disorder using electrodermal activity. Sci Rep 2018;8:17030. https://doi.org/10.1038/s41598-018-35147-3.
• [22] Jaques N, Taylor S, Azaria A, Ghandeharioun A, Sano A, Picard R. Predicting students’ happiness from physiology, phone, mobility, and behavioral data. Int Conference on Affective Computing and Intelligent Interaction (ACII) 2015;2015: 222-8. https://doi.org/10.1109/ACII.2015.7344575.
• [23] Jang E-H, Park B-J, Park M-S, Kim S-H, Sohn J-H. Analysis of physiological signals for recognition of boredom, pain, and surprise emotions. J Physiol Anthropol 2015; 34:25. https://doi.org/10.1186/s40101-015-0063-5.
• [24] Publication recommendations for electrodermal measurements. Psychophysiology 2012;49:1017-34. DOI: 10.1111/j.1469-8986.2012.01384.x.
• [25] Posada-Quintero HF, Chon KH. Innovations in electrodermal activity data collection and signal processing: a systematic review. Sensors 2020;20:479. https://doi.org/10.3390/s20020479.
• [26] Posada-Quintero, Hugo F., Bruce J. Derrick, Christopher Winstead-Derlega, Sara I. Gonzalez, M. Claire Ellis, John J. Freiberger, and Ki H. Chon. “Time-Varying Spectral Index of Electrodermal Activity to Predict Central Nervous System Oxygen Toxicity Symptoms in Divers: Preliminary Results.” In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC), 1242-45, 2021. https://doi.org/10.1109/EMBC46164.2021.9629924.
• [27] Posada-Quintero HF, Kong Y, Nguyen K, Tran C, Beardslee L, Chen L, et al. Using electrodermal activity to validate multilevel pain stimulation in healthy volunteers evoked by thermal grills. American J Physiology-Regulatory, Integrative and Comparative Physiology 2020;319:R366-75. https://doi.org/10.1152/ ajpregu.00102.2020.
• [28] Posada-Quintero HF, Reljin N, Moutran A, Georgopalis D, Lee E-C-H, Giersch GEW, et al. Mild dehydration identification using machine Learning to assess autonomic responses to cognitive stress. Nutrients 2020;12:42. https://doi.org/10.3390/ nu12010042.
• [29] Posada-Quintero HF, Florian JP, Orjuela-Cañón ÁD, Chon KH. Highly sensitive index of sympathetic activity based on time-frequency spectral analysis of electrodermal activity. American J Physiology-Regulatory, Integrative and Comparative Physiology 2016;311:R582-91. https://doi.org/10.1152/ajpregu.00180.2016.
• [30] Posada-Quintero HF, Bolkhovsky JB, Reljin N, Chon KH. Sleep deprivation in young and healthy subjects is more sensitively identified by higher frequencies of electrodermal activity than by skin conductance level evaluated in the time domain. Front Physiol 2017;8.
• [31] Kong Y, Posada-Quintero HF, Chon KH. Real-time high-level acute pain detection using a smartphone and a wrist-worn electrodermal activity sensor. Sensors 2021; 21:3956. https://doi.org/10.3390/s21123956.
• [32] Posada-Quintero HF, Landon CS, Stavitzski NM, Dean JB, Chon KH. Seizures caused by exposure to Hyperbaric oxygen in rats can be predicted by Early changes in electrodermal activity. Front Physiol 2022;12.
• [33] Santiago-Espada Y. The multi-attribute task battery II (MATB-II) software for human performance and workload research: a user’s guide. Hampton, Virginia: National Aeronautics and Space Administration, Langley Research Center; 2011.
• [34] Hossain M-B, Posada-Quintero HF, Kong Y, McNaboe R, Chon KH. Automatic motion artifact detection in electrodermal activity data using machine learning. Biomed Signal Process Control 2022;74:103483. https://doi.org/10.1016/j. Bspc.2022.103483.
• [35] Hossain MB, Posada-Quintero H, Chon K. A deep convolutional autoencoder for automatic motion artifact removal in electrodermal activity. IEEE Trans Biomed Eng 2022:1. https://doi.org/10.1109/TBME.2022.3174509.
• [36] Kleckner IR, Jones RM, Wilder-Smith O, Wormwood JB, Akcakaya M, Quigley KS, et al. Simple, transparent, and flexible automated quality assessment procedures for ambulatory electrodermal activity data. IEEE Trans Biomed Eng 2018;65: 1460-7. https://doi.org/10.1109/TBME.2017.2758643.
• [37] Posada-Quintero HF, Florian JP, Orjuela-Cañón AD, Chon KH. Electrodermal activity is sensitive to cognitive stress under water. Front Physiol 2018:8. https:// doi.org/10.3389/fphys.2017.01128.
• [38] Wang H, Siu K, Ju K, Chon KH. A high resolution approach to estimating time-frequency spectra and their amplitudes. Ann Biomed Eng 2006;34:326-38. https://doi.org/10.1007/s10439-005-9035-y.
• [39] Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proce Royal Society of London Series A: Mathematical Physical and Eng Sci 1998;454:903-95. https://doi.org/10.1098/rspa.1998.0193.
• [40] Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Int Res 2002;16:321-57.
• [41] Breiman L. Random forests. Mach Learn 2001;45:5-32. https://doi.org/10.1023/A:1010933404324.
• [42] Fisher A, Rudin C, Dominici F. All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously. J Mach Learn Res 2019. https://doi.org/10.48550/arXiv.1801.01489.
• [43] Hossain M-B, Kong Y, Posada-Quintero HF, Chon KH. Comparison of electrodermal activity from multiple body locations based on Standard EDA indices’ quality and robustness against motion Artifact. Sensors 2022;22:3177. https://doi.org/ 10.3390/s22093177.