A Comprehensive Review of Stress Detection Using Physiological Signals and Machine Learning Approaches
Article Sidebar
Main Article Content
Abstract
Stress is one of the most severe issues in contemporary society as it has bohemian effects on the physical health and mental state as well as the productivity at the workplace. The well-known self-reporting and questionnaires methods of assessing stress has various modest limitations of low reliability and subjectivity cueing the rise of automated methodologies of stress measurements. Over the past years, electrocardiogram (ECG), electroencephalogram (EEG), galvanic skin response (GSR), heart rate variability (HRV), blood pressure, and respiration rate have been used as reliable stress monitoring biomarkers. At the same time, machine learning (ML) advances contributed to the creation of intelligent models that can analyze even complex physiological data, and make precise predictions of the level of stress. This paper has the aim of covering the literature on stress detection with physiological signals and machine learning techniques in detail. We classify the literature with respect to what kinds of physiological signals are used, the methods used during the preprocessing step, feature extraction methods and machine learning algorithms, including both classical models (i.e., Support Vector Machines, Random Forests, and k-Nearest Neighbors) as well as deep learning models (i.e., Convolutional Neural Networks and Long Short-Term Memory networks). Additionally, we report stress-related datasets that have become publicly available with the help of which the benchmarking and comparative analyses across other studies became possible. Besides, this review also discusses the existing in the field, including inter-subject variability, signal noise, small dataset size, the real-time monitoring limitations, and generalization of non-homogeneous groups. We also comment on hybrid designs involving stacks of several physiological signals, wearable combinations, and the role of new technologies explaining the AI and federated learning might play in the development of stress detection systems. This paper concludes by providing future research directions on using multimodal datasets in large scale, privacy-preserving hardware and software models, and practical applications in the fields of healthcare, workplaces, and personal well-being solutions. The review will inform researchers and practitioners of a more comprehensive overview of the field and point to potentially fruitful areas of future-generation stress detecting systems.
Article Details
References
Stein DJ, Palk AC, Kendler KS (2021) What is a mental disorder? An exemplar-focused approach. Psychol Med 51:894–901. https://doi.org/10.1017/S0033291721001185
Cuijpers P (2014) Towards a dimensional approach to common mental disorders in the ICD-11? Aust N Z J Psychiatry 48:481–482. https://doi.org/10.1177/0004867414525846
Tandon R (2014) Schizophrenia and other psychotic disorders in diagnostic and statistical manual of mental disorders (DSM)-5: Clinical implications of revisions from DSM-IV. Indian J Psychol Med 36:223–225. https://doi.org/10.4103/0253-7176.135365
Doernberg E, Hollander E (2016) Neurodevelopmental Disorders (ASD and ADHD): DSM-5, ICD-10, and ICD-11. CNS Spectr 21:295–299. https://doi.org/10.1017/S1092852916000262
WHO (2017) Depression and other common mental disorders: global health estimates. World Health Organization. WHO/MSD/MER/2017.2, 24
Ahmedani BK (2011) Mental Health Stigma: Society, Individuals, and the Profession. J Soc Work Values Ethics 8:41–416
Pinheiro M, Ivandic I, Razzouk D (2017) The Economic Impact of Mental Disorders and Mental Health Problems in the Workplace. Mental Health Economics: The Costs and Benefits of Psychiatric Care 415–430. https://doi.org/10.1007/978-3-319-55266-8_28
Schomerus G, Evans-Lacko S, Rüsch N, Mojtabai R, Angermeyer MC, Thornicroft G (2015) Collective levels of stigma and national suicide rates in 25 European countries. Epidemiol Psychiatric Sci 24:166–171. https://doi.org/10.1017/S2045796014000109
Crocq MA (2003) Alcohol, nicotine, caffeine, and mental disorders. Dialogues Clin Neurosci 5:175–185. https://doi.org/10.31887/dcns.2003.5.2/macrocq
Trull TJ, Freeman LK, Vebares TJ, Choate AM, Helle AC, Wycoff AM (2018) Borderline personality disorder and substance use disorders: An updated review. Borderline Personal Disord Emot Dysregulation 5:1–12. https://doi.org/10.1186/s40479-018-0093-9
Corrigan PW, Bink AB, Schmidt A (2017) Reducing physical illness stigma: Insights from the mental illness arena. In B. Major, J.F. Dovidio, & B.G. Link,eds., Oxford Handb. Stigma, Discrim. Heal. (Oxford University Press), pp 413–427. https://doi.org/10.1093/oxfordhb/9780190243470.001.0001
Arango C, Díaz-Caneja CM, McGorry PD, Rapoport J, Sommer IE, Vorstman JA, McDaid D, Marín O, Serrano-Drozdowskyj E, Freedman R, Carpenter W (2018) Preventive strategies for mental health. Lancet Psychiatry 5:591–604. https://doi.org/10.1016/S2215-0366(18)30057-9
Chen J, Abbod M, Shieh JS (2021) Pain and stress detection using wearable sensors and devices—a review. Sensors 21:1–18. https://doi.org/10.3390/s21041030 (Switzerland)
Hussain I, Young S, Kim CH, Benjamin HCM, Park SJ (2021) Quantifying physiological biomarkers of a microwave brain stimulation device. Sensors 21:1–16. https://doi.org/10.3390/s21051896
Panure T, Sonawani S (2019) Stress Detection Using Smartphone and Wearable Devices: a Review. Asian J Converg Technol 05:1–4. https://doi.org/10.33130/ajct.2019v05i01.007
Song T, Lu G, Yan J (2020) Emotion Recognition Based on Physiological Signals Using Convolution Neural Networks. ACM Int Conf Proc Ser 161–165. https://doi.org/10.1145/3383972.3384003
Critchley HD, Garfinkel SN (2018) The influence of physiological signals on cognition. Curr Opin Behav Sci 19:13–18. https://doi.org/10.1016/j.cobeha.2017.08.014
Sarchiapone M, Gramaglia C, Iosue M, Carli V, Mandelli L, Serretti A, Marangon D, Zeppegno P (2018) The association between electrodermal activity (EDA), depression and suicidal behaviour: A systematic review and narrative synthesis. BMC Psychiatry 18. https://doi.org/10.1186/s12888-017-1551-4
Chang HA, Chang CC, Tzeng NS, Kuo TBJ, Lu RB, Huang SY (2014) Heart rate variability in unmedicated patients with bipolar disorder in the manic phase. Psychiatry Clin Neurosci 68:674–682. https://doi.org/10.1111/pcn.12178
Berle JO, Hauge ER, Oedegaard KJ, Holsten F, Fasmer OB (2010) Actigraphic registration of motor activity reveals a more structured behavioural pattern in schizophrenia than in major depression. BMC Res Notes 3:1–7. https://doi.org/10.1186/1756-0500-3-149
Lin Q, Li T, Shakeel PM, Samuel RDJ (2021) Advanced artificial intelligence in heart rate and blood pressure monitoring for stress management. J Ambient Intell Humaniz Comput 12:3329–3340. https://doi.org/10.1007/s12652-020-02650-3
Sriramprakash S, Prasanna VD, Murthy OVR (2017) Stress Detection in Working People. Procedia Comput Sci 115:359–366. https://doi.org/10.1016/j.procs.2017.09.090
Rim B, Sung NJ, Min S, Hong M (2020) Deep learning in physiological signal data: A survey. Sensors 20. https://doi.org/10.3390/s20040969 (Switzerland)
Faust O, Hagiwara Y, Hong TJ, Lih OS, Acharya UR (2018) Deep learning for healthcare applications based on physiological signals: A review. Comput Methods Programs Biomed 161:1–13. https://doi.org/10.1016/j.cmpb.2018.04.005
Panicker SS, Gayathri P (2019) A survey of machine learning techniques in physiology based mental stress detection systems. Biocybernetics Biomed Eng 39:444–469. https://doi.org/10.1016/j.bbe.2019.01.004
Bota PJ, Wang C, Fred ALN, Placido Da Silva H, Review A (2019) Current Challenges, and Future Possibilities on Emotion Recognition Using Machine Learning and Physiological Signals. IEEE Access 7:140990–141020. https://doi.org/10.1109/ACCESS.2019.2944001
Wang Z, Ho SB, Cambria E (2020) A review of emotion sensing: categorization models and algorithms. Multimed Tools Appl 79:35553–35582. https://doi.org/10.1007/s11042-019-08328-z
Bardram JE, Matic A (2020) A Decade of Ubiquitous Computing Research in Mental Health. IEEE Pervasive Comput 19:62–72. https://doi.org/10.1109/MPRV.2019.2925338
Garcia-Ceja E, Riegler M, Nordgreen T, Jakobsen P, Oedegaard KJ, Tørresen J (2018) Mental health monitoring with multimodal sensing and machine learning: A survey. Pervasive Mob Comput 51:1–26. https://doi.org/10.1016/j.pmcj.2018.09.003
Siddiqui MK, Morales-Menendez R, Huang X, Hussain N (2020) A review of epileptic seizure detection using machine learning classifiers. Brain Inform 7:1–18. https://doi.org/10.1186/s40708-020-00105-1
Suhaimi NS, Mountstephens J, Teo J (2020). EEG-Based Emotion Recognition: A State-of-the-Art Review of Current Trends and Opportunities. Comput Intell Neurosci 2020. https://doi.org/10.1155/2020/8875426
Rivera MJ, Teruel MA, Maté A, Trujillo J (2022) Diagnosis and prognosis of mental disorders by means of EEG and deep learning: a systematic mapping study. https://doi.org/10.1007/s10462-021-09986-y (Springer Netherlands)
Dev A, Roy N, Islam MK, Biswas C, Ahmed HU, Amin MA, Sarker F, Vaidyanathan R, Mamun KA (2022) Exploration of EEG-Based Depression Biomarkers Identification Techniques and Their Applications: A Systematic Review. IEEE Access 10:16756–16781.
Shoeibi A, Khodatars M, Ghassemi N, Jafari M, Moridian P, Alizadehsani R, Panahiazar M, Khozeimeh F, Zare A, Hosseini-Nejad H, Khosravi A, Atiya AF, Aminshahidi D, Hussain S, Rouhani M, Nahavandi S, Acharya UR (2021) Epileptic seizures detection using deep learning techniques: A review. Int J Environ Res Public Health 18. https://doi.org/10.3390/ijerph18115780
Li M, Cao L, Zhai Q, Li P, Liu S, Li R, Feng L, Wang G, Hu B, Lu S (2020) Method of Depression Classification Based on Behavioral and Physiological Signals of Eye Movement. Complexity 2020. https://doi.org/10.1155/2020/4174857
Carneiro de Melo W, Granger E, Hadid A (2020) A Deep Multiscale Spatiotemporal Network for Assessing Depression from Facial Dynamics. IEEE Trans Affect Comput 3045:1–1. https://doi.org/10.1109/taffc.2020.3021755
de Belen RAJ, Bednarz T, Sowmya A, Del Favero D (2020) Computer vision in autism spectrum disorder research: a systematic review of published studies from 2009 to 2019. Transl Psychiatry 10. https://doi.org/10.1038/s41398-020-01015-w
Liu X (2021) Model Construction of Using Physiological Signals to Detect Mental Health Status. J Healthc Eng 2021:1–8. https://doi.org/10.1155/2021/8544750
Siuly S, Li Y, Wen PP (2011) Clustering technique-based least square support vector machine for EEG signal classification. Comput Methods Programs Biomed 104:358–372. https://doi.org/10.1016/j.cmpb.2010.11.014
Acharya UR, Molinari F, Sree SV, Chattopadhyay S, Ng KH, Suri JS (2012) Automated diagnosis of epileptic EEG using entropies. Biomed Signal Process Control 7:401–408. https://doi.org/10.1016/j.bspc.2011.07.007
Mahato S, Paul S (2019) Detection of major depressive disorder using linear and non-linear features from EEG signals. Microsyst Technol 25:1065–1076. https://doi.org/10.1007/s00542-018-4075-z
adatnezhad K, Boostani R, Ghanizadeh A (2011) Classification of BMD and ADHD patients using their EEG signals. Expert Syst Appl 38:1956–1963. https://doi.org/10.1016/j.eswa.2010.07.128
Erguzel TT, Sayar GH, Tarhan N (2016) Artificial intelligence approach to classify unipolar and bipolar depressive disorders. Neural Comput Appl 27:1607–1616. https://doi.org/10.1007/s00521-015-1959-z
Abdolzadegan D, Moattar MH, Ghoshuni M (2020) A robust method for early diagnosis of autism spectrum disorder from EEG signals based on feature selection and DBSCAN method. Biocybern Biomed Eng 40:482–493. https://doi.org/10.1016/j.bbe.2020.01.008
Djemal R, Alsharabi K, Ibrahim S, Alsuwailem A (2017) EEG-Based computer aided diagnosis of autism spectrum disorder using wavelet, entropy, and ANN. BioMed Res Int 2017. https://doi.org/10.1155/2017/9816591
Saeedi A, Saeedi M, Maghsoudi A, Shalbaf A (2021) Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolutional neural network and long short-term memory approach. Cogn Neurodyn 15:239–252. https://doi.org/10.1007/s11571-020-09619-0
Ay B, Yildirim O, Talo M, Baloglu UB, Aydin G, Puthankattil SD, Acharya UR (2019) Automated Depression Detection Using Deep Representation and Sequence Learning with EEG Signals. J Med Syst 43:1–12. https://doi.org/10.1007/s10916-019-1345-y
Thoduparambil PP, Dominic A, Varghese SM (2020) EEG-based deep learning model for the automatic detection of clinical depression. Phys Eng Sci Med 43(4):1349–1360. https://doi.org/10.1007/S13246-020-00938-4
Seal A, Bajpai R, Agnihotri J, Yazidi A, Herrera-Viedma E, Krejcar O (2021) DeprNet: A Deep Convolution Neural Network Framework for Detecting Depression Using EEG. IEEE Trans Instrum Meas 70. https://doi.org/10.1109/TIM.2021.3053999
Sandheep P, Vineeth S, Poulose M, Subha DP (2019) Performance analysis of deep learning CNN in classification of depression EEG signals. IEEE Region 10 Annual International Conference, Proceedings/TENCON, pp 1339–1344. https://doi.org/10.1109/TENCON.2019.8929254
Li X, Zhang X, Zhu J, Mao W, Sun S, Wang Z, Xia C, Hu B (2019) Depression recognition using machine learning methods with different feature generation strategies. Artif Intell Med 99:101696. https://doi.org/10.1016/j.artmed.2019.07.004
Khare SK, Bajaj V, Acharya UR (2021) SPWVD-CNN for Automated Detection of Schizophrenia Patients Using EEG Signals. IEEE Trans Instrum Meas 70. https://doi.org/10.1109/TIM.2021.3070608
Baygin M, Yaman O, Tuncer T, Dogan S, Barua PD, Acharya UR (2021) Automated accurate schizophrenia detection system using Collatz pattern technique with EEG signals. Biomed Signal Process Control 70:102936. https://doi.org/10.1016/j.bspc.2021.102936
Nikhil Chandran A, Sreekumar K, Subha DP (2021) EEG-Based Automated Detection of Schizophrenia Using Long Short-Term Memory (LSTM) Network Adv Mach Learn Comput Intell (Springer, Singapore), pp 229–236. https://doi.org/10.1007/978-981-15-5243-4_19
Moghaddari M, Lighvan MZ, Danishvar S (2020) Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG. Comput Methods Programs Biomed 197:105738. https://doi.org/10.1016/J.CMPB.2020.105738