Artificial intelligence and EEG during anesthesia: ideal match or fleeting bond?

Abstract

Artificial intelligence (AI) has shown considerable potential in perioperative monitoring, particularly in its application to electroencephalogram (EEG) analysis for assessing the depth of anesthesia. AI methods may enable the dynamic recognition of complex time-frequency EEG patterns and the adaptation of monitoring strategies to patient-specific brain responses. Convolutional neural networks, artificial neural networks, and hybrid deep learning models have reported encouraging results in detecting anesthetic states, estimating bispectral index values, and identifying relevant EEG features - such as alpha-delta shifts or burst suppression - without relying on manual feature engineering. Parallel efforts using virtual and augmented reality platforms suggest possible benefits for anesthesiologist training in EEG interpretation and pharmacologic titration. Despite these advances, important limitations constrain clinical translation. A major challenge is the absence of standardized EEG pattern definitions across anesthetic agents and patient groups, limiting model generalizability. Restricted interoperability between EEG monitors and electronic health records, coupled with proprietary data formats, reduces access to raw EEG signals and hampers large-scale development. Privacy and governance requirements add further barriers to data integration. Methodologically, many studies are affected by insufficient internal validation, suboptimal reporting, and testing in experimental rather than real-world conditions, reducing their translational value. While AI could eventually improve anesthetic precision and safety through EEG-guided approaches, realizing this potential will require transparent algorithms, multicenter and heterogeneous datasets, and robust interoperability and data-sharing standards. Only through such coordinated efforts can these tools evolve from promising research applications into reliable components of routine anesthetic care.

Keywords

Artificial intelligence / AI / anesthesia / DoA / pEEG / machine learning / ML

References

[1] Kim MC,Brown EN.Role of electroencephalogram oscillations and the spectrogram in monitoring anaesthesia.BJA Educ2020;20:166-72 PMCID:PMC7807831

[2] Lobo FA,Nardiello I,Osborn IP.Electroencephalogram monitoring in anesthesia practice.Curr Anesthesiol Rep2021;11:169-80

[3] Rampil IJ.A primer for EEG signal processing in anesthesia.Anesthesiology1998;89:980-1002

[4] Purdon PL,Pavone KJ.Clinical electroencephalography for anesthesiologists: part I: background and basic signatures.Anesthesiology2015;123:937-60 PMCID:PMC4573341

[5] Obert DP,Sleigh J.The first derivative of the electroencephalogram facilitates tracking of electroencephalographic alpha band activity during general anesthesia.Anesth Analg2022;134:1062-71

[6] Fahy BG.The technology of processed electroencephalogram monitoring devices for assessment of depth of anesthesia.Anesth Analg2018;126:111-7

[7] Mashour GA.Consciousness, anesthesia, and the thalamocortical system.Anesthesiology2013;118:13-5

[8] Pollak M,Röhr V,Spies C.Electroencephalogram biomarkers from anesthesia induction to identify vulnerable patients at risk for postoperative delirium.Anesthesiology2024;140:979-89

[9] Bruzzone MJ,Walker J.Electroencephalographic measures of delirium in the perioperative setting: a systematic review.Anesth Analg2025;140:1127-39

[10] Koch S,Chakravarty S.BioCog Study GroupCognitive impairment is associated with absolute intraoperative frontal α-band power but not with baseline α-band power: a pilot study.Dement Geriatr Cogn Disord2019;48:83-92 PMCID:PMC7367434

[11] Alfonso JCF,Antonio AFM.Comparison of bioelectric signals and their applications in artificial intelligence: a review.Computers2025;14:145

[12] Yoon D,Choi BJ,Han CH.Discovering hidden information in biosignals from patients using artificial intelligence.Korean J Anesthesiol2020;73:275-84 PMCID:PMC7403115

[13] Lee YJ,Kim H,Yeo W.Artificial intelligence on biomedical signals: technologies, applications, and future directions.Med-X2024;2:43

[14] Bergmann D. What is vector embedding? Available from: https://www.ibm.com/think/topics/vector-embedding#:~:text=Vector%20embeddings%20are%20numerical%20representations,(ML)%20models%20can%20process [accessed 11 December 2025].

[15] LeCun Y,Hinton G.Deep learning.Nature2015;521:436-44

[16] Gomez-Quintana S,Factor A,Temko A.A method for AI assisted human interpretation of neonatal EEG.Sci Rep2022;12:10932 PMCID:PMC9243143

[17] Cao Z.A review of artificial intelligence for EEG‐based brain-computer interfaces and applications.Brain Sci Adv2020;6:162-70

[18] Craik A,Contreras-Vidal JL.Deep learning for electroencephalogram (EEG) classification tasks: a review.J Neural Eng2019;16:031001

[19] Krizhevsky A,Hinton GE.ImageNet classification with deep convolutional neural networks.Commun ACM2017;60:84-90

[20] Castellano G.Deep learning approaches to pattern extraction and recognition in paintings and drawings: an overview.Neural Comput Appl2021;33:12263-82

[21] Lopes S,Guimarães-Pereira L.Artificial intelligence and its clinical application in anesthesiology: a systematic review.J Clin Monit Comput2024;38:247-59 PMCID:PMC10995017

[22] Ram M,Moulaei K.Application of artificial intelligence in chronic myeloid leukemia (CML) disease prediction and management: a scoping review.BMC Cancer2024;24:1026 PMCID:PMC11337640

[23] Praveena D, Angelin Sarah D, Thomas George S. Deep learning techniques for EEG signal applications - a review.IETE J Res2022;68:3030-7

[24] Boonyakitanont P,Chomtho K.A comparison of deep neural networks for seizure detection in EEG signals.BioRxiv2019:702654

[25] Gu Y,Hagihira S.Use of multiple EEG features and artificial neural network to monitor the depth of anesthesia.Sensors2019;19:2499 PMCID:PMC6603666

[26] Jiang GJA,Abbod MF.Sample entropy analysis of EEG signals via artificial neural networks to model patients’ consciousness level based on anesthesiologists experience.Biomed Res Int2015;2015:343478 PMCID:PMC4337052

[27] Lee HC,Chung EJ.Prediction of bispectral index during target-controlled infusion of propofol and remifentanil: a deep learning approach.Anesthesiology2018;128:492-501

[28] Gambus P.Artificial intelligence for everyone.Anesthesiology2018;128:431-3

[29] Yu R,Xu M.SQI-DOANet: electroencephalogram-based deep neural network for estimating signal quality index and depth of anaesthesia.J Neural Eng2024;21:046031

[30] Afshar S,Sanei S.A combinatorial deep learning structure for precise depth of anesthesia estimation from EEG signals.IEEE J Biomed Health Inform2021;25:3408-15

[31] Haghighi SJ,Hatzinakos D.40-Hz ASSR for measuring depth of anaesthesia during induction phase.IEEE J Biomed Health Inform2018;22:1871-82

[32] Yu H,Lee J,Hwang B.Deep neural network-based empirical mode decomposition for motor imagery EEG classification.IEEE Trans Neural Syst Rehabil Eng2024;32:3647-56

[33] Madanu R,Abbod MF,Shieh JS.Depth of anesthesia prediction via EEG signals using convolutional neural network and ensemble empirical mode decomposition.Math Biosci Eng2021;18:5047-68

[34] Alsafy I.Developing a robust model to predict depth of anesthesia from single channel EEG signal.Phys Eng Sci Med2022;45:793-808 PMCID:PMC9448694

[35] Diykh M,Wen P.Complex networks approach for depth of anesthesia assessment.Measurement2018;119:178-89

[36] Li R,Liu J,Li C.Monitoring depth of anesthesia based on hybrid features and recurrent neural network.Front Neurosci2020;14:26 PMCID:PMC7020827

[37] Shalbaf A,Saffar M.Monitoring the level of hypnosis using a hierarchical SVM system.J Clin Monit Comput2020;34:331-8

[38] Gambús PL,Jospin M.Modeling the effect of propofol and remifentanil combinations for sedation-analgesia in endoscopic procedures using an Adaptive Neuro Fuzzy Inference System (ANFIS).Anesth Analg2011;112:331-9

[39] Jensen EW,López A.Monitoring hypnotic effect and nociception with two EEG-derived indices, qCON and qNOX, during general anaesthesia.Acta Anaesthesiol Scand2014;58:933-41

[40] Vellinga R,van Amsterdam K.Implementation of a Bayesian based advisory tool for target-controlled infusion of propofol using qCON as control variable.J Clin Monit Comput2024;38:519-29

[41] Tacke M,Mueller M,Jordan D.Machine learning for a combined electroencephalographic anesthesia index to detect awareness under anesthesia.PLoS One2020;15:e0238249 PMCID:PMC7449480

[42] Zhan J,Duan ZX.Heart rate variability-derived features based on deep neural network for distinguishing different anaesthesia states.BMC Anesthesiol2021;21:66 PMCID:PMC7923817

[43] U. S. Food & Drug Administration. Artificial intelligence and machine learning (ai/ml)-enabled medical devices. Available from: https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices [accessed 11 December 2025].

[44] Fan W,Shi D,Kou L.Multi-agent modeling and simulation in the AI age.Tsinghua Sci Technol2021;26:608-24

[45] Elendu C,Okatta AU.The impact of simulation-based training in medical education: a review.Medicine2024;103:e38813 PMCID:PMC11224887

[46] Bellini V,Bignami E.Metaverse and anesthesia.Anesth Analg2024;138:491-4

[47] Dai CP.Educational applications of artificial intelligence in simulation-based learning: a systematic mapping review.Comput Educ Artif Intell2022;3:100087

[48] Wang Z,Zhan Y.Hypnos: a domain-specific large language model for anesthesiology.Neurocomputing2025;624:129389

[49] Kundra P.Amalgamation of artificial intelligence and simulation in anaesthesia training: much-needed future endeavour.Indian J Anaesth2024;68:8-10 PMCID:PMC10893798

[50] Javvaji CK,Vagha JD,Kommareddy A.Immersive innovations: exploring the diverse applications of virtual reality (VR) in healthcare.Cureus2024;16:e56137 PMCID:PMC11016331

[51] Lungu AJ,Claesen L,Egger J.A review on the applications of virtual reality, augmented reality and mixed reality in surgical simulation: an extension to different kinds of surgery.Expert Rev Med Devices2021;18:47-62

[52] McKnight RR,Buck JS,Hsu JR.Virtual reality and augmented reality-translating surgical training into surgical technique.Curr Rev Musculoskelet Med2020;13:663-74 PMCID:PMC7661680

[53] Paro MR,Bulsara KR.History of virtual reality and augmented reality in neurosurgical training.World Neurosurg2022;167:37-43

[54] Heinrich F,Schmidt G.HoloPointer: a virtual augmented reality pointer for laparoscopic surgery training.Int J Comput Assist Radiol Surg2021;16:161-8 PMCID:PMC7822765

[55] Moo-Young J,Kapralos B,Alam F.Development of unity simulator for epidural insertion training for replacing current lumbar puncture simulators.Cureus2021;13:e13409

[56] Savage M,Turbitt L.The educational impact of technology-enhanced learning in regional anaesthesia: a scoping review.Br J Anaesth2024;133:400-15 PMCID:PMC7978159

[57] Bejani M,Samad-Soltani T,Rezaei-Hachesu P.The effects of virtual reality-based bronchoscopy simulator on learning outcomes of medical trainees: a systematic review.Health Sci Rep2023;6:e1398 PMCID:PMC10320745

[58] Bracq MS,Jannin P.Virtual reality simulation in nontechnical skills training for healthcare professionals: a systematic review.Simul Healthc2019;14:188-94

[59] Evans LV,Shah TD.Simulation training in central venous catheter insertion: improved performance in clinical practice.Acad Med2010;85:1462-9

[60] Björn M. Development of an effective pedagogical EEG simulator: design-based research project among biomedical laboratory science students. Ph.D. Dissertation, University of Eastern Finland, Joensuu, Finland, 2022. Available from: https://erepo.uef.fi/server/api/core/bitstreams/575e4b96-e61e-48f4-a44f-7585be1cd91a/content [accessed 11 December 2025].

[61] Yun WJ,Jung S,Lee HC.Deep reinforcement learning-based propofol infusion control for anesthesia: a feasibility study with a 3000-subject dataset.Comput Biol Med2023;156:106739

[62] Bombardieri AM,Stevens T.Practical training of anesthesia clinicians in electroencephalogram-based determination of hypnotic depth of general anesthesia.Anesth Analg2020;130:777-86

[63] Barnard JP,Voss LJ.Can anaesthetists be taught to interpret the effects of general anaesthesia on the electroencephalogram?.Br J Anaesth2007;99:532-7

[64] Fahy BG,Johnson WT.An online, interactive, screen-based simulator for learning basic EEG interpretation.Neurol Sci2021;42:1017-22

[65] Fahy BG,Cibula JE.Impact of simulation on critical care fellows’ electroencephalography learning.Cureus2022;14:e24439 PMCID:PMC9128666

[66] Singh PM,Trikha A.Virtual reality in anesthesia “simulation”.Anesth Essays Res2012;6:134-9 PMCID:PMC4173452

[67] Alam F.A new virtual world?.Anesth Analg2022;135:230-8 PMCID:PMC9259048

[68] Venkatesan M,Ryan JR.Virtual and augmented reality for biomedical applications.Cell Rep Med2021;2:100348 PMCID:PMC8324499

[69] Farrell K. An overview of clinical applications of virtual and augmented reality. Canadian Agency for Drugs and Technologies in Health; 2023. Report No.: EH0011. Available from: https://www.ncbi.nlm.nih.gov/books/NBK596298/ [accessed 11 December 2025].

[70] Stanney KM,Drexler JM.Cybersickness is not simulator sickness.Proc Hum Factors Ergon Soc Annu Meet1997;41:1138-42

[71] Spiegel JS.The ethics of virtual reality technology: social hazards and public policy recommendations.Sci Eng Ethics2018;24:1537-50

[72] Lowell VL.Authentic learning and fidelity in virtual reality learning experiences for self-efficacy and transfer.Comput Educ X Real2023;2:100017

[73] Arthur T,Williams C.Examining the validity and fidelity of a virtual reality simulator for basic life support training.BMC Digit Health2023;1:16

[74] Corrêa NK,Santos JW.Worldwide AI ethics: a review of 200 guidelines and recommendations for AI governance.Patterns2023;4:100857 PMCID:PMC10591196

[75] Hight D,Ugen G.Five commercial ‘depth of anaesthesia’ monitors provide discordant clinical recommendations in response to identical emergence-like EEG signals.Br J Anaesth2023;130:536-45

[76] McCulloch TJ.Depth of anaesthesia monitoring: time to reject the index?.Br J Anaesth2023;131:196-9

[77] Introna M,Carozzi C.Improving the benefit of processed EEG monitors: it’s not about the car but the driver.J Clin Monit Comput2023;37:723-5 PMCID:PMC10175406

[78] U. S. Centers for Disease Control and Prevention. Health Insurance Portability and Accountability Act of 1996 (HIPAA). Available from: https://www.cdc.gov/phlp/php/resources/health-insurance-portability-and-accountability-act-of-1996-hipaa.html [accessed 11 December 2025].

[79] House of Commons of Canada. Bill-C72. Available from: https://www.parl.ca/documentviewer/en/44-1/bill/C-72/first-reading [accessed 11 December 2025].

[80] Torab-Miandoab A,Jodati A.Interoperability of heterogeneous health information systems: a systematic literature review.BMC Med Inform Decis Mak2023;23:18 PMCID:PMC9875417

[81] Jendle J,Choudhary P.A narrative commentary about interoperability in medical devices and data used in diabetes therapy from an academic EU/UK/US perspective.Diabetologia2024;67:236-45 PMCID:PMC10789828

[82] European Commission. European Health Data Space Regulation (EHDS). Available from: https://health.ec.europa.eu/ehealth-digital-health-and-care/european-health-data-space_en#more-information [accessed 11 December 2025].

[83] European Commission. Data Act: Proposal for a Regulation on harmonised rules on fair access to and use of data. Available from: https://digital-strategy.ec.europa.eu/en/library/data-act-proposal-regulation-harmonised-rules-fair-access-and-use-data [accessed 11 December 2025].

[84] Connor CW.A forensic disassembly of the BIS monitor.Anesth Analg2020;131:1923-33 PMCID:PMC7669712

[85] Connor CW.OpenBSR: an open algorithm for burst suppression rate concordant with the BIS monitor.Anesth Analg2025;140:220-3 PMCID:PMC11649468

[86] Lipp M,Kreuzer M.Substance-dependent EEG during recovery from anesthesia and optimization of monitoring.J Clin Monit Comput2024;38:603-12 PMCID:PMC11164797

[87] Karippacheril JG.Data acquisition from S/5 GE Datex anesthesia monitor using VSCapture.J Anaesthesiol Clin Pharmacol2013;29:423-4 PMCID:PMC3788264

[88] Vistisen ST,Enevoldsen J.VitalDB: fostering collaboration in anaesthesia research.Br J Anaesth2021;127:184-7

[89] Lee HC,Yoon SB,Park D.VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients.Sci Data2022;9:279 PMCID:PMC9178032

[90] GitHub. Karippacheril JG. VSCaptureBISV. Available from: https://github.com/xeonfusion/VSCaptureBISV [accessed 11 December 2025].

[91] SourceForge. Karippacheril JG. VitalSignsCapture. Available from: https://sourceforge.net/projects/vscapture/ [accessed 11 December 2025].

[92] Lichtenfeld F,Hinzmann D,Schneider G.The influence of electromyographic on electroencephalogram-based monitoring: putting the forearm on the forehead.Anesth Analg2024;138:1285-94

[93] Van Beleen T. EDFbrowser. Available from: https://www.teuniz.net/edfbrowser/ [accessed 11 December 2025].

[94] Schmierer T,Li Y.Harnessing machine learning for EEG signal analysis: Innovations in depth of anaesthesia assessment.Artif Intell Med2024;151:102869

[95] Zeng S,Xu W.Personalized anesthesia and precision medicine: a comprehensive review of genetic factors, artificial intelligence, and patient-specific factors.Front Med2024;11:1365524 PMCID:PMC11111965

[96] Pose F,Campanini G,Redelico FO.Using EEG total energy as a noninvasively tracking of intracranial (and cerebral perfussion) pressure in an animal model: a pilot study.Heliyon2024;10:e28544 PMCID:PMC11004541

[97] Li W,Dicks E.Data-driven retrieval of population-level EEG features and their role in neurodegenerative diseases.Brain Commun2024;6:fcae227 PMCID:PMC11289732

[98] Laferrière-Langlois P,Jeffries S,Espitalier F.Depth of anesthesia and nociception monitoring: current state and vision for 2050.Anesth Analg2024;138:295-307

[99] Eaneff S,Butte AJ.The case for algorithmic stewardship for artificial intelligence and machine learning technologies.JAMA2020;324:1397-8

[100] Enevoldsen J.Performance of the hypotension prediction index may be overestimated due to selection bias.Anesthesiology2022;137:283-9

[101] Davies SJ,Jian Z,Scheeren TWL.Ability of an arterial waveform analysis-derived hypotension prediction index to predict future hypotensive events in surgical patients.Anesth Analg2020;130:352-9

[102] Montomoli J,Cascella M.Algor-ethics: charting the ethical path for AI in critical care.J Clin Monit Comput2024;38:931-9 PMCID:PMC11297831

[103] Wilkinson J,Murray EJ.Time to reality check the promises of machine learning-powered precision medicine.Lancet Digit Health2020;2:e677-80 PMCID:PMC9060421

[104] Introna M,Gentile A.Target controlled infusion in the intensive care unit: a scoping review.J Clin Monit Comput2025;

[105] Collins GS,Altman DG.Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement.BMJ2015;350:g7594