Classification of Three Anesthesia Stages Based on Near-Infrared Spectroscopy Signals
The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.
Abstract
Proper monitoring of anesthesia stages can guarantee the safe performance of clinical surgeries. In this study, different anesthesia stages were classified using near-infrared spectroscopy (NIRS) signals with machine learning. The cerebral hemodynamic variables of right proximal oxyhemoglobin (HbO2) in maintenance (MNT), emergence (EM) and the consciousness (CON) stage were collected and then the differences between the three stages were compared by phase-amplitude coupling (PAC). Then combined with time-domain including linear (mean, standard deviation, max, min and range), nonlinear (sample entropy) and power in frequency-domain signal features, feature selection was performed and finally classification was performed by support vector machine (SVM) classifier. The results show that the PAC of the NIRS signal was gradually enhanced with the deepening of anesthesia level. A good three-classification accuracy of 69.27% was obtained, which exceeded the result of classification of any single category feature. These results indicate the feasibility of NIRS signals in performing three or even more anesthesia stage classifications, providing insight into the development of new anesthesia monitoring modalities.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“One major issue is the trade-off between model accuracy and interpretability. Simpler models such as logistic regression and decision trees are easier to explain but may lack the predictive power of complex neural networks [26,27].”
From Explainable AI in Clinical Decision Support Systems: A Meta-Analysis of Methods, Applications, and Usability Challenges (2025) · cites this paper as [27]
Citations
Cites
Peng, H., Long, F., & Ding, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.159 · Cited by 10,544 · cited 1×
“The Max-Relevance and Min-Redundancy (MRMR) algorithm based on mutual information [40], in which MRMR algorithm can be divided into mutual information difference (MID) algorithm and mutual information quotient (MIQ) algorithm according to the scheme of the optimized operator.”
MethodTheoretical and Empirical Analysis of ReliefF and RReliefF
Robnik-Šikonja, M., & Kononenko, I. (2003) · Machine Learning · doi:10.1023/a:1025667309714 · Cited by 3,025
Estimation of optical pathlength through tissue from direct time of flight measurement
Delpy, D. T., Cope, M., Zee, P. V. D., Arridge, S., Wray, S., & Wyatt, J. (1988) · Physics in Medicine and Biology · doi:10.1088/0031-9155/33/12/008 · Cited by 2,245 · cited 1×
“These digital signals were then used to calculate changes in brain hemodynamic variables such as Hb and HbO 2 concentrations using the modified Beer-Lambert law [32].”
MethodMeasuring Phase-Amplitude Coupling Between Neuronal Oscillations of Different Frequencies
Tort, A. B. L., Komorowski, R., Eichenbaum, H., & Kopell, N. (2010) · Journal of Neurophysiology · doi:10.1152/jn.00106.2010 · Cited by 1,363 · cited 1×
“Similarly, in the frequency domain, Phase-Amplitude Coupling (PAC), an adaptation of Kullback-Leibler (KL) distance, which can measure the coupling between the “phase modulating” and “amplitude modulated” frequency bands [24].”
BackgroundThe Influence of Age on Propofol Pharmacodynamics
Schnider, T. W., Minto, C. F., Shafer, S. L., Gambus, P. L., Andresen, C., Goodale, D. B., & Youngs, E. J. (1999) · Anesthesiology · doi:10.1097/00000542-199906000-00003 · Cited by 1,064 · cited 1×
“On the one hand, it may be related to the fast metabolism of propofol during the recovery stage of anesthesia [47].”
BackgroundCross-frequency coupling between neuronal oscillations
Jensen, O., & Colgin, L. L. (2007) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2007.05.003 · Cited by 991 · cited 1×
“…of the signal and time-domain SI features reflecting the linear features of the signal. a) PAC-related feature calculation: PAC is a form of cross frequency interaction that reflects the modulation of power in relatively high frequency bands by the phase in relatively low frequency bands [36].”
BackgroundElectroencephalogram signatures of loss and recovery of consciousness from propofol
Purdon, P. L., Pierce, E. T., Mukamel, E. A., Prerau, M. J., Walsh, J. L., Wong, K. F. K., Salazar-Gomez, A. F., Harrell, P. G., Sampson, A. L., Cimenser, A., et al. (2013) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1221180110 · Cited by 854 · cited 1×
“…in the slow-wave ( < 1 Hz) and alpha bands exhibited a fixed PAC pattern during multiple stages of unconsciousness induced by anesthetic agents [25], [26] Meanwhile, unlike the two categories of wakefulness and anesthesia stages mentioned above, in clinical practice, there exists a semi-or…”
BackgroundScholkmann, F., Spichtig, S., Muehlemann, T., & Wolf, M. (2010) · Physiological Measurement · doi:10.1088/0967-3334/31/5/004 · Cited by 683 · cited 1×
“Then for complex movement artifacts, the movement artifact reduction algorithm (MARA) was used to remove them [34].”
MethodFeature selection using Joint Mutual Information Maximisation
Bennasar, M., Hicks, Y., & Setchi, R. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.07.007 · Cited by 659 · cited 2×
“The common “filter” methods are achieved by measuring the direct relationship between the independent variable and the target variable, including Relief, Max-Relevance and Min-Redundancy (MRMR), Fisher Score (FS), etc. [29], [30], [31].”
MethodPrevention of Intraoperative Awareness in a High-Risk Surgical Population
Avidan, M. S., Jacobsohn, E., Glick, D., Burnside, B. A., Zhang, L., Villafranca, A., Karl, L., Kamal, S., Torres, B., O'Connor, M., et al. (2011) · New England Journal of Medicine · doi:10.1056/nejmoa1100403 · Cited by 581 · cited 1×
“Each year, tens of millions of patients undergo surgery, and accidental intraoperative awareness may affect up to 1% of patients world-wide [2].”
Background
Cited by
Abbas, Q., Jeong, W., & Lee, S. W. (2025) · Healthcare · doi:10.3390/healthcare13172154 · Cited by 236
“Simpler models such as logistic regression and decision trees are easier to explain but may lack the predictive power of complex neural networks [26,27].”
Rani, S., Kumar, R., Panda, B. S., Kumar, R., Muften, N. F., Abass, M. A., & Šajić, J. L. (2025) · Diagnostics · doi:10.3390/diagnostics15151914 · Cited by 91
“Recent work has illustrated how various ML methods, covering ensemble classifiers and support vector machines to DL models and federated learning, can be efficiently used in multiple clinical fields [59,60].”
2D material-based infrared photodetectors: recent progress, challenges, and perspectives
Zulfiqar, M. W., Nisar, S., Dastgeer, G., Rabeel, M., Ghazanfar, H., Ali, A., Imran, M., Kim, H., & Kim, D. (2025) · Nanoscale · doi:10.1039/d5nr01920f · Cited by 42
Faizan, M., Han, C., & Lee, S. W. (2025) · Healthcare · doi:10.3390/healthcare13182319 · Cited by 56
“These technologies provide real-time data for both users and clinicians, allowing for early detection of anomalies and proactive interventions [17,18].”
Ahmad, A. Y. A. B., Alzubi, J. A. A., Vasanthan, M., Kondaveeti, S. B., Shreyas, J., & Priyanka, T. P. (2025) · Scientific Reports · doi:10.1038/s41598-025-96827-5 · Cited by 25
“In 2024, Liu et al. 28 have investigated the different stages of anesthesia using Near-Infrared Spectroscopy (NIRS) signals with machine learning.”
Metadata
- Authors
- Liu, Z., Si, L., Shi, S., Li, J., Zhu, J., Lee, W. H., Lo, S.-L., Yan, X., Chen, B., Fu, F., Zheng, Y., & Wang, G.
- Affiliations
- Ministry of Civil Affairs (CN)
- Xi'an Honghui Hospital (CN)
- Shaanxi Provincial People's Hospital (CN)
- Kyung Hee University (KR)
- Macau University of Science and Technology (MO)
- Xi'an Jiaotong University (CN)
- Air Force Medical University (CN)
- ORCID
- Venue
- IEEE Journal of Biomedical and Health Informatics
- Published
- 2024-09
- Volume
- 28
- Issue
- 9
- Pages
- 5270-5279
- ISSN
- 2168-2194 (ISSN-L)
- 2168-2208
- OpenAlex
- W4399342664
- Semantic Scholar
- 3cd7febe6b800ca6934d4f3451c31102e1277ecf
- Cited by
- 71
- References
- 49
- Citations by year
- 2026: 11 · 2025: 59 · 2024: 1
- FWCI
- 18.01
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Journal of Biomedical and Health Informatics (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (32071372, 62271385)
- National Key R&D Program of China (2022YFC2503803)
- Sichuan Provincial Science and Technology Support Program (2022YFS0030)
- Natural Science Basic Research Program of Shaanxi (2022JM-526)
- Science and Technology Program of Xi'an under Program (21YXYJ0093)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Optical Imaging and Spectroscopy Techniques
- Health Sciences › Medicine › Anesthesiology and Pain Medicine › Anesthesia and Sedative Agents
- Physical Sciences › Chemistry › Analytical Chemistry › Spectroscopy and Chemometric Analyses
- Keywords
- depth of anesthesia monitoring, near-infrared spectroscopy, phase-amplitude coupling, oxyhemoglobin, cerebral hemodynamics, emergence from anesthesia, anesthesia maintenance, sample entropy, feature selection, support vector machine, signal classification
- MeSH terms
- Adult, Anesthesia, Female, Humans, Male, Middle Aged, Signal Processing, Computer-Assisted, Monitoring, Intraoperative, Spectroscopy, Near-Infrared, Young Adult, Support Vector Machine
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Classification of Three Anesthesia Stages Based on Near-Infrared Spectroscopy Signals. https://app.cochat.ai/papers/10.1109/jbhi.2024.3409163
- The paper
- Liu, Z., Si, L., Shi, S., Li, J., Zhu, J., Lee, W. H., Lo, S.-L., Yan, X., Chen, B., Fu, F., Zheng, Y., & Wang, G. (2024). Classification of Three Anesthesia Stages Based on Near-Infrared Spectroscopy Signals. IEEE Journal of Biomedical and Health Informatics. https://doi.org/10.1109/jbhi.2024.3409163
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.