Abstract
This study explored the value of nonlinear features extracted from EEG signals to facilitate the assessment of patients with disorders of consciousness (DOC) with limited communication capacity. We utilized a dataset comprising 104 participants, 56 with vegetative state (VS)/unresponsive wakefulness syndrome (UWS) and 48 in a minimally conscious state (MCS). For each participant, we computed channel-wise approximate entropy (ApEn) from EEG time-series data using a sliding window approach under two experimental paradigms: resting state and preferred music stimulation. These nonlinear measures were then spatially interpolated to generate topographical maps. Both resting state and preferred music stimulation data were processed as 1-second epochs using identical convolutional neural networks (CNN) architectures. The classification performance and validity of the CNN were compared against support vector machine (SVM) and generalized regression neural network (GRNN) models. ApEn in the resting state and under stimulation with preferred music correlated with the Coma Recovery Scale-Revised scores in patients with DOC, showing varied regional responses. Notably, the CNNs resulted in a positive diagnostic performance with an accuracy of 90.00% and an AUC of 0.902. The CNN was better than the SVM and GRNN in differentiating between the VS/UWS and MCS states. This study offers a convenient and accurate method for detecting awareness in patients with VS/UWS and MCS using ApEn features in the resting state and under preferred music stimulation using deep learning.
Data availability
Data supporting the results of this study are available on request from the corresponding authors. This data will not be made public due to privacy or ethical restrictions.
References
Thibaut, A., Schiff, N., Giacino, J., Laureys, S. & Gosseries, O. Therapeutic interventions in patients with prolonged disorders of consciousness. Lancet Neurol. 18, 600–614. https://doi.org/10.1016/s1474-4422(19)30031-6 (2019).
Kondziella, D. et al. European academy of neurology guideline on the diagnosis of coma and other disorders of consciousness. Eur. J. Neurol. 27, 741–756. https://doi.org/10.1111/ene.14151 (2020).
Schnakers, C. et al. Diagnostic accuracy of the vegetative and minimally conscious state: clinical consensus versus standardized neurobehavioral assessment. BMC Neurol. 9, 35. https://doi.org/10.1186/1471-2377-9-35 (2009).
Løvstad, M. et al. Reliability and diagnostic characteristics of the JFK coma recovery scale-revised: exploring the influence of rater’s level of experience. J. Head Trauma Rehabil. 25, 349–356. https://doi.org/10.1097/HTR.0b013e3181cec841 (2010).
Hermann, B. et al. Multimodal FDG-PET and EEG assessment improves diagnosis and prognostication of disorders of consciousness. Neuroimage Clin. 30, 102601. https://doi.org/10.1016/j.nicl.2021.102601 (2021).
Jansen, B. H. Nonlinear dynamics and quantitative EEG analysis. Electroencephalogr. Clin. Neurophysiol. Suppl. 45, 39–56 (1996).
Liu, B. et al. Outcome prediction in unresponsive wakefulness syndrome and minimally conscious state by Non-linear dynamic analysis of the EEG. Front. Neurol. 12, 510424. https://doi.org/10.3389/fneur.2021.510424 (2021).
Ma, Y., Shi, W., Peng, C. K. & Yang, A. C. Nonlinear dynamical analysis of sleep electroencephalography using fractal and entropy approaches. Sleep. Med. Rev. 37, 85–93. https://doi.org/10.1016/j.smrv.2017.01.003 (2018).
Liu, B. et al. tDCS-EEG for predicting outcome in patients with unresponsive wakefulness syndrome. Front. Neurosci. 16, 771393. https://doi.org/10.3389/fnins.2022.771393 (2022).
Wu, D. Y. et al. Measuring interconnection of the residual cortical functional Islands in persistent vegetative state and minimal conscious state with EEG nonlinear analysis. Clin. Neurophysiol. 122, 1956–1966. https://doi.org/10.1016/j.clinph.2011.03.018 (2011).
Pincus, S. M. Irregularity and asynchrony in biologic network signals. Methods Enzymol. 321, 149–182. https://doi.org/10.1016/s0076-6879(00)21192-0 (2000).
Sarà, M. et al. Functional isolation within the cerebral cortex in the vegetative state: a nonlinear method to predict clinical outcomes. Neurorehabil Neural Repair. 25, 35–42. https://doi.org/10.1177/1545968310378508 (2011).
Stefan, S. et al. Consciousness indexing and outcome prediction with Resting-State EEG in severe disorders of consciousness. Brain Topogr. 31, 848–862. https://doi.org/10.1007/s10548-018-0643-x (2018).
Zhang, X. et al. Multi-Target and Multi-Session transcranial direct current stimulation in patients with prolonged disorders of consciousness: A controlled study. Front. Neurosci. 15, 641951. https://doi.org/10.3389/fnins.2021.641951 (2021).
Qu, S. et al. Analyzing brain-activation responses to auditory stimuli improves the diagnosis of a disorder of consciousness by non-linear dynamic analysis of the EEG. Sci. Rep. 14, 17446. https://doi.org/10.1038/s41598-024-67825-w (2024).
Ma, X. et al. How well do neural signatures of resting-state EEG detect consciousness? A large-scale clinical study. Hum. Brain Mapp. 45, e26586. https://doi.org/10.1002/hbm.26586 (2024).
Qureshi, A. Y. & Stevens, R. D. Mapping the unconscious brain: insights from advanced neuroimaging. J. Clin. Neurophysiol. 39, 12–21. https://doi.org/10.1097/wnp.0000000000000846 (2022).
Ling, Y. et al. Cortical responses to auditory stimulation predict the prognosis of patients with disorders of consciousness. Clin. Neurophysiol. 153, 11–20. https://doi.org/10.1016/j.clinph.2023.06.002 (2023).
Demertzi, A. et al. Intrinsic functional connectivity differentiates minimally conscious from unresponsive patients. Brain 138, 2619–2631. https://doi.org/10.1093/brain/awv169 (2015).
Çevik, K. & Namik, E. Effect of auditory stimulation on the level of consciousness in comatose patients admitted to the intensive care unit: A randomized controlled trial. J. Neurosci. Nurs. 50, 375–380. https://doi.org/10.1097/jnn.0000000000000407 (2018).
Li, M. A., Han, J. F. & Yang, J. F. Automatic feature extraction and fusion recognition of motor imagery EEG using multilevel multiscale CNN. Med. Biol. Eng. Comput. 59, 2037–2050. https://doi.org/10.1007/s11517-021-02396-w (2021).
Craik, A., He, Y. & Contreras-Vidal, J. L. Deep learning for electroencephalogram (EEG) classification tasks: a review. J. Neural Eng. 16, 031001. https://doi.org/10.1088/1741-2552/ab0ab5 (2019).
Lawhern, V. J. et al. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces. J. Neural Eng. 15, 056013. https://doi.org/10.1088/1741-2552/aace8c (2018).
Ding, L. et al. Predicting functional outcome in patients with acute brainstem infarction using deep neuroimaging features. Eur. J. Neurol. 29, 744–752. https://doi.org/10.1111/ene.15181 (2022).
Aellen, F. M. et al. Auditory stimulation and deep learning predict awakening from coma after cardiac arrest. Brain 146, 778–788. https://doi.org/10.1093/brain/awac340 (2023).
Stender, J. et al. Diagnostic precision of PET imaging and functional MRI in disorders of consciousness: a clinical validation study. Lancet (London England). 384, 514–522. https://doi.org/10.1016/s0140-6736(14)60042-8 (2014).
Nakamura, S. et al. Analysis of music-brain interaction with simultaneous measurement of regional cerebral blood flow and electroencephalogram beta rhythm in human subjects. Neurosci. Lett. 275, 222–226. https://doi.org/10.1016/s0304-3940(99)00766-1 (1999).
Castro, M. et al. Boosting cognition with music in patients with disorders of consciousness. Neurorehabil Neural Repair. 29, 734–742. https://doi.org/10.1177/1545968314565464 (2015).
Pincus, S. M., Goldberger, A. L. & H1643-1656. Physiological time-series analysis: what does regularity quantify? Am. J. Physiol. 266 https://doi.org/10.1152/ajpheart.1994.266.4.H1643 (1994).
Bruhn, J., Röpcke, H. & Hoeft, A. Approximate entropy as an electroencephalographic measure of anesthetic drug effect during desflurane anesthesia. Anesthesiology 92, 715–726. https://doi.org/10.1097/00000542-200003000-00016 (2000).
Wu, D. Y. et al. Application of nonlinear dynamics analysis in assessing unconsciousness: a preliminary study. Clin. Neurophysiol. 122, 490–498. https://doi.org/10.1016/j.clinph.2010.05.036 (2011).
Cai, L. et al. Assessment of impaired consciousness using EEG-based connectivity features and convolutional neural networks. Cogn. Neurodyn. 18, 919–930. https://doi.org/10.1007/s11571-023-09944-0 (2024).
Kingma, D., Ba, J. & Adam A method for stochastic optimization: Published as a conference paper at ICLR. Computer Science. 7, 12. (2015)
Rzempoluck, E. J. Neural network classification of EEG during camouflaged object identification. Int. J. Med. Inf. 44, 169–175. https://doi.org/10.1016/s1386-5056(97)85798-x (1997).
Liu, Q., Deng, J. & Liu, M. Classification models for predicting the antimalarial activity against plasmodium falciparum. SAR QSAR Environ. Res. 31, 313–324. https://doi.org/10.1080/1062936x.2020.1740890 (2020).
Qu, S. et al. Optimizing acute stroke outcome prediction models: comparison of generalized regression neural networks and logistic regressions. PLoS One. 17, e0267747. https://doi.org/10.1371/journal.pone.0267747 (2022).
Wu, M. et al. Effect of acoustic stimuli in patients with disorders of consciousness: a quantitative electroencephalography study. Neural Regen Res. 13, 1900–1906. https://doi.org/10.4103/1673-5374.238622 (2018).
Song, M. et al. Prognostic models for prolonged disorders of consciousness: an integrative review. Cell. Mol. Life Sci. 77, 3945–3961. https://doi.org/10.1007/s00018-020-03512-z (2020).
Heine, L. et al. Exploration of functional connectivity during preferred music stimulation in patients with disorders of consciousness. Front. Psychol. 6, 1704. https://doi.org/10.3389/fpsyg.2015.01704 (2015).
Wang, Y., Chen, S., Xia, X., Peng, Y. & Wu, B. Altered functional connectivity and regional brain activity in a triple-network model in minimally conscious state and vegetative-state/unresponsive wakefulness syndrome patients: A resting-state functional magnetic resonance imaging study. Front. Behav. Neurosci. 16, 1001519. https://doi.org/10.3389/fnbeh.2022.1001519 (2022).
Usami, N. et al. Cerebral glucose metabolism in patients with chronic disorders of consciousness. Can. J. Neurol. Sci. 50, 719–729. https://doi.org/10.1017/cjn.2022.301 (2023).
Yin, J. et al. Effects of different frequencies music on cortical responses and functional connectivity in patients with minimal conscious state. J. Biophotonics. 17, e202300427. https://doi.org/10.1002/jbio.202300427 (2024).
Jiang, L. et al. A deep learning-based model for prediction of hemorrhagic transformation after stroke. Brain Pathol. 33, e13023. https://doi.org/10.1111/bpa.13023 (2023).
Jonas, S. et al. EEG-based outcome prediction after cardiac arrest with convolutional neural networks: performance and visualization of discriminative features. Hum. Brain. Mapp. 40, 4606–4617. https://doi.org/10.1002/hbm.24724 (2019).
Cai, H. et al. Decoding musical neural activity in patients with disorders of consciousness through Self-Supervised contrastive domain generalization. Affective Computing, IEEE Transactions on,16(2):726-743. http://doi.10.1109/TAFFC.2024.3462603 (2025).
Pan, J., Cai, H., Huang, H., He, Y. & Li, Y. Multiple scale convolutional Few-Shot learning networks for online P300-Based Brain–Computer interface and its application to patients with disorder of consciousness. IEEE Trans. Instrum. Meas. 72, 1–16. https://doi.org/10.1109/TIM.2023.3267367 (2023).
Yang, H. et al. Precise detection of awareness in disorders of consciousness using deep learning framework. NeuroImage 290, 120580. https://doi.org/10.1016/j.neuroimage.2024.120580 (2024).
Liang, Z. et al. Constructing a consciousness meter based on the combination of Non-Linear measurements and genetic Algorithm-Based support vector machine. IEEE Trans. Neural Syst. Rehabil Eng. 28, 399–408. https://doi.org/10.1109/tnsre.2020.2964819 (2020).
Zheng, Z. S., Reggente, N., Lutkenhoff, E., Owen, A. M. & Monti, M. M. Disentangling disorders of consciousness: insights from diffusion tensor imaging and machine learning. Hum. Brain Mapp. 38, 431–443. https://doi.org/10.1002/hbm.23370 (2017).
Sezer, E., Işik, H. & Saracoğlu, E. Employment and comparison of different artificial neural networks for epilepsy diagnosis from EEG signals. J. Med. Syst. 36, 347–362. https://doi.org/10.1007/s10916-010-9480-5 (2012).
Acknowledgements
The authors of this study thank all the staff from the rehabilitation department of the Second Qilu Hospital of Shandong University who supported this research. We thank the editor and the anonymous reviewers whose comments and suggestions helped improve this manuscript.
Funding
This study was supported by the National Key R&D Program Projects of China (2020YFC2006100) and Shandong Provincial Natural Science Foundation of China (ZR2024MH345).
Author information
Authors and Affiliations
Contributions
Conceptualization: Fanshuo Zeng, Sheng Qu, Xinchun Wu.Data curation: Sheng Qu, Yancai Zhou.Funding acquisition: Fanshuo Zeng.Methodology: Sheng Qu, Xinchun Wu, Laigang Huang, Qiangsan Sun.Writing – original draft: Sheng Qu, Laigang Huang, Xinchun Wu.Writing – review & editing: Fanshuo Zeng, Qiangsan Sun.All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Patient consent
Written informed consent was obtained from the family members of the patients with DOC or their legal guardians.
Ethics approval
The study was approved by the Ethics Committee of the Second Hospital of Shandong University (NO. KYLL-2023-414). All research procedures were conducted according to the principles of the Declaration of Helsinki.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Qu, S., Wu, X., Huang, L. et al. Diagnosis of disorders of consciousness using nonlinear feature derived EEG topographic maps via deep learning. Sci Rep (2026). https://doi.org/10.1038/s41598-026-36733-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-36733-6
