{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T01:20:49Z","timestamp":1789348849523,"version":"build-2803163510"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Hum. Neurosci."],"abstract":"<jats:p>Processing incoming neural oscillatory signals in real-time and decoding from them relevant behavioral or pathological states is often required for adaptive Deep Brain Stimulation (aDBS) and other brain-computer interface (BCI) applications. Most current approaches rely on first extracting a set of predefined features, such as the power in canonical frequency bands or various time-domain features, and then training machine learning systems that use those predefined features as inputs and infer what the underlying brain state is at each given time point. However, whether this algorithmic approach is best suited to extract all available information contained within the neural waveforms remains an open question. Here, we aim to explore different algorithmic approaches in terms of their potential to yield improvements in decoding performance based on neural activity such as measured through local field potentials (LFPs) recordings or electroencephalography (EEG). In particular, we aim to explore the potential of end-to-end convolutional neural networks, and compare this approach with other machine learning methods that are based on extracting predefined feature sets. To this end, we implement and train a number of machine learning models, based either on manually constructed features or, in the case of deep learning-based models, on features directly learnt from the data. We benchmark these models on the task of identifying neural states using simulated data, which incorporates waveform features previously linked to physiological and pathological functions. We then assess the performance of these models in decoding movements based on local field potentials recorded from the motor thalamus of patients with essential tremor. Our findings, derived from both simulated and real patient data, suggest that end-to-end deep learning-based methods may surpass feature-based approaches, particularly when the relevant patterns within the waveform data are either unknown, difficult to quantify, or when there may be, from the point of view of the predefined feature extraction pipeline, unidentified features that could contribute to decoding performance. The methodologies proposed in this study might hold potential for application in adaptive deep brain stimulation (aDBS) and other brain-computer interface systems.<\/jats:p>","DOI":"10.3389\/fnhum.2023.1134599","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T08:50:19Z","timestamp":1685695819000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["The potential of convolutional neural networks for identifying neural states based on electrophysiological signals: experiments on synthetic and real patient data"],"prefix":"10.3389","volume":"17","author":[{"given":"Fernando","family":"Rodriguez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenghong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiling","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,6,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/abaca3","article-title":"Rapid motor fluctuations reveal short-timescale neurophysiological biomarkers of Parkinson\u2019s disease.","volume":"17","author":"Ahn","year":"2020","journal-title":"J. Neural Eng"},{"key":"B2","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1038\/s41562-022-01310-0","article-title":"Decoding naturalistic affective behaviour from spectro-spatial features in multiday human iEEG.","volume":"6","author":"Bijanzadeh","year":"2022","journal-title":"Nat. Hum. Behav"},{"key":"B3","doi-asserted-by":"publisher","first-page":"3121","DOI":"10.1109\/ICPR.2010.764","article-title":"The balanced accuracy and its posterior distribution","author":"Brodersen","year":"2010","journal-title":"Proceedings of the 2010 20th International Conference on Pattern Recognition"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.1126\/science.1128115","article-title":"High gamma power is phase-locked to theta oscillations in human neocortex.","volume":"313","author":"Canolty","year":"2006","journal-title":"Science"},{"key":"B5","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1109\/WACV.2018.00097","article-title":"Grad-CAM++: Improved visual explanations for deep convolutional networks","author":"Chattopadhyay","year":"2018","journal-title":"Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"key":"B6","doi-asserted-by":"publisher","first-page":"4830","DOI":"10.1523\/JNEUROSCI.2208-16.2017","article-title":"Nonsinusoidal beta oscillations reflect cortical pathophysiology in Parkinson\u2019s Disease.","volume":"37","author":"Cole","year":"2017","journal-title":"J. Neurosci"},{"key":"B7","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1109\/WACV45572.2020.9093360","article-title":"Ablation-CAM: Visual explanations for deep convolutional network via gradient-free localization","author":"Desai","year":"2020","journal-title":"Proceedings of the 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/TNSRE.2021.3083548","article-title":"Learning invariant patterns based on a convolutional neural network and big electroencephalography data for subject-independent P300 brain-computer interfaces.","volume":"29","author":"Gao","year":"2021","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2020.108621","article-title":"LFP-Net: A deep learning framework to recognize human behavioral activities using brain STN-LFP signals.","volume":"335","author":"Golshan","year":"2020","journal-title":"J. Neurosci. Methods"},{"key":"B10","author":"Goodfellow","year":"2016","journal-title":"Deep Learning."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1016\/j.brs.2021.07.063","article-title":"Clinical perspectives of adaptive deep brain stimulation.","volume":"14","author":"Guidetti","year":"2021","journal-title":"Brain Stimul"},{"key":"B12","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1002\/mds.28513","article-title":"Closed-loop deep brain stimulation for essential tremor based on thalamic local field potentials.","volume":"36","author":"He","year":"2021","journal-title":"Mov. Disord"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift.","author":"Ioffe","year":"2015","journal-title":"arXiv [Preprint]"},{"key":"B14","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1002\/mds.27996","article-title":"Debugging adaptive deep brain stimulation for Parkinson\u2019s disease.","volume":"35","author":"Little","year":"2020","journal-title":"Mov. Disord"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1388","DOI":"10.1136\/jnnp-2016-313518","article-title":"Adaptive deep brain stimulation for Parkinson\u2019s disease demonstrates reduced speech side effects compared to conventional stimulation in the acute setting","volume":"87","author":"Little","year":"2016","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"B16","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1111\/nyas.14099","article-title":"Phase-amplitude coupling between theta and gamma oscillations adapts to speech rate.","volume":"1453","author":"Lizarazu","year":"2019","journal-title":"Ann. N. Y. Acad. Sci"},{"key":"B17","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.nbd.2019.02.005","article-title":"Synchronised spiking activity underlies phase amplitude coupling in the subthalamic nucleus of Parkinson\u2019s disease patients.","volume":"127","author":"Meidahl","year":"2019","journal-title":"Neurobiol. Dis"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.expneurol.2022.113993","article-title":"Machine learning based brain signal decoding for intelligent adaptive deep brain stimulation.","volume":"351","author":"Merk","year":"","journal-title":"Exp. Neurol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.75126","article-title":"Electrocorticography is superior to subthalamic local field potentials for movement decoding in Parkinson\u2019s disease.","volume":"11","author":"Merk","year":"","journal-title":"Elife"},{"key":"B20","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.clinph.2022.05.004","article-title":"A practical guide to invasive neurophysiology in patients with deep brain stimulation.","volume":"140","author":"Neumann","year":"2022","journal-title":"Clin. Neurophysiol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.01703","article-title":"PyTorch: An imperative style, high-performance deep learning library.","author":"Paszke","year":"2019","journal-title":"arXiv [Preprint]"},{"key":"B22","first-page":"2825","article-title":"Scikit-learn: Machine learning in python.","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2021.696950","article-title":"Habituation after deep brain stimulation in tremor syndromes: Prevalence, risk factors and long-term outcomes.","volume":"12","author":"Peters","year":"2021","journal-title":"Front. Neurol."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/abda0b","article-title":"Generalized neural decoders for transfer learning across participants and recording modalities.","volume":"18","author":"Peterson","year":"2021","journal-title":"J. Neural Eng."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1152\/jn.00201.2021","article-title":"Within-cycle instantaneous frequency profiles report oscillatory waveform dynamics.","volume":"126","author":"Quinn","year":"2021","journal-title":"J. Neurophysiol"},{"key":"B26","article-title":"Searching for activation functions.","author":"Ramachandran","year":"2017","journal-title":"arXiv."},{"key":"B27","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization.","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"B28","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1109\/TNSRE.2018.2837500","article-title":"Towards real-time, continuous decoding of gripping force from deep brain local field potentials.","volume":"26","author":"Shah","year":"2018","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2021.777977","article-title":"Automatic diagnosis of schizophrenia in EEG signals using CNN-LSTM models.","volume":"15","author":"Shoeibi","year":"2021","journal-title":"Front. Neuroinform"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2201128119","article-title":"Deep neural networks constrained by neural mass models improve electrophysiological source imaging of spatiotemporal brain dynamics.","volume":"119","author":"Sun","year":"2022","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106225","article-title":"A deep learning based model using RNN-LSTM for the detection of schizophrenia from EEG data.","author":"Supakar","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.abo1800","article-title":"Principles of gait encoding in the subthalamic nucleus of people with Parkinson\u2019s disease.","volume":"14","author":"Thenaisie","year":"2022","journal-title":"Sci. Transl. Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.nbd.2018.06.007","article-title":"Beta burst coupling across the motor circuit in Parkinson\u2019s disease.","volume":"117","author":"Tinkhauser","year":"2018","journal-title":"Neurobiol. Dis"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1152\/jn.00106.2010","article-title":"Measuring phase-amplitude coupling between neuronal oscillations of different frequencies.","volume":"104","author":"Tort","year":"2010","journal-title":"J. Neurophysiol"},{"key":"B35","doi-asserted-by":"publisher","first-page":"12827","DOI":"10.1073\/pnas.1705120114","article-title":"Brain network dynamics are hierarchically organized in time.","volume":"114","author":"Vidaurre","year":"2017","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"B36","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1002\/hipo.23284","article-title":"Theta power and theta-gamma coupling support long-term spatial memory retrieval.","volume":"31","author":"Vivekananda","year":"2021","journal-title":"Hippocampus"},{"key":"B37","article-title":"Score-CAM: Score-weighted visual explanations for convolutional neural networks.","author":"Wang","year":"2020","journal-title":"arXiv."},{"key":"B38","author":"Wang","year":"2015","journal-title":"Encoding Time Series as Images for Visual Inspection and Classification Using Tiled Convolutional Neural Networks."},{"key":"B39","doi-asserted-by":"publisher","first-page":"2086","DOI":"10.1016\/j.clinph.2020.05.035","article-title":"Waveform changes with the evolution of beta bursts in the human subthalamic nucleus.","volume":"131","author":"Yeh","year":"2020","journal-title":"Clin. Neurophysiol"},{"key":"B40","article-title":"mixup: Beyond empirical risk minimization.","author":"Zhang","year":"2018","journal-title":"arXiv."}],"container-title":["Frontiers in Human Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2023.1134599\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T08:50:26Z","timestamp":1685695826000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2023.1134599\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,2]]},"references-count":40,"alternative-id":["10.3389\/fnhum.2023.1134599"],"URL":"https:\/\/doi.org\/10.3389\/fnhum.2023.1134599","relation":{},"ISSN":["1662-5161"],"issn-type":[{"value":"1662-5161","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,2]]},"article-number":"1134599"}}