1
|
Kayabekir M, Yağanoğlu M. SPINDILOMETER: a model describing sleep spindles on EEG signals for polysomnography. Phys Eng Sci Med 2024; 47:1073-1085. [PMID: 38819611 PMCID: PMC11408404 DOI: 10.1007/s13246-024-01428-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2023] [Accepted: 04/16/2024] [Indexed: 06/01/2024]
Abstract
This paper aims to present a model called SPINDILOMETER, which we propose to be integrated into polysomnography (PSG) devices for researchers focused on electrophysiological signals in PSG, physicians, and technicians practicing sleep in clinics, by examining the methods of the sleep electroencephalogram (EEG) signal analysis in recent years. For this purpose, an assist diagnostic model for PSG has been developed that measures the number and density of sleep spindles by analyzing EEG signals in PSG. EEG signals of 72 volunteers, 51 males and 21 females (age; 51.7 ± 3.42 years and body mass index; 37.6 ± 4.21) diagnosed with sleep-disordered breathing by PSG were analyzed by machine learning methods. The number and density of sleep spindles were compared between the classical method (EEG monitoring with the naked eye in PSG) ('method with naked eye') and the model (SPINDILOMETER). A strong positive correlation was found between 'method with naked eye' and SPINDILOMETER results (correlation coefficient: 0.987), and this correlation was statistically significant (p = 0.000). Confusion matrix (accuracy (94.61%), sensitivity (94.61%), specificity (96.60%)), and ROC analysis (AUC: 0.95) were performed to prove the adequacy of SPINDILOMETER (p = 0.000). In conclusion SPINDILOMETER can be included in PSG analysis performed in sleep laboratories. At the same time, this model provides diagnostic convenience to the physician in understanding the neurological events associated with sleep spindles and sheds light on research for thalamocortical regions in the fields of neurophysiology and electrophysiology.
Collapse
Affiliation(s)
- Murat Kayabekir
- Department of Physiology, Medical School, Atatürk University, 25240, Erzurum, Turkey.
| | - Mete Yağanoğlu
- Department of Computer Engineering, Faculty of Engineering, Atatürk University, Erzurum, Turkey
| |
Collapse
|
2
|
Ajra Z, Xu B, Dray G, Montmain J, Perrey S. Using shallow neural networks with functional connectivity from EEG signals for early diagnosis of Alzheimer's and frontotemporal dementia. Front Neurol 2023; 14:1270405. [PMID: 37900600 PMCID: PMC10602655 DOI: 10.3389/fneur.2023.1270405] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Accepted: 09/25/2023] [Indexed: 10/31/2023] Open
Abstract
Introduction Dementia is a neurological disorder associated with aging that can cause a loss of cognitive functions, impacting daily life. Alzheimer's disease (AD) is the most common cause of dementia, accounting for 50-70% of cases, while frontotemporal dementia (FTD) affects social skills and personality. Electroencephalography (EEG) provides an effective tool to study the effects of AD on the brain. Methods In this study, we propose to use shallow neural networks applied to two sets of features: spectral-temporal and functional connectivity using four methods. We compare three supervised machine learning techniques to the CNN models to classify EEG signals of AD / FTD and control cases. We also evaluate different measures of functional connectivity from common EEG frequency bands considering multiple thresholds. Results and discussion Results showed that the shallow CNN-based models achieved the highest accuracy of 94.54% with AEC in test dataset when considering all connections, outperforming conventional methods and providing potentially an additional early dementia diagnosis tool.
Collapse
Affiliation(s)
- Zaineb Ajra
- EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales, Montpellier, France
| | - Binbin Xu
- EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales, Ales, France
| | - Gérard Dray
- EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales, Ales, France
| | - Jacky Montmain
- EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales, Ales, France
| | - Stéphane Perrey
- EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales, Montpellier, France
| |
Collapse
|
3
|
Adama S, Bogdan M. Application of Soft-Clustering to Assess Consciousness in a CLIS Patient. Brain Sci 2022; 13:brainsci13010065. [PMID: 36672046 PMCID: PMC9856569 DOI: 10.3390/brainsci13010065] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2022] [Revised: 12/12/2022] [Accepted: 12/21/2022] [Indexed: 01/01/2023] Open
Abstract
Completely locked-in (CLIS) patients are characterized by sufficiently intact cognitive functions, but a complete paralysis that prevents them to interact with their surroundings. On one hand, studies have shown that the ability to communicate plays an important part in these patients' quality of life and prognosis. On the other hand, brain-computer interfaces (BCIs) provide a means for them to communicate using their brain signals. However, one major problem for such patients is the difficulty to determine if they are conscious or not at a specific time. This work aims to combine different sets of features consisting of spectral, complexity and connectivity measures, to increase the probability of correctly estimating CLIS patients' consciousness levels. The proposed approach was tested on data from one CLIS patient, which is particular in the sense that the experimenter was able to point out one time frame Δt during which he was undoubtedly conscious. Results showed that the method presented in this paper was able to detect increases and decreases of the patient's consciousness levels. More specifically, increases were observed during this Δt, corroborating the assertion of the experimenter reporting that the patient was definitely conscious then. Assessing the patients' consciousness is intended as a step prior attempting to communicate with them, in order to maximize the efficiency of BCI-based communication systems.
Collapse
|
4
|
Abubshait A, Parenti L, Perez-Osorio J, Wykowska A. Misleading Robot Signals in a Classification Task Induce Cognitive Load as Measured by Theta Synchronization Between Frontal and Temporo-parietal Brain Regions. FRONTIERS IN NEUROERGONOMICS 2022; 3:838136. [PMID: 38235447 PMCID: PMC10790903 DOI: 10.3389/fnrgo.2022.838136] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/17/2021] [Accepted: 06/01/2022] [Indexed: 01/19/2024]
Abstract
As technological advances progress, we find ourselves in situations where we need to collaborate with artificial agents (e.g., robots, autonomous machines and virtual agents). For example, autonomous machines will be part of search and rescue missions, space exploration and decision aids during monitoring tasks (e.g., baggage-screening at the airport). Efficient communication in these scenarios would be crucial to interact fluently. While studies examined the positive and engaging effect of social signals (i.e., gaze communication) on human-robot interaction, little is known about the effects of conflicting robot signals on the human actor's cognitive load. Moreover, it is unclear from a social neuroergonomics perspective how different brain regions synchronize or communicate with one another to deal with the cognitive load induced by conflicting signals in social situations with robots. The present study asked if neural oscillations that correlate with conflict processing are observed between brain regions when participants view conflicting robot signals. Participants classified different objects based on their color after a robot (i.e., iCub), presented on a screen, simulated handing over the object to them. The robot proceeded to cue participants (with a head shift) to the correct or incorrect target location. Since prior work has shown that unexpected cues can interfere with oculomotor planning and induces conflict, we expected that conflicting robot social signals which would interfere with the execution of actions. Indeed, we found that conflicting social signals elicited neural correlates of cognitive conflict as measured by mid-brain theta oscillations. More importantly, we found higher coherence values between mid-frontal electrode locations and posterior occipital electrode locations in the theta-frequency band for incongruent vs. congruent cues, which suggests that theta-band synchronization between these two regions allows for communication between cognitive control systems and gaze-related attentional mechanisms. We also find correlations between coherence values and behavioral performance (Reaction Times), which are moderated by the congruency of the robot signal. In sum, the influence of irrelevant social signals during goal-oriented tasks can be indexed by behavioral, neural oscillation and brain connectivity patterns. These data provide insights about a new measure for cognitive load, which can also be used in predicting human interaction with autonomous machines.
Collapse
Affiliation(s)
- Abdulaziz Abubshait
- Social Cognition in Human Robot Interaction (S4HRI), Italian Institute of Technology, Genova, Italy
| | - Lorenzo Parenti
- Social Cognition in Human Robot Interaction (S4HRI), Italian Institute of Technology, Genova, Italy
- Department of Psychology, University of Torino, Turin, Italy
| | - Jairo Perez-Osorio
- Social Cognition in Human Robot Interaction (S4HRI), Italian Institute of Technology, Genova, Italy
| | - Agnieszka Wykowska
- Social Cognition in Human Robot Interaction (S4HRI), Italian Institute of Technology, Genova, Italy
| |
Collapse
|
5
|
Sakellariou DF, Vakrinou A, Koutroumanidis M, Richardson MP. Neurocraft: software for microscale brain network dynamics. Sci Rep 2021; 11:20716. [PMID: 34671076 PMCID: PMC8528833 DOI: 10.1038/s41598-021-99195-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2021] [Accepted: 06/28/2021] [Indexed: 11/08/2022] Open
Abstract
The brain operates at millisecond timescales but despite of that, the study of its functional networks is approached with time invariant methods. Equally, for a variety of brain conditions treatment is delivered with fixed temporal protocols unable to monitor and follow the rapid progression and therefore the cycles of a disease. To facilitate the understanding of brain network dynamics we developed Neurocraft, a user friendly software suite. Neurocraft features a highly novel signal processing engine fit for tracking evolving network states with superior time and frequency resolution. A variety of analytics like dynamic connectivity maps, force-directed representations and propagation models, allow for the highly selective investigation of transient pathophysiological dynamics. In addition, machine-learning tools enable the unsupervised investigation and selection of key network features at individual and group-levels. For proof of concept, we compared six seizure-free and non seizure-free focal epilepsy patients after resective surgery using Neurocraft. The network features were calculated using 50 intracranial electrodes on average during at least 120 epileptiform discharges lasting less than one second, per patient. Powerful network differences were detected in the pre-operative data of the two patient groups (effect size = 1.27), suggesting the predictive value of dynamic network features. More than one million patients are treated with cardiac and neuro modulation devices that are unable to track the hourly or daily changes in a subject's disease. Decoding the dynamics of transition from normal to abnormal states may be crucial in the understanding, tracking and treatment of neurological conditions. Neurocraft provides a user-friendly platform for the research of microscale brain dynamics and a stepping stone for the personalised device-based adaptive neuromodulation in real-time.
Collapse
Affiliation(s)
- Dimitris Fotis Sakellariou
- Real World Solutions, IQVIA, London, N1 9JY, UK.
- Department of Basic and Clinical Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
- Department of Neurophysiology and Epilepsy, St Thomas' Hospital NHS Trust, London, UK.
| | - Angeliki Vakrinou
- Department of Basic and Clinical Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
- Department of Neurophysiology and Epilepsy, St Thomas' Hospital NHS Trust, London, UK
| | | | - Mark Phillip Richardson
- Department of Basic and Clinical Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
| |
Collapse
|
6
|
Sakellariou DF, Dall'Orso S, Burdet E, Lin JP, Richardson MP, McClelland VM. Abnormal microscale neuronal connectivity triggered by a proprioceptive stimulus in dystonia. Sci Rep 2020; 10:20758. [PMID: 33247213 PMCID: PMC7695825 DOI: 10.1038/s41598-020-77533-w] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2020] [Accepted: 10/07/2020] [Indexed: 12/15/2022] Open
Abstract
We investigated modulation of functional neuronal connectivity by a proprioceptive stimulus in sixteen young people with dystonia and eight controls. A robotic wrist interface delivered controlled passive wrist extension movements, the onset of which was synchronised with scalp EEG recordings. Data were segmented into epochs around the stimulus and up to 160 epochs per subject were averaged to produce a Stretch Evoked Potential (StretchEP). Event-related network dynamics were estimated using a methodology that features Wavelet Transform Coherency (WTC). Global Microscale Nodal Strength (GMNS) was introduced to estimate overall engagement of areas into short-lived networks related to the StretchEP, and Global Connectedness (GC) estimated the spatial extent of the StretchEP networks. Dynamic Connectivity Maps showed a striking difference between dystonia and controls, with particularly strong theta band event-related connectivity in dystonia. GC also showed a trend towards higher values in dystonia than controls. In summary, we demonstrate the feasibility of this method to investigate event-related neuronal connectivity in relation to a proprioceptive stimulus in a paediatric patient population. Young people with dystonia show an exaggerated network response to a proprioceptive stimulus, displaying both excessive theta-band synchronisation across the sensorimotor network and widespread engagement of cortical regions in the activated network.
Collapse
Affiliation(s)
- Dimitris F Sakellariou
- Department of Basic and Clinical Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, SE5 9RX, UK.,Machine Learning & Artificial Intelligence Solutions Global Unit, Real World Solutions, IQVIA, London, N1 9JY, UK
| | - Sofia Dall'Orso
- Department of Biomedical Engineering and Human Robotics, Imperial College London, London, SW7 2AZ, UK
| | - Etienne Burdet
- Department of Biomedical Engineering and Human Robotics, Imperial College London, London, SW7 2AZ, UK
| | - Jean-Pierre Lin
- Children's Neurosciences Department, Evelina London Children's Hospital, Guy's and St Thomas' NHS Foundation Trust, London, SE1 7EH, UK
| | - Mark P Richardson
- Department of Basic and Clinical Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, SE5 9RX, UK
| | - Verity M McClelland
- Department of Basic and Clinical Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, SE5 9RX, UK. .,Children's Neurosciences Department, Evelina London Children's Hospital, Guy's and St Thomas' NHS Foundation Trust, London, SE1 7EH, UK.
| |
Collapse
|
7
|
Sakellariou DF, Koutroumanidis M, Richardson MP, Kostopoulos GK. Cross-subject network investigation of the EEG microstructure: A sleep spindles study. J Neurosci Methods 2019; 312:16-26. [PMID: 30408558 PMCID: PMC6327148 DOI: 10.1016/j.jneumeth.2018.11.001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2018] [Revised: 11/01/2018] [Accepted: 11/01/2018] [Indexed: 12/01/2022]
Abstract
Grand averages across subjects can distort connectivity results for a group. Within-group network variance may hold information for the EEG event under investigation. The proposed method can serve as an observatory tool, complementary to the existing topography EEG techniques.
Background The microstructural EEG elements and their functional networks relate to many neurophysiological functions of the brain and can reveal abnormalities. Despite the blooming variety of methods for estimating connectivity in the EEG of a single subject, a common pitfall is seen in relevant studies; grand averaging is used for estimating the characteristic connectivity patterns of a group of subjects. This averaging may distort results and fail to account for the internal variability of connectivity results across the subjects of a group. New Method In this study, we propose a novel methodology for the cross-subject network investigation of EEG graphoelements. We used dimensionality reduction techniques in order to reveal internal connectivity properties and to examine how consistent these are across a number of subjects. In addition, graph theoretical measures were utilized to prioritize regions according to their network attributes. Results As proof of concept, we applied this method on fast sleep spindles across 10 healthy subjects. Neurophysiological findings revealed subnetworks of the spindle events across subjects, highlighting a predominance for occipito-parietal areas and their connectivity with frontal regions. Comparison with existing methods This is a new approach for the examination of within-group connectivities in EEG research. The results accounted for more than 85% of the overall data variance and the detected subnetworks were found to be meaningful down-projections of the grand average of the group, suggesting sufficient performance for the proposed methodology. Conclusion We conclude that the proposed methodology can serve as an observatory tool for the EEG connectivity patterns across subjects, providing a supplementary analysis of the existing topography techniques.
Collapse
Affiliation(s)
- Dimitris F Sakellariou
- Division of Neuroscience, Department of Basic and Clinical Neuroscience, King's College, London, UK; Neurophysiology Unit, Department of Physiology, School of Medicine, University of Patras, Rio, Greece; Department of Clinical Neurophysiology and Epilepsy, Guy's and St Thomas' NHS Foundation Trust, London, UK.
| | - Michalis Koutroumanidis
- Neurophysiology Unit, Department of Physiology, School of Medicine, University of Patras, Rio, Greece; Department of Clinical Neurophysiology and Epilepsy, Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Mark P Richardson
- Division of Neuroscience, Department of Basic and Clinical Neuroscience, King's College, London, UK
| | - George K Kostopoulos
- Neurophysiology Unit, Department of Physiology, School of Medicine, University of Patras, Rio, Greece
| |
Collapse
|
8
|
Mikulan E, Hesse E, Sedeño L, Bekinschtein T, Sigman M, García MDC, Silva W, Ciraolo C, García AM, Ibáñez A. Intracranial high-γ connectivity distinguishes wakefulness from sleep. Neuroimage 2017; 169:265-277. [PMID: 29225064 DOI: 10.1016/j.neuroimage.2017.12.015] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2017] [Revised: 11/21/2017] [Accepted: 12/06/2017] [Indexed: 12/27/2022] Open
Abstract
Neural synchrony in the γ-band is considered a fundamental process in cortical computation and communication and it has also been proposed as a crucial correlate of consciousness. However, the latter claim remains inconclusive, mainly due to methodological limitations, such as the spectral constraints of scalp-level electroencephalographic recordings or volume-conduction confounds. Here, we circumvented these caveats by comparing γ-band connectivity between two global states of consciousness via intracranial electroencephalography (iEEG), which provides the most reliable measurements of high-frequency activity in the human brain. Non-REM Sleep recordings were compared to passive-wakefulness recordings of the same duration in three subjects with surgically implanted electrodes. Signals were analyzed through the weighted Phase Lag Index connectivity measure and relevant graph theory metrics. We found that connectivity in the high-γ range (90-120 Hz), as well as relevant graph theory properties, were higher during wakefulness than during sleep and discriminated between conditions better than any other canonical frequency band. Our results constitute the first report of iEEG differences between wakefulness and sleep in the high-γ range at both local and distant sites, highlighting the utility of this technique in the search for the neural correlates of global states of consciousness.
Collapse
Affiliation(s)
- Ezequiel Mikulan
- Laboratory of Experimental Psychology and Neuroscience (LPEN), Institute of Cognitive and Translational Neuroscience (INCYT), INECO Foundation, Favaloro University, Buenos Aires, Argentina; National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina; Consciousness and Cognition Lab, Department of Psychology, University of Cambridge, UK.
| | - Eugenia Hesse
- Laboratory of Experimental Psychology and Neuroscience (LPEN), Institute of Cognitive and Translational Neuroscience (INCYT), INECO Foundation, Favaloro University, Buenos Aires, Argentina; National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina; Instituto de Ingeniería Biomédica, Facultad de Ingeniería, Universidad de Buenos Aires, Argentina
| | - Lucas Sedeño
- Laboratory of Experimental Psychology and Neuroscience (LPEN), Institute of Cognitive and Translational Neuroscience (INCYT), INECO Foundation, Favaloro University, Buenos Aires, Argentina; National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina
| | - Tristán Bekinschtein
- Consciousness and Cognition Lab, Department of Psychology, University of Cambridge, UK
| | | | - María Del Carmen García
- Programa de Cirugía de Epilepsia, Hospital Italiano de Buenos Asires, Buenos Aires, Argentina
| | - Walter Silva
- Programa de Cirugía de Epilepsia, Hospital Italiano de Buenos Asires, Buenos Aires, Argentina
| | - Carlos Ciraolo
- Programa de Cirugía de Epilepsia, Hospital Italiano de Buenos Asires, Buenos Aires, Argentina
| | - Adolfo M García
- Laboratory of Experimental Psychology and Neuroscience (LPEN), Institute of Cognitive and Translational Neuroscience (INCYT), INECO Foundation, Favaloro University, Buenos Aires, Argentina; National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina; Faculty of Education, National University of Cuyo (UNCuyo), Mendoza, Argentina
| | - Agustín Ibáñez
- Laboratory of Experimental Psychology and Neuroscience (LPEN), Institute of Cognitive and Translational Neuroscience (INCYT), INECO Foundation, Favaloro University, Buenos Aires, Argentina; National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina; Universidad Autónoma del Caribe, Barranquilla, Colombia; Center for Social and Cognitive Neuroscience (CSCN), School of Psychology, Universidad Adolfo Ibañez, Santiago de Chile, Chile; Australian Research Council Centre of Excellence in Cognition and its Disorders, Sydney, Australia.
| |
Collapse
|
9
|
Schiecke K, Pester B, Piper D, Feucht M, Benninger F, Witte H, Leistritz L. Advanced nonlinear approach to quantify directed interactions within EEG activity of children with temporal lobe epilepsy in their time course. ACTA ACUST UNITED AC 2017. [DOI: 10.1051/epjnbp/2017002] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
|
10
|
A Study on Automatic Sleep Stage Classification Based on Clustering Algorithm. Brain Inform 2017. [DOI: 10.1007/978-3-319-70772-3_13] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022] Open
|