Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning

Nature Communications, Journal Year: 2022, Volume and Issue: 13(1)

Published: Feb. 25, 2022

Consciousness can be defined by two components: arousal (wakefulness) and awareness (subjective experience). However, neurophysiological consciousness metrics able to disentangle between these components have not been reported. Here, we propose an explainable indicator (ECI) using deep learning the of consciousness. We employ electroencephalographic (EEG) responses transcranial magnetic stimulation under various conditions, including sleep (n = 6), general anesthesia 16), severe brain injury 34). also test our framework resting-state EEG 15) ECI simultaneously quantifies physiological, pharmacological, pathological conditions. Particularly, ketamine-induced rapid eye movement with low high are clearly distinguished from other states. In addition, parietal regions appear most relevant for quantifying awareness. This provides insights into neural correlates altered states

Language: Английский

---

Automatic Cardiac Arrhythmia Classification Using Residual Network Combined With Long Short-Term Memory

IEEE Transactions on Instrumentation and Measurement, Journal Year: 2022, Volume and Issue: 71, P. 1 - 17

Published: Jan. 1, 2022

Diagnosis and classification of arrhythmia, which is associated with abnormal electrical activities in the heart, are critical for clinical treatments. Previous studies focused on diagnosis atrial fibrillation, most common arrhythmia adults. The performance achieved by other types not satisfactory use owing to small number classes (minority classes). In this study, we propose a novel framework automatic that combines residual network squeeze excitation block, bidirectional long short-term memory. 8-class, 4-class, 2-class performances were evaluated MIT-BIH database (MITDB), fibrillation (AFDB), PhysioNet/Computing cardiology challenge 2017 (CinC DB), respectively, they superior conventional methods. addition, class-wise F1-score minority was higher than those methods adopted existing studies. To measure generalization ability proposed framework, AFDB CinC DB tested using MITDB-trained model, compared ShallowConvNet DeepConvNet. We performed cross-subject experiment obtained statistically method typical machine learning can enable direct trials based accurate detection class.

Language: Английский

---

A synergistic workspace for human consciousness revealed by Integrated Information Decomposition

eLife, Journal Year: 2023, Volume and Issue: 12

Published: July 25, 2023

How is the information-processing architecture of human brain organised, and how does its organisation support consciousness? Here, we combine network science a rigorous information-theoretic notion synergy to delineate ‘synergistic global workspace’, comprising gateway regions that gather synergistic information from specialised modules across brain. This then integrated within workspace widely distributed via broadcaster regions. Through functional MRI analysis, show correspond brain’s default mode network, whereas broadcasters coincide with executive control network. We find loss consciousness due general anaesthesia or disorders corresponds diminished ability integrate information, which restored upon recovery. Thus, coincides breakdown integration work contributes conceptual empirical reconciliation between two prominent scientific theories consciousness, Global Neuronal Workspace Integrated Information Theory, while also advancing our understanding supports through information.

Language: Английский

---

Exploring Artificial Intelligence in Anesthesia: A Primer on Ethics, and Clinical Applications

Surgeries, Journal Year: 2023, Volume and Issue: 4(2), P. 264 - 274

Published: May 29, 2023

The field of anesthesia has always been at the forefront innovation and technology, integration Artificial Intelligence (AI) represents next frontier in care. use AI its subtypes, such as machine learning, potential to improve efficiency, reduce costs, ameliorate patient outcomes. can assist with decision making, but primary advantage lies empowering anesthesiologists adopt a proactive approach address clinical issues. uses be schematically grouped into support pharmacologic mechanical robotic applications. Tele-anesthesia includes strategies telemedicine, well device networking, for improving logistics operating room, augmented reality approaches training assistance. Despite growing scientific interest, further research validation are needed fully understand benefits limitations these applications practice. Moreover, ethical implications must also considered ensure that safety privacy not compromised. This paper aims provide comprehensive overview anesthesia, including current applications, considerations safe effective technology.

Language: Английский

---

The coming decade of digital brain research: A vision for neuroscience at the intersection of technology and computing

Imaging Neuroscience, Journal Year: 2024, Volume and Issue: 2, P. 1 - 35

Published: April 1, 2024

Abstract In recent years, brain research has indisputably entered a new epoch, driven by substantial methodological advances and digitally enabled data integration modelling at multiple scales—from molecules to the whole brain. Major are emerging intersection of neuroscience with technology computing. This science combines high-quality research, across scales, culture multidisciplinary large-scale collaboration, translation into applications. As pioneered in Europe’s Human Brain Project (HBP), systematic approach will be essential for meeting coming decade’s pressing medical technological challenges. The aims this paper to: develop concept decade digital discuss community large, identify points convergence, derive therefrom scientific common goals; provide framework current future development EBRAINS, infrastructure resulting from HBP’s work; inform engage stakeholders, funding organisations institutions regarding research; address transformational potential comprehensive models artificial intelligence, including machine learning deep learning; outline collaborative that integrates reflection, dialogues, societal engagement on ethical opportunities challenges as part research.

Language: Английский

---

Covert cortical processing: a diagnosis in search of a definition

Neuroscience of Consciousness, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Feb. 1, 2024

Abstract Historically, clinical evaluation of unresponsive patients following brain injury has relied principally on serial behavioral examination to search for emerging signs consciousness and track recovery. Advances in neuroimaging electrophysiologic techniques now enable clinicians peer into residual functions even the absence overt signs. These advances have expanded clinicians’ ability sub-stratify behaviorally seemingly unaware by querying classifying covert activity made evident through active or passive techniques, including functional MRI, electroencephalography (EEG), transcranial magnetic stimulation-EEG, positron emission tomography. Clinical research thus reciprocally influenced practice, giving rise new diagnostic categories cognitive-motor dissociation (i.e. ‘covert consciousness’) cortical processing (CCP). While received extensive attention study, CCP is relatively less understood. We describe that an clinically relevant state marked presence intact association cortex responses environmental stimuli evidence stimulus processing. not a monotonic but rather encapsulates spectrum possible from rudimentary complex range stimuli. In constructing roadmap this evolving field, we emphasize efforts inform clinicians, philosophers, researchers condition are crucial. Along with strategies sensitize criteria disorders nosology these vital discoveries, democratizing access resources necessary identification ethical imperative.

Language: Английский

---

Harnessing machine learning for EEG signal analysis: Innovations in depth of anaesthesia assessment

Artificial Intelligence in Medicine, Journal Year: 2024, Volume and Issue: 151, P. 102869 - 102869

Published: April 4, 2024

Anaesthesia, crucial to surgical practice, is undergoing renewed scrutiny due the integration of artificial intelligence in its medical use. The precise control over temporary loss consciousness vital ensure safe, pain-free procedures. Traditional methods depth anaesthesia (DoA) assessment, reliant on physical characteristics, have proven inconsistent individual variations. In response, electroencephalography (EEG) techniques emerged, with indices such as Bispectral Index offering quantifiable assessments. This literature review explores current scope and frontier DoA research, emphasising utilising EEG signals for effective clinical monitoring. offers a critical synthesis recent advances, specifically focusing their role enhancing By examining 117 high-impact papers, delves into nuances feature extraction, model building, algorithm design EEG-based analysis. Comparative assessments these studies highlight methodological approaches performance, including correlations established like Index. identifies knowledge gaps, particularly need improved collaboration data access, which essential developing superior machine learning models real-time predictive algorithms patient management. It also calls refined evaluation processes robustness across diverse demographics anaesthetic agents. underscores potential technological advancements enhance precision, safety, outcomes anaesthesia, paving way new standard care. findings this contribute ongoing discourse application providing insights advancement area practice.

Language: Английский

---

Quantum deep learning in neuroinformatics: a systematic review

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(5)

Published: Feb. 14, 2025

Language: Английский

---

Advances in neuroimaging in disorders of consciousness

Handbook of clinical neurology, Journal Year: 2025, Volume and Issue: unknown, P. 97 - 127

Published: Jan. 1, 2025

Language: Английский

---

The current and future contribution of neuroimaging to the understanding of disorders of consciousness

La Presse Médicale, Journal Year: 2023, Volume and Issue: 52(2), P. 104163 - 104163

Published: Feb. 15, 2023

Patients with disorders of consciousness (DoC) represent a group severely brain-injured patients varying capacities for in terms both wakefulness and awareness. The current state-of-the-art assessing these is through standardised behavioural examinations, but inaccuracies are commonplace. Neuroimaging electrophysiological techniques have revealed vast insights into the relationships between neural alterations, andcognitive features DoC. This has led to establishment neuroimaging paradigms clinical assessment DoC patients. Here, we review selected findings on population, outlining key dysfunction underlying presenting utility tools. We discuss that whilst individual brain areas play instrumental roles generating supporting consciousness, activation alone not sufficient conscious experience. Instead, arise, need preserved thalamo-cortical circuits, addition connectivity distinctly differentiated networks, underlined by within, such networks. Finally, present recent advances future perspectives computational methodologies applied DoC, notion progress science will be driven symbiosis data-driven analyses, theory-driven research. Both work tandem provide mechanistic contextualised within theoretical frameworks which ultimately inform practice neurology.

Language: Английский

---