Applying deep learning to single-trial EEG data provides evidence for complementary theories on action control.
Ontology highlight
ABSTRACT:
SUBMITTER: Vahid A
PROVIDER: S-EPMC7062698 | biostudies-literature | 2020 Mar
REPOSITORIES: biostudies-literature
Publications
Applying deep learning to single-trial EEG data provides evidence for complementary theories on action control.
Vahid Amirali A Mückschel Moritz M Stober Sebastian S Stock Ann-Kathrin AK Beste Christian C
Communications biology 20200309 1
Efficient action control is indispensable for goal-directed behaviour. Different theories have stressed the importance of either attention or response selection sub-processes for action control. Yet, it is unclear to what extent these processes can be identified in the dynamics of neurophysiological (EEG) processes at the single-trial level and be used to predict the presence of conflicts in a given moment. Applying deep learning, which was blind to cognitive theory, on single-trial EEG data all ...[more]
Similar Datasets
Project description:BackgroundPsychological models are used to understand and predict behaviour in a wide range of settings, but have not been consistently applied to health professional behaviours, and the contribution of differing theories is not clear. This study explored the usefulness of a range of models to predict an evidence-based behaviour -- the placing of fissure sealants.MethodsMeasures were collected by postal questionnaire from a random sample of general dental practitioners (GDPs) in Scotland. Outcomes were behavioural simulation (scenario decision-making), and behavioural intention. Predictor variables were from the Theory of Planned Behaviour (TPB), Social Cognitive Theory (SCT), Common Sense Self-regulation Model (CS-SRM), Operant Learning Theory (OLT), Implementation Intention (II), Stage Model, and knowledge (a non-theoretical construct). Multiple regression analysis was used to examine the predictive value of each theoretical model individually. Significant constructs from all theories were then entered into a 'cross theory' stepwise regression analysis to investigate their combined predictive value.ResultsBehavioural simulation - theory level variance explained was: TPB 31%; SCT 29%; II 7%; OLT 30%. Neither CS-SRM nor stage explained significant variance. In the cross theory analysis, habit (OLT), timeline acute (CS-SRM), and outcome expectancy (SCT) entered the equation, together explaining 38% of the variance. Behavioural intention - theory level variance explained was: TPB 30%; SCT 24%; OLT 58%, CS-SRM 27%. GDPs in the action stage had significantly higher intention to place fissure sealants. In the cross theory analysis, habit (OLT) and attitude (TPB) entered the equation, together explaining 68% of the variance in intention.SummaryThe study provides evidence that psychological models can be useful in understanding and predicting clinical behaviour. Taking a theory-based approach enables the creation of a replicable methodology for identifying factors that may predict clinical behaviour and so provide possible targets for knowledge translation interventions. Results suggest that more evidence-based behaviour may be achieved by influencing beliefs about the positive outcomes of placing fissure sealants and building a habit of placing them as part of patient management. However a number of conceptual and methodological challenges remain.
| S-EPMC2864198 | biostudies-literature
Project description:Repetitive practice is one of the most important factors in improving the performance of motor skills. This paper focuses on the analysis and classification of forearm gestures in the context of violin playing. We recorded five experts and three students performing eight traditional classical violin bow-strokes: martelé, staccato, detaché, ricochet, legato, trémolo, collé, and col legno. To record inertial motion information, we utilized the Myo sensor, which reports a multidimensional time-series signal. We synchronized inertial motion recordings with audio data to extract the spatiotemporal dynamics of each gesture. Applying state-of-the-art deep neural networks, we implemented and compared different architectures where convolutional neural networks (CNN) models demonstrated recognition rates of 97.147%, 3DMultiHeaded_CNN models showed rates of 98.553%, and rates of 99.234% were demonstrated by CNN_LSTM models. The collected data (quaternion of the bowing arm of a violinist) contained sufficient information to distinguish the bowing techniques studied, and deep learning methods were capable of learning the movement patterns that distinguish these techniques. Each of the learning algorithms investigated (CNN, 3DMultiHeaded_CNN, and CNN_LSTM) produced high classification accuracies which supported the feasibility of training classifiers. The resulting classifiers may provide the foundation of a digital assistant to enhance musicians' time spent practicing alone, providing real-time feedback on the accuracy and consistency of their musical gestures in performance.
| S-EPMC7813937 | biostudies-literature
Project description:ObjectiveThe concurrent recording of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) is a technique that has received much attention due to its potential for combined high temporal and spatial resolution. However, the ballistocardiogram (BCG), a large-amplitude artifact caused by cardiac induced movement contaminates the EEG during EEG-fMRI recordings. Removal of BCG in software has generally made use of linear decompositions of the corrupted EEG. This is not ideal as the BCG signal propagates in a manner which is non-linearly dependent on the electrocardiogram (ECG). In this paper, we present a novel method for BCG artifact suppression using recurrent neural networks (RNNs).MethodsEEG signals were recovered by training RNNs on the nonlinear mappings between ECG and the BCG corrupted EEG. We evaluated our model's performance against the commonly used Optimal Basis Set (OBS) method at the level of individual subjects, and investigated generalization across subjects.ResultsWe show that our algorithm can generate larger average power reduction of the BCG at critical frequencies, while simultaneously improving task relevant EEG based classification.ConclusionThe presented deep learning architecture can be used to reduce BCG related artifacts in EEG-fMRI recordings.SignificanceWe present a deep learning approach that can be used to suppress the BCG artifact in EEG-fMRI without the use of additional hardware. This method may have scope to be combined with current hardware methods, operate in real-time and be used for direct modeling of the BCG.
| S-EPMC7808341 | biostudies-literature
Project description:Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc.
| S-EPMC5655781 | biostudies-literature
Project description:BackgroundPsychological models can be used to understand and predict behaviour in a wide range of settings. However, they have not been consistently applied to health professional behaviours, and the contribution of differing theories is not clear. The aim of this study was to explore the usefulness of a range of psychological theories to predict health professional behaviour relating to management of upper respiratory tract infections (URTIs) without antibiotics.MethodsPsychological measures were collected by postal questionnaire survey from a random sample of general practitioners (GPs) in Scotland. The outcome measures were clinical behaviour (using antibiotic prescription rates as a proxy indicator), behavioural simulation (scenario-based decisions to managing URTI with or without antibiotics) and behavioural intention (general intention to managing URTI without antibiotics). Explanatory variables were the constructs within the following theories: Theory of Planned Behaviour (TPB), Social Cognitive Theory (SCT), Common Sense Self-Regulation Model (CS-SRM), Operant Learning Theory (OLT), Implementation Intention (II), Stage Model (SM), and knowledge (a non-theoretical construct). For each outcome measure, multiple regression analysis was used to examine the predictive value of each theoretical model individually. Following this 'theory level' analysis, a 'cross theory' analysis was conducted to investigate the combined predictive value of all significant individual constructs across theories.ResultsAll theories were tested, but only significant results are presented. When predicting behaviour, at the theory level, OLT explained 6% of the variance and, in a cross theory analysis, OLT 'evidence of habitual behaviour' also explained 6%. When predicting behavioural simulation, at the theory level, the proportion of variance explained was: TPB, 31%; SCT, 26%; II, 6%; OLT, 24%. GPs who reported having already decided to change their management to try to avoid the use of antibiotics made significantly fewer scenario-based decisions to prescribe. In the cross theory analysis, perceived behavioural control (TPB), evidence of habitual behaviour (OLT), CS-SRM cause (chance/bad luck), and intention entered the equation, together explaining 36% of the variance. When predicting intention, at the theory level, the proportion of variance explained was: TPB, 30%; SCT, 29%; CS-SRM 27%; OLT, 43%. GPs who reported that they had already decided to change their management to try to avoid the use of antibiotics had a significantly higher intention to manage URTIs without prescribing antibiotics. In the cross theory analysis, OLT evidence of habitual behaviour, TPB attitudes, risk perception, CS-SRM control by doctor, TPB perceived behavioural control and CS-SRM control by treatment entered the equation, together explaining 49% of the variance in intention.ConclusionThe study provides evidence that psychological models can be useful in understanding and predicting clinical behaviour. Taking a theory-based approach enables the creation of a replicable methodology for identifying factors that predict clinical behaviour. However, a number of conceptual and methodological challenges remain.
| S-EPMC2042498 | biostudies-literature
Project description:Electroencephalography (EEG) datasets are often small and high dimensional, owing to cumbersome recording processes. In these conditions, powerful machine learning techniques are essential to deal with the large amount of information and overcome the curse of dimensionality. Artificial Neural Networks (ANNs) have achieved promising performance in EEG-based Brain-Computer Interface (BCI) applications, but they involve computationally intensive training algorithms and hyperparameter optimization methods. Thus, an awareness of the quality-cost trade-off, although usually overlooked, is highly beneficial. In this paper, we apply a hyperparameter optimization procedure based on Genetic Algorithms to Convolutional Neural Networks (CNNs), Feed-Forward Neural Networks (FFNNs), and Recurrent Neural Networks (RNNs), all of them purposely shallow. We compare their relative quality and energy-time cost, but we also analyze the variability in the structural complexity of networks of the same type with similar accuracies. The experimental results show that the optimization procedure improves accuracy in all models, and that CNN models with only one hidden convolutional layer can equal or slightly outperform a 6-layer Deep Belief Network. FFNN and RNN were not able to reach the same quality, although the cost was significantly lower. The results also highlight the fact that size within the same type of network is not necessarily correlated with accuracy, as smaller models can and do match, or even surpass, bigger ones in performance. In this regard, overfitting is likely a contributing factor since deep learning approaches struggle with limited training examples.
| S-EPMC7289369 | biostudies-literature
Project description:Presurgical evaluation that can precisely delineate the epileptogenic zone (EZ) is one important step for successful surgical resection treatment of refractory epilepsy patients. The noninvasive EEG-fMRI recording technique combined with general linear model (GLM) analysis is considered an important tool for estimating the EZ. However, the manual marking of interictal epileptic discharges (IEDs) needed in this analysis is challenging and time-consuming because the quality of the EEG recorded inside the scanner is greatly deteriorated compared to the usual EEG obtained outside the scanner. This is one of main impediments to the widespread use of EEG-fMRI in epilepsy. We propose a deep learning based semi-automatic IED detector that can find the candidate IEDs in the EEG recorded inside the scanner which resemble sample IEDs marked in the EEG recorded outside the scanner. The manual marking burden is greatly reduced as the expert need only edit candidate IEDs. The model is trained on data from 30 patients. Validation of IEDs detection accuracy on another 37 consecutive patients shows our method can improve the median sensitivity from 50.0% for the previously proposed template-based method to 84.2%, with false positive rate as 5 events/min. Reproducibility validation on 15 patients is applied to evaluate if our method can produce similar hemodynamic response maps compared with the manual marking ground truth results. We explore the concordance between the maximum hemodynamic response and the intracerebral EEG defined EZ and find that both methods produce similar percentage of concordance (76.9%, 10 out of 13 patients, electrode was absent in the maximum hemodynamic response in two patients). This tool will make EEG-fMRI analysis more practical for clinical usage.
| S-EPMC5752096 | biostudies-literature
Project description:Recently, more personalized travel methods have emerged in the tourism industry, such as individual travel and self-guided travel. The service models of traditional tourism limit the diversity of service options and cannot fully meet the individual needs of tourists anymore. The aim is to integrate sparse tourism information on the Internet, thereby providing more convenient, faster, and more personalized tourism services. Based on the shortcomings of the traditional tourism recommendation system, a deep learning-based classification processing method of tourism product information is proposed. This method uses word embedding in the data preprocessing stage. The Convolutional Neural Network (CNN) is used to process review information of users and tourism service items. The Deep Neural Network (DNN) is used to process the necessary information of users and tourism service items. Also, factorization machine technology is used to learn the interaction between the extracted features to improve the prediction model. The results show that the proposed model can maintain an excellent precision of 64.2% when generating personalized recommendation lists for users. The sensitivity and accuracy of the recommendation list are better than other algorithms. By adding DNN, the word embedding method, and the factorization machine model, the precision is improved by 30%, 33.3%, and 40%, respectively. The model accuracy is the highest with 40 hidden factors, 100 convolutions, and a 100+50 combination hidden layer. Compared with traditional methods, the proposed algorithm can provide users with personalized travel products more accurately in personalized travel recommendations. The results have enriched and developed the theory of tourism service supply chain, providing a reference for constructing a personalized tourism service system.
| S-EPMC7714558 | biostudies-literature
Project description:Background: Magnetic resonance (MR) scans are routine clinical procedures for monitoring people with multiple sclerosis (PwMS). Patient discomfort, timely scheduling, and financial burden motivate the need to accelerate MR scan time. We examined the clinical application of a deep learning (DL) model in restoring the image quality of accelerated routine clinical brain MR scans for PwMS. Methods: We acquired fast 3D T1w BRAVO and fast 3D T2w FLAIR MRI sequences (half the phase encodes and half the number of slices) in parallel to conventional parameters. Using a subset of the scans, we trained a DL model to generate images from fast scans with quality similar to the conventional scans and then applied the model to the remaining scans. We calculated clinically relevant T1w volumetrics (normalized whole brain, thalamic, gray matter, and white matter volume) for all scans and T2 lesion volume in a sub-analysis. We performed paired t-tests comparing conventional, fast, and fast with DL for these volumetrics, and fit repeated measures mixed-effects models to test for differences in correlations between volumetrics and clinically relevant patient-reported outcomes (PRO). Results: We found statistically significant but small differences between conventional and fast scans with DL for all T1w volumetrics. There was no difference in the extent to which the key T1w volumetrics correlated with clinically relevant PROs of MS symptom burden and neurological disability. Conclusion: A deep learning model that improves the image quality of the accelerated routine clinical brain MR scans has the potential to inform clinically relevant outcomes in MS.
| S-EPMC8504490 | biostudies-literature
Project description:Behavioral health theory provides a framework for researchers to design, implement, and evaluate the effects of health promotion programs. However, limited research has examined theories used in interventions to promote long-term maintenance of health behaviors. The purpose of this review was to evaluate the available literature and identify prominent behavioral health theories used in intervention research to promote maintenance of health behaviors. We reviewed theories used in intervention research assessing long-term maintenance (≥ 6 months post-intervention) of physical activity, weight loss, and smoking cessation. Five prominent behavioral theories were referenced by the 34 studies included in the review: Self-Determination Theory, Theory of Planned Behavior, Social Cognitive Theory, Transtheoretical Model, and Social Ecological Model. Descriptions and examples of applications of these theories are provided. Implications for future research are discussed.
| S-EPMC5313056 | biostudies-literature