scholarly journals Predictive analysis of patient recovery from cardiac-respiratory arrest

2019 ◽  
Author(s):  
A. Floyrac ◽  
A. Doumergue ◽  
N. Kubis ◽  
D. Holcman
Keyword(s):  
Input Data ◽  
Cross Validation ◽  
Event Related Potentials ◽  
Respiratory Arrest ◽  
Predictive Analysis ◽  
Two Dimensional ◽  
Auditory Responses ◽  
Related Potentials ◽  
Validation Procedure ◽  
Anoxic Coma

AbstractThe severity of neuronal damages in comatose patients following anoxic brain injury can be probed by evoked auditory responses. However, it remains challenging to predict the return to full consciousness of post-anoxic coma of hospitalized patients. We presented here a method to predict the return to consciousness based on the analysis of periodic responses to auditory stimulations, recorded from surface cranial electrodes. The input data are event-related potentials (ERPs), recorded non-invasively with electro-encephalography (EEG). We extracted several novel features from the time series responses in a window of few hundreds of milliseconds from deviant and non-deviant auditory stimulations. We use these features to construct two-dimensional statistical maps, that show two separated clusters for recovered (conscience) and deceased patients, leading to a high classification success as tested by a cross-validation procedure. Finally, using Gaussian, K-neighborhood and SVM classifiers, we construct probabilistic maps to predict the outcome of post-anoxic coma. To conclude, statistics of deviant and non-deviant responses considered separately provide complementary and confirmatory predictions for the outcome of anoxic coma.

scholarly journals Neurophysiological Correlates of Concussion: Deep Learning for Clinical Assessment

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Rober Boshra ◽  
Kyle I. Ruiter ◽  
Carol DeMatteo ◽  
James P. Reilly ◽  
John F. Connolly
Keyword(s):  
Cross Validation ◽  
Assessment Tool ◽  
Event Related Potentials ◽  
Population Level ◽  
Single Trial ◽  
Clinical Integration ◽  
Concussion Management ◽  
Related Potentials ◽  
Fold Cross Validation ◽  
Trial Performance

AbstractConcussion has been shown to leave the afflicted with significant cognitive and neurobehavioural deficits. The persistence of these deficits and their link to neurophysiological indices of cognition, as measured by event-related potentials (ERP) using electroencephalography (EEG), remains restricted to population level analyses that limit their utility in the clinical setting. In the present paper, a convolutional neural network is extended to capitalize on characteristics specific to EEG/ERP data in order to assess for post-concussive effects. An aggregated measure of single-trial performance was able to classify accurately (85%) between 26 acutely to post-acutely concussed participants and 28 healthy controls in a stratified 10-fold cross-validation design. Additionally, the model was evaluated in a longitudinal subsample of the concussed group to indicate a dissociation between the progression of EEG/ERP and that of self-reported inventories. Concordant with a number of previous studies, symptomatology was found to be uncorrelated to EEG/ERP results as assessed with the proposed models. Our results form a first-step towards the clinical integration of neurophysiological results in concussion management and motivate a multi-site validation study for a concussion assessment tool in acute and post-acute cases.

scholarly journals A dimension reduction technique applied to regression on high dimension, low sample size neurophysiological data sets

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Adrielle C. Santana ◽  
Adriano V. Barbosa ◽  
Hani C. Yehia ◽  
Rafael Laboissière
Keyword(s):  
Sample Size ◽  
Frequency Domain ◽  
High Dimension ◽  
Cross Validation ◽  
Signal To Noise Ratio ◽  
Event Related Potentials ◽  
Discrete Wavelet ◽  
Prediction Errors ◽  
Time Frequency ◽  
Related Potentials

Abstract Background A common problem in neurophysiological signal processing is the extraction of meaningful information from high dimension, low sample size data (HDLSS). We present RoLDSIS (regression on low-dimension spanned input space), a regression technique based on dimensionality reduction that constrains the solution to the subspace spanned by the available observations. This avoids regularization parameters in the regression procedure, as needed in shrinkage regression methods. Results We applied RoLDSIS to the EEG data collected in a phonemic identification experiment. In the experiment, morphed syllables in the continuum /da/–/ta/ were presented as acoustic stimuli to the participants and the event-related potentials (ERP) were recorded and then represented as a set of features in the time-frequency domain via the discrete wavelet transform. Each set of stimuli was chosen from a preliminary identification task executed by the participant. Physical and psychophysical attributes were associated to each stimulus. RoLDSIS was then used to infer the neurophysiological axes, in the feature space, associated with each attribute. We show that these axes can be reliably estimated and that their separation is correlated with the individual strength of phonemic categorization. The results provided by RoLDSIS are interpretable in the time-frequency domain and may be used to infer the neurophysiological correlates of phonemic categorization. A comparison with commonly used regularized regression techniques was carried out by cross-validation. Conclusion The prediction errors obtained by RoLDSIS are comparable to those obtained with Ridge Regression and smaller than those obtained with LASSO and SPLS. However, RoLDSIS achieves this without the need for cross-validation, a procedure that requires the extraction of a large amount of observations from the data and, consequently, a decreased signal-to-noise ratio when averaging trials. We show that, even though RoLDSIS is a simple technique, it is suitable for the processing and interpretation of neurophysiological signals.

Face and Word Recognition in Patients with Left and Right Hemispheric Lesions: Evidence from Reaction Times and ERPs

2002 ◽  
Vol 13 (1) ◽  
pp. 69-83 ◽  
Author(s):  
Stefan R. Schweinberger ◽  
Thomas Klos ◽  
Werner Sommer
Keyword(s):  
Slow Wave ◽  
Reaction Times ◽  
Memory Search ◽  
Event Related Potentials ◽  
Performance Deficits ◽  
Set Size ◽  
Left Brain ◽  
Related Potentials ◽  
Abstract Words ◽  
Left Brain Damage

Abstract: We recorded reaction times (RTs) and event-related potentials (ERPs) in patients with unilateral lesions during a memory search task. Participants memorized faces or abstract words, which were then recognized among new ones. The RT deficit found in patients with left brain damage (LBD) for words increased with memory set size, suggesting that their problem relates to memory search. In contrast, the RT deficit found in patients with RBD for faces was apparently related to perceptual encoding, a conclusion also supported by their reduced P100 ERP component. A late slow wave (720-1720 ms) was enhanced in patients, particularly to words in patients with LBD, and to faces in patients with RBD. Thus, the slow wave was largest in the conditions with most pronounced performance deficits, suggesting that it reflects deficit-related resource recruitment.

Sign in / Sign up

Export Citation Format

Share Document