scholarly journals Prediction of Recovery from Traumatic Brain Injury with EEG Power Spectrum in Combination of Independent Component Analysis and RUSBoost Model

2022 ◽  
Vol 2 (1) ◽  
pp. 106-123
Author(s):  
Nor Safira Elaina Mohd Noor ◽  
Haidi Ibrahim ◽  
Muhammad Hanif Che Lah ◽  
Jafri Malin Abdullah
Keyword(s):  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Independent Component Analysis ◽  
Model Development ◽  
Area Under The Curve ◽  
Predictive Performance ◽  
Component Analysis ◽  
Independent Component ◽  
Moderate Traumatic Brain Injury ◽  
Continuous Eeg

The computational electroencephalogram (EEG) is recently garnering significant attention in examining whether the quantitative EEG (qEEG) features can be used as new predictors for the prediction of recovery in moderate traumatic brain injury (TBI). However, the brain’s recorded electrical activity has always been contaminated with artifacts, which in turn further impede the subsequent processing steps. As a result, it is crucial to devise a strategy for meticulously flagging and extracting clean EEG data to retrieve high-quality discriminative features for successful model development. This work proposed the use of multiple artifact rejection algorithms (MARA), which is an independent component analysis (ICA)-based algorithm, to eliminate artifacts automatically, and explored their effects on the predictive performance of the random undersampling boosting (RUSBoost) model. Continuous EEG were acquired using 64 electrodes from 27 moderate TBI patients at four weeks to one-year post-accident. The MARA incorporates an artifact removal stage based on ICA prior to RUSBoost, SVM, DT, and k-NN classification. The area under the curve (AUC) of RUSBoost was higher in absolute power spectral density (PSD) in AUCδ = 0.75, AUC α = 0.73 and AUCθ = 0.71 bands than SVM, DT, and k-NN. The MARA has provided a good generalization performance of the RUSBoost prediction model.

scholarly journals Changes in the gray and white matter of patients with ischemic-edematous insults after traumatic brain injury

2019 ◽  
Vol 131 (4) ◽  
pp. 1243-1253 ◽  
Author(s):  
Hakseung Kim ◽  
Young-Tak Kim ◽  
Eun-Suk Song ◽  
Byung C. Yoon ◽  
Young Hun Choi ◽  
...  
Keyword(s):  
Traumatic Brain Injury ◽  
Brain Injury ◽  
White Matter ◽  
Area Under The Curve ◽  
Hounsfield Unit ◽  
Predictive Performance ◽  
Prognostic Models ◽  
Quantitative Ct ◽  
Densitometric Analysis ◽  
Secondary Insult

OBJECTIVEGray matter (GM) and white matter (WM) are vulnerable to ischemic-edematous insults after traumatic brain injury (TBI). The extent of secondary insult after brain injury is quantifiable using quantitative CT analysis. One conventional quantitative CT measure, the gray-white matter ratio (GWR), and a more recently proposed densitometric analysis are used to assess the extent of these insults. However, the prognostic capacity of the GWR in patients with TBI has not yet been validated. This study aims to test the prognostic value of the GWR and evaluate the alternative parameters derived from the densitometric analysis acquired during the acute phase of TBI. In addition, the prognostic ability of the conventional TBI prognostic models (i.e., IMPACT [International Mission for Prognosis and Analysis of Clinical Trials in TBI] and CRASH [Corticosteroid Randomisation After Significant Head Injury] models) were compared to that of the quantitative CT measures.METHODSThree hundred patients with TBI of varying ages (92 pediatric, 94 adult, and 114 geriatric patients) and admitted between 2008 and 2013 were included in this retrospective cohort study. The normality of the density of the deep GM and whole WM was evaluated as the proportion of CT pixels with Hounsfield unit values of 31–35 for GM and 26–30 for WM on CT images of the entire supratentorial brain. The outcome was evaluated using the Glasgow Outcome Scale (GOS) at discharge (GOS score ≤ 3, n = 100).RESULTSLower proportions of normal densities in the deep GM and whole WM indicated worse outcomes. The proportion of normal WM exhibited a significant prognostic capacity (area under the curve [AUC] = 0.844). The association between the outcome and the normality of the WM density was significant in adult (AUC = 0.792), pediatric (AUC = 0.814), and geriatric (AUC = 0.885) patients. In pediatric patients, the normality of the overall density and the density of the GM were indicative of the outcome (AUC = 0.751). The average GWR was not associated with the outcome (AUC = 0.511). IMPACT and CRASH models showed adequate and reliable performance in the pediatric and geriatric groups but not in the adult group. The highest overall predictive performance was achieved by the densitometry-augmented IMPACT model (AUC = 0.881).CONCLUSIONSBoth deep GM and WM are susceptible to ischemic-edematous insults during the early phase of TBI. The extent of the secondary injury was better evaluated by analyzing the normality of the deep GM and WM rather than by calculating the GWR.

scholarly journals A Predictive Model for Postoperative Progressive Haemorrhagic Injury in Traumatic Brain Injuries

2021 ◽  
Author(s):  
Tiange Chen ◽  
Siming Chen ◽  
Yilei Chen ◽  
Lei Wang ◽  
Yun Wu ◽  
...  
Keyword(s):  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Predictive Model ◽  
Brain Injuries ◽  
Univariate Analysis ◽  
Area Under The Curve ◽  
Predictive Performance ◽  
Individual Risk ◽  
Lasso Regression ◽  
Predictive Tool

Abstract Background Progressive haemorrhagic injury after surgery in patients with traumatic brain injury often results in poor patient outcomes. This study aimed to develop and validate a practical predictive tool that can reliably estimate the risk of postoperative progressive haemorrhagic injury (PHI) in patients with traumatic brain injury (TBI). Methods Data from 645 patients who underwent surgery for TBI between March 2018 and December 2020 were collected. The outcome was postoperative intracranial PHI, which was assessed on postoperative computed tomography. The least absolute shrinkage and selection operator (LASSO) regression model, univariate analysis, and Delphi method were applied to select the most relevant prognostic predictors. We combined conventional coagulation test (CCT) data, thromboelastography (TEG) variables, and several predictors to develop a predictive model using binary logistic regression and then presented the results as a nomogram. The predictive performance of the model was assessed with calibration and discrimination. Internal validation was assessed. ResultsThe signature, which consisted of 11 selected features, was significantly associated with intracranial PHI (p < 0.05, for both primary and validation cohorts). Predictors in the prediction nomogram included age, S-pressure, D-pressure, pulse, temperature, reaction time, PLT, prothrombin time, activated partial thromboplastin time, FIB, and kinetics values. The model showed good discrimination, with an area under the curve of 0.8694 (95% CI, 0.8083–0.9304), and good 3 calibration. ConclusionThis model is based on a nomogram incorporating CCT and TEG variables, which can be conveniently derived at hospital admission. It allows determination of this individual risk for postoperative intracranial PHI and will facilitate a timely intervention to improve outcomes.

scholarly journals A predictive model for postoperative progressive haemorrhagic injury in traumatic brain injuries

BMC Neurology ◽  
2022 ◽  
Vol 22 (1) ◽  
Author(s):  
Tiange Chen ◽  
Siming Chen ◽  
Yun Wu ◽  
Yilei Chen ◽  
Lei Wang ◽  
...  
Keyword(s):  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Predictive Model ◽  
Brain Injuries ◽  
Univariate Analysis ◽  
Area Under The Curve ◽  
Predictive Performance ◽  
Individual Risk ◽  
Lasso Regression ◽  
Predictive Tool

Abstract Background Progressive haemorrhagic injury after surgery in patients with traumatic brain injury often results in poor patient outcomes. This study aimed to develop and validate a practical predictive tool that can reliably estimate the risk of postoperative progressive haemorrhagic injury (PHI) in patients with traumatic brain injury (TBI). Methods Data from 645 patients who underwent surgery for TBI between March 2018 and December 2020 were collected. The outcome was postoperative intracranial PHI, which was assessed on postoperative computed tomography. The least absolute shrinkage and selection operator (LASSO) regression model, univariate analysis, and Delphi method were applied to select the most relevant prognostic predictors. We combined conventional coagulation test (CCT) data, thromboelastography (TEG) variables, and several predictors to develop a predictive model using binary logistic regression and then presented the results as a nomogram. The predictive performance of the model was assessed with calibration and discrimination. Internal validation was assessed. Results The signature, which consisted of 11 selected features, was significantly associated with intracranial PHI (p < 0.05, for both primary and validation cohorts). Predictors in the prediction nomogram included age, S-pressure, D-pressure, pulse, temperature, reaction time, PLT, prothrombin time, activated partial thromboplastin time, FIB, and kinetics values. The model showed good discrimination, with an area under the curve of 0.8694 (95% CI, 0.8083–0.9304), and good calibration. Conclusion This model is based on a nomogram incorporating CCT and TEG variables, which can be conveniently derived at hospital admission. It allows determination of this individual risk for postoperative intracranial PHI and will facilitate a timely intervention to improve outcomes.

Skin Chromophore Estimation from Mobile Selfie Images using Constrained Independent Component Analysis

2020 ◽  
Vol 2020 (14) ◽  
pp. 357-1-357-6
Author(s):  
Luisa F. Polanía ◽  
Raja Bala ◽  
Ankur Purwar ◽  
Paul Matts ◽  
Martin Maltz
Keyword(s):  
Independent Component Analysis ◽  
Spectral Reflectance ◽  
Source Separation ◽  
Principal Component ◽  
Component Analysis ◽  
Previous Method ◽  
Independent Component ◽  
Light Transport ◽  
Camera Model ◽  
Constrained Independent Component Analysis

Human skin is made up of two primary chromophores: melanin, the pigment in the epidermis giving skin its color; and hemoglobin, the pigment in the red blood cells of the vascular network within the dermis. The relative concentrations of these chromophores provide a vital indicator for skin health and appearance. We present a technique to automatically estimate chromophore maps from RGB images of human faces captured with mobile devices such as smartphones. The ultimate goal is to provide a diagnostic aid for individuals to monitor and improve the quality of their facial skin. A previous method approaches the problem as one of blind source separation, and applies Independent Component Analysis (ICA) in camera RGB space to estimate the chromophores. We extend this technique in two important ways. First we observe that models for light transport in skin call for source separation to be performed in log spectral reflectance coordinates rather than in RGB. Thus we transform camera RGB to a spectral reflectance space prior to applying ICA. This process involves the use of a linear camera model and Principal Component Analysis to represent skin spectral reflectance as a lowdimensional manifold. The camera model requires knowledge of the incident illuminant, which we obtain via a novel technique that uses the human lip as a calibration object. Second, we address an inherent limitation with ICA that the ordering of the separated signals is random and ambiguous. We incorporate a domain-specific prior model for human chromophore spectra as a constraint in solving ICA. Results on a dataset of mobile camera images show high quality and unambiguous recovery of chromophores.

Exploring Independent Component Analysis for GPR Signal Processing

PIERS Online ◽  
2005 ◽  
Vol 1 (6) ◽  
pp. 750-753 ◽  
Author(s):  
Anxing Zhao ◽  
Yansheng Jiang ◽  
Wenbing Wang
Keyword(s):  
Signal Processing ◽  
Independent Component Analysis ◽  
Component Analysis ◽  
Independent Component
Sign in / Sign up

Export Citation Format

Share Document