scholarly journals Automated tracking of level of consciousness and delirium in critical illness using deep learning

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Haoqi Sun ◽  
Eyal Kimchi ◽  
Oluwaseun Akeju ◽  
Sunil B. Nagaraj ◽  
Lauren M. McClain ◽  
...  
Keyword(s):  
Deep Learning ◽  
Critical Illness ◽  
Elective Surgery ◽  
Confusion Assessment Method ◽  
Assessment Method ◽  
Eeg Signals ◽  
Automated Tracking ◽  
Level Of Consciousness ◽  
Behavioral Assessments ◽  
Deep Learning Model

Abstract Over- and under-sedation are common in the ICU, and contribute to poor ICU outcomes including delirium. Behavioral assessments, such as Richmond Agitation-Sedation Scale (RASS) for monitoring levels of sedation and Confusion Assessment Method for the ICU (CAM-ICU) for detecting signs of delirium, are often used. As an alternative, brain monitoring with electroencephalography (EEG) has been proposed in the operating room, but is challenging to implement in ICU due to the differences between critical illness and elective surgery, as well as the duration of sedation. Here we present a deep learning model based on a combination of convolutional and recurrent neural networks that automatically tracks both the level of consciousness and delirium using frontal EEG signals in the ICU. For level of consciousness, the system achieves a median accuracy of 70% when allowing prediction to be within one RASS level difference across all patients, which is comparable or higher than the median technician–nurse agreement at 59%. For delirium, the system achieves an AUC of 0.80 with 69% sensitivity and 83% specificity at the optimal operating point. The results show it is feasible to continuously track level of consciousness and delirium in the ICU.

scholarly journals EEG Emotion Classification Using an Improved SincNet-Based Deep Learning Model

2019 ◽  
Vol 9 (11) ◽  
pp. 326 ◽  
Author(s):  
Hong Zeng ◽  
Zhenhua Wu ◽  
Jiaming Zhang ◽  
Chen Yang ◽  
Hua Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Speaker Recognition ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Signal To Noise Ratio ◽  
Single Subject ◽  
Emotion Classification ◽  
Eeg Signals ◽  
Electroencephalogram Eeg ◽  
Deep Learning Model

Deep learning (DL) methods have been used increasingly widely, such as in the fields of speech and image recognition. However, how to design an appropriate DL model to accurately and efficiently classify electroencephalogram (EEG) signals is still a challenge, mainly because EEG signals are characterized by significant differences between two different subjects or vary over time within a single subject, non-stability, strong randomness, low signal-to-noise ratio. SincNet is an efficient classifier for speaker recognition, but it has some drawbacks in dealing with EEG signals classification. In this paper, we improve and propose a SincNet-based classifier, SincNet-R, which consists of three convolutional layers, and three deep neural network (DNN) layers. We then make use of SincNet-R to test the classification accuracy and robustness by emotional EEG signals. The comparable results with original SincNet model and other traditional classifiers such as CNN, LSTM and SVM, show that our proposed SincNet-R model has higher classification accuracy and better algorithm robustness.

scholarly journals Improved Deep Feature Learning by Synchronization Measurements for Multi-Channel EEG Emotion Recognition

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-15 ◽  
Author(s):  
Hao Chao ◽  
Liang Dong ◽  
Yongli Liu ◽  
Baoyun Lu
Keyword(s):  
Deep Learning ◽  
Emotion Recognition ◽  
Affective Computing ◽  
Learning Model ◽  
Support Vector ◽  
Eeg Signals ◽  
Global Synchronization ◽  
Spatial Characteristics ◽  
Maximal Information Coefficient ◽  
Deep Learning Model

Emotion recognition based on multichannel electroencephalogram (EEG) signals is a key research area in the field of affective computing. Traditional methods extract EEG features from each channel based on extensive domain knowledge and ignore the spatial characteristics and global synchronization information across all channels. This paper proposes a global feature extraction method that encapsulates the multichannel EEG signals into gray images. The maximal information coefficient (MIC) for all channels was first measured. Subsequently, an MIC matrix was constructed according to the electrode arrangement rules and represented by an MIC gray image. Finally, a deep learning model designed with two principal component analysis convolutional layers and a nonlinear transformation operation extracted the spatial characteristics and global interchannel synchronization features from the constructed feature images, which were then input to support vector machines to perform the emotion recognition tasks. Experiments were conducted on the benchmark dataset for emotion analysis using EEG, physiological, and video signals. The experimental results demonstrated that the global synchronization features and spatial characteristics are beneficial for recognizing emotions and the proposed deep learning model effectively mines and utilizes the two salient features.

scholarly journals Advanced Age Is Associated With Catatonia in Critical Illness: Results From the Delirium and Catatonia Prospective Cohort Investigation

2021 ◽  
Vol 12 ◽  
Author(s):  
Jennifer Connell ◽  
Ahra Kim ◽  
Nathan E. Brummel ◽  
Mayur B. Patel ◽  
Simon N. Vandekar ◽  
...  
Keyword(s):  
Intensive Care ◽  
Critical Illness ◽  
Critically Ill ◽  
Rating Scale ◽  
Medical Center ◽  
Adult Population ◽  
Academic Medical Center ◽  
Confusion Assessment Method ◽  
Assessment Method ◽  
Advanced Age

Introduction: Catatonia, characterized by motor, behavioral and affective abnormalities, frequently co-occurs with delirium during critical illness. Advanced age is a known risk factor for development of delirium. However, the association between age and catatonia has not been described. We aim to describe the occurrence of catatonia, delirium, and coma by age group in a critically ill, adult population.Design: Convenience cohort, nested within two clinical trials and two observational cohort studies.Setting: Intensive care units in an academic medical center in Nashville, TN.Patients: 378 critically ill adult patients on mechanical ventilation and/or vasopressors.Measurements and Main Results: Patients were assessed for catatonia, delirium, and coma by independent and blinded personnel, the Bush Francis Catatonia Rating Scale, the Confusion Assessment Method for the Intensive Care Unit (ICU) and the Richmond Agitation and Sedation Scale. Of 378 patients, 23% met diagnostic criteria for catatonia, 66% experienced delirium, and 52% experienced coma during the period of observation. There was no relationship found between age and catatonia severity or age and presence of specific catatonia items. The prevalence of catatonia was strongly associated with age in the setting of critical illness (p < 0.05). Delirium and comas' association with age was limited to the setting of catatonia.Conclusion: Given the significant relationship between age and catatonia independent of coma and delirium status, these data demonstrate catatonia's association with advanced age in the setting of critical illness. Future studies can explore the causative factors for this association and further elucidate the risk factors for acute brain dysfunction across the age spectrum.

An Integrated Deep Learning Model for Motor Intention Recognition of Multi-Class EEG Signals in Upper Limb Amputees

2021 ◽  
pp. 106121
Author(s):  
Oluwagbenga Paul Idowu ◽  
Ademola Enitan Ilesanmi ◽  
Xiangxin Li ◽  
Oluwarotimi Williams Samuel ◽  
Peng Fang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Upper Limb ◽  
Learning Model ◽  
Eeg Signals ◽  
Intention Recognition ◽  
Motor Intention ◽  
Deep Learning Model

scholarly journals Cerebrospinal Fluid Concentration of Neurogranin in Hip Fracture Patients with Delirium

2021 ◽  
pp. 1-11
Author(s):  
Nathalie Bodd Halaas ◽  
Henrik Zetterberg ◽  
Ane-Victoria Idland ◽  
Anne-Brita Knapskog ◽  
Leiv Otto Watne ◽  
...  
Keyword(s):  
Cerebrospinal Fluid ◽  
Hip Fracture ◽  
Elective Surgery ◽  
Confusion Assessment Method ◽  
Assessment Method ◽  
Sensitivity Analyses ◽  
Synaptic Dysfunction ◽  
Increased Risk ◽  
Fluid Concentration ◽  
Early Alzheimer’S Disease

Background: Delirium is associated with an increased risk of incident dementia and accelerated progression of existing cognitive symptoms. Reciprocally, dementia increases the risk of delirium. Cerebrospinal fluid (CSF) concentration of the dendritic protein neurogranin has been shown to increase in early Alzheimer’s disease (AD), likely reflecting synaptic dysfunction and/or degeneration. Objective: To elucidate the involvement of synaptic dysfunction in delirium pathophysiology, we tested the association between CSF neurogranin concentration and delirium in hip fracture patients with different AD-biomarker profiles, while comparing them to cognitively unimpaired older adults (CUA) and AD patients. Methods: The cohort included hip fracture patients with (n = 70) and without delirium (n = 58), CUA undergoing elective surgery (n = 127), and AD patients (n = 46). CSF was collected preoperatively and diagnostically in surgery and AD patients respectively. CSF neurogranin concentrations were analyzed in all samples with an in-house ELISA. Delirium was assessed pre-and postoperatively in hip fracture patients by trained investigators using the Confusion Assessment Method. Hip fracture patients were further stratified based on pre-fracture dementia status, delirium subtype, and AD fluid biomarkers. Results: No association was found between delirium and CSF neurogranin concentration (main analysis: delirium versus no delirium, p = 0.68). Hip fracture patients had lower CSF neurogranin concentration than AD patients (p = 0.001) and CUA (p = 0.035) in age-adjusted sensitivity analyses. Conclusion: The findings suggest that delirium is not associated with increased CSF neurogranin concentration in hip fracture patients, possibly due to advanced neurodegenerative disease and age and/or because synaptic degeneration is not an important pathophysiological process in delirium.

scholarly journals Ultrabrief Screens for Detecting Delirium in Postoperative Cognitively Intact Older Adults

2020 ◽  
Vol 15 (9) ◽  
pp. 544-547
Author(s):  
Andrea Yevchak Sillner ◽  
Long Ngo ◽  
Yoojin Jung ◽  
Sharon Inouye ◽  
Marie Boltz ◽  
...  
Keyword(s):  
Older Adults ◽  
Postoperative Delirium ◽  
Elective Surgery ◽  
Confusion Assessment Method ◽  
Assessment Method ◽  
Reference Standard ◽  
Patient Reports ◽  
Confusion Assessment ◽  
Overall Performance ◽  
Cognitively Intact

The authors’ sought to develop an ultrabrief screen for postoperative delirium in cognitively intact patients older than 70 years undergoing major elective surgery. All possible combinations of one-, two- and three-item screens and their sensitivities, specificities, and 95% confidence intervals were calculated and compared with the delirium reference standard Confusion Assessment Method (CAM). Among the 560 participants (mean age, 77 years; 58% women), delirium occurred in 134 (24%). We considered 1,100 delirium assessments from postoperative days 1 and 2. The screen with the best overall performance consisted of three items: (1) Patient reports feeling confused, (2) Months of the year backward, and (3) “Does the patient appear sleepy?” with sensitivity of 92% and specificity of 72%. This brief, three-item screen rules out delirium quickly, identifies a subset of patients who require further testing, and may be an important tool to improve recognition of postoperative delirium.

scholarly journals An Earthquake Fatalities Assessment Method Based on Feature Importance with Deep Learning and Random Forest Models

2019 ◽  
Vol 11 (10) ◽  
pp. 2727 ◽  
Author(s):  
Hanxi Jia ◽  
Junqi Lin ◽  
Jinlong Liu
Keyword(s):  
Deep Learning ◽  
Random Forest ◽  
Regression Tree ◽  
Learning Model ◽  
Assessment Method ◽  
Classification And Regression Tree ◽  
Model Classification ◽  
China Mainland ◽  
Deep Learning Model ◽  
Earthquake Fatalities

This study aims to analyze and compare the importance of feature affecting earthquake fatalities in China mainland and establish a deep learning model to assess the potential fatalities based on the selected factors. The random forest (RF) model, classification and regression tree (CART) model, and AdaBoost model were used to assess the importance of nine features and the analysis showed that the RF model was better than the other models. Furthermore, we compared the contributions of 43 different structure types to casualties based on the RF model. Finally, we proposed a model for estimating earthquake fatalities based on the seismic data from 1992 to 2017 in China mainland. These results indicate that the deep learning model produced in this study has good performance for predicting seismic fatalities. The method could be helpful to reduce casualties during emergencies and future building construction.

scholarly journals Moving the Lab into the Mountains: A Pilot Study of Human Activity Recognition in Unstructured Environments

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 654
Author(s):  
Brian Russell ◽  
Andrew McDaid ◽  
William Toscano ◽  
Patria Hume
Keyword(s):  
Deep Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
A Priori ◽  
Parameter Tuning ◽  
Learning Model ◽  
Assessment Method ◽  
Human Activity Recognition ◽  
The One ◽  
Deep Learning Model

Goal: To develop and validate a field-based data collection and assessment method for human activity recognition in the mountains with variations in terrain and fatigue using a single accelerometer and a deep learning model. Methods: The protocol generated an unsupervised labelled dataset of various long-term field-based activities including run, walk, stand, lay and obstacle climb. Activity was voluntary so transitions could not be determined a priori. Terrain variations included slope, crossing rivers, obstacles and surfaces including road, gravel, clay, mud, long grass and rough track. Fatigue levels were modulated between rested to physical exhaustion. The dataset was used to train a deep learning convolutional neural network (CNN) capable of being deployed on battery powered devices. The human activity recognition results were compared to a lab-based dataset with 1,098,204 samples and six features, uniform smooth surfaces, non-fatigued supervised participants and activity labelling defined by the protocol. Results: The trail run dataset had 3,829,759 samples with five features. The repetitive activities and single instance activities required hyper parameter tuning to reach an overall accuracy 0.978 with a minimum class precision for the one-off activity (climbing gate) of 0.802. Conclusion: The experimental results showed that the CNN deep learning model performed well with terrain and fatigue variations compared to the lab equivalents (accuracy 97.8% vs. 97.7% for trail vs. lab). Significance: To the authors knowledge this study demonstrated the first successful human activity recognition (HAR) in a mountain environment. A robust and repeatable protocol was developed to generate a validated trail running dataset when there were no observers present and activity types changed on a voluntary basis across variations in terrain surface and both cognitive and physical fatigue levels.

scholarly journals ICU delirium burden predicts functional neurologic outcomes

PLoS ONE ◽  
2021 ◽  
Vol 16 (12) ◽  
pp. e0259840
Author(s):  
Luis Paixao ◽  
Haoqi Sun ◽  
Jacob Hogan ◽  
Katie Hartnack ◽  
Mike Westmeijer ◽  
...  
Keyword(s):  
Critical Illness ◽  
Confusion Assessment Method ◽  
Assessment Method ◽  
Neurologic Outcome ◽  
Post Discharge ◽  
Mechanically Ventilated ◽  
Neurological Outcomes ◽  
Survival Status ◽  
Neurologic Outcomes ◽  
Icu Delirium

Background We investigated the effect of delirium burden in mechanically ventilated patients, beginning in the ICU and continuing throughout hospitalization, on functional neurologic outcomes up to 2.5 years following critical illness. Methods Prospective cohort study of enrolling 178 consecutive mechanically ventilated adult medical and surgical ICU patients between October 2013 and May 2016. Altogether, patients were assessed daily for delirium 2941days using the Confusion Assessment Method for the ICU (CAM-ICU). Hospitalization delirium burden (DB) was quantified as number of hospital days with delirium divided by total days at risk. Survival status up to 2.5 years and neurologic outcomes using the Glasgow Outcome Scale were recorded at discharge 3, 6, and 12 months post-discharge. Results Of 178 patients, 19 (10.7%) were excluded from outcome analyses due to persistent coma. Among the remaining 159, 123 (77.4%) experienced delirium. DB was independently associated with >4-fold increased mortality at 2.5 years following ICU admission (adjusted hazard ratio [aHR], 4.77; 95% CI, 2.10–10.83; P < .001), and worse neurologic outcome at discharge (adjusted odds ratio [aOR], 0.02; 0.01–0.09; P < .001), 3 (aOR, 0.11; 0.04–0.31; P < .001), 6 (aOR, 0.10; 0.04–0.29; P < .001), and 12 months (aOR, 0.19; 0.07–0.52; P = .001). DB in the ICU alone was not associated with mortality (HR, 1.79; 0.93–3.44; P = .082) and predicted neurologic outcome less strongly than entire hospital stay DB. Similarly, the number of delirium days in the ICU and for whole hospitalization were not associated with mortality (HR, 1.00; 0.93–1.08; P = .917 and HR, 0.98; 0.94–1.03, P = .535) nor with neurological outcomes, except for the association between ICU delirium days and neurological outcome at discharge (OR, 0.90; 0.81–0.99, P = .038). Conclusions Delirium burden throughout hospitalization independently predicts long term neurologic outcomes and death up to 2.5 years after critical illness, and is more predictive than delirium burden in the ICU alone and number of delirium days.

scholarly journals Neurofilament Light in Serum and Cerebrospinal Fluid of Hip Fracture Patients with Delirium

2018 ◽  
Vol 46 (5-6) ◽  
pp. 346-357 ◽  
Author(s):  
Nathalie Bodd Halaas ◽  
Kaj Blennow ◽  
Ane-Victoria Idland ◽  
Torgeir Bruun Wyller ◽  
Johan Ræder ◽  
...  
Keyword(s):  
Cerebrospinal Fluid ◽  
Hip Fracture ◽  
Elective Surgery ◽  
Confusion Assessment Method ◽  
Assessment Method ◽  
Neurofilament Light ◽  
Cognitively Normal ◽  
Preoperative Serum ◽  
Median Serum ◽  
Postoperative Serum

Background: Delirium is associated with new-onset dementia, suggesting that delirium pathophysiology involves neuronal injury. Neurofilament light (NFL) is a sensitive biomarker for neuroaxonal injury. Methods: NFL was measured in cerebrospinal fluid (CSF) (n = 130), preoperative serum (n = 192), and postoperative serum (n = 280) in hip fracture patients, and in CSF (n = 123) and preoperative serum (n = 134) in cognitively normal older adults undergoing elective surgery. Delirium was diagnosed with the Confusion Assessment Method. Results: Median serum NFL (pg/mL) was elevated in delirium in hip fracture patients (94 vs. 54 pre- and 135 vs. 92 postoperatively, both p < 0.001). Median CSF NFL tended to be higher in hip fracture patients with delirium (1,804 vs. 1,636, p = 0.074). Serum and CSF NFL were positively correlated (ρ = 0.56, p < 0.001). Conclusion: Our findings support an association between neuroaxonal injury and delirium. The correlation between serum and CSF NFL supports the use of NFL as a blood biomarker in future delirium studies.

Sign in / Sign up

Export Citation Format

Share Document