scholarly journals Development and Evaluation of a Method for Automated Detection of Spreading Depolarizations in the Injured Human Brain

2021 ◽  
Author(s):  
Sharon Jewell ◽  
Stephen Hobson ◽  
Grant Brewer ◽  
Michelle Rogers ◽  
Jed A. Hartings ◽  
...  
Keyword(s):  
Intensive Care ◽  
Confidence Interval ◽  
Real Time ◽  
Ground Truth ◽  
Automated Detection ◽  
Pathogenic Potential ◽  
Data Files ◽  
Electrocorticogram Ecog ◽  
Prototype Software ◽  
Additional Loss

Abstract Background Spreading depolarizations (SDs) occur in some 60% of patients receiving intensive care following severe traumatic brain injury and often occur at a higher incidence following serious subarachnoid hemorrhage and malignant hemisphere stroke (MHS); they are independently associated with worse clinical outcome. Detection of SDs to guide clinical management, as is now being advocated, currently requires continuous and skilled monitoring of the electrocorticogram (ECoG), frequently extending over many days. Methods We developed and evaluated in two clinical intensive care units (ICU) a software routine capable of detecting SDs both in real time at the bedside and retrospectively and also capable of displaying patterns of their occurrence with time. We tested this prototype software in 91 data files, each of approximately 24 h, from 18 patients, and the results were compared with those of manual assessment (“ground truth”) by an experienced assessor blind to the software outputs. Results The software successfully detected SDs in real time at the bedside, including in patients with clusters of SDs. Counts of SDs by software (dependent variable) were compared with ground truth by the investigator (independent) using linear regression. The slope of the regression was 0.7855 (95% confidence interval 0.7149–0.8561); a slope value of 1.0 lies outside the 95% confidence interval of the slope, representing significant undersensitivity of 79%. R2 was 0.8415. Conclusions Despite significant undersensitivity, there was no additional loss of sensitivity at high SD counts, thus ensuring that dense clusters of depolarizations of particular pathogenic potential can be detected by software and depicted to clinicians in real time and also be archived.

scholarly journals Characterisation of Textile Embedded Electrodes for Use in a Neonatal Smart Mattress Electrocardiography System

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 999
Author(s):  
Henry Dore ◽  
Rodrigo Aviles-Espinosa ◽  
Zhenhua Luo ◽  
Oana Anton ◽  
Heike Rabe ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Heart Rate ◽  
Intensive Care ◽  
High Resolution ◽  
Neonatal Intensive Care Unit ◽  
Real Time ◽  
Neonatal Intensive Care ◽  
Delivery Room ◽  
Proof Of Concept ◽  
Heart Rate Monitoring

Heart rate monitoring is the predominant quantitative health indicator of a newborn in the delivery room. A rapid and accurate heart rate measurement is vital during the first minutes after birth. Clinical recommendations suggest that electrocardiogram (ECG) monitoring should be widely adopted in the neonatal intensive care unit to reduce infant mortality and improve long term health outcomes in births that require intervention. Novel non-contact electrocardiogram sensors can reduce the time from birth to heart rate reading as well as providing unobtrusive and continuous monitoring during intervention. In this work we report the design and development of a solution to provide high resolution, real time electrocardiogram data to the clinicians within the delivery room using non-contact electric potential sensors embedded in a neonatal intensive care unit mattress. A real-time high-resolution electrocardiogram acquisition solution based on a low power embedded system was developed and textile embedded electrodes were fabricated and characterised. Proof of concept tests were carried out on simulated and human cardiac signals, producing electrocardiograms suitable for the calculation of heart rate having an accuracy within ±1 beat per minute using a test ECG signal, ECG recordings from a human volunteer with a correlation coefficient of ~ 87% proved accurate beat to beat morphology reproduction of the waveform without morphological alterations and a time from application to heart rate display below 6 s. This provides evidence that flexible non-contact textile-based electrodes can be embedded in wearable devices for assisting births through heart rate monitoring and serves as a proof of concept for a complete neonate electrocardiogram monitoring system.

Māori health outcomes in an intensive care unit in Aotearoa New Zealand

2021 ◽  
pp. 0310057X2198971
Author(s):  
M Atif Mohd Slim ◽  
Hamish M Lala ◽  
Nicholas Barnes ◽  
Robert A Martynoga
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
New Zealand ◽  
Renal Replacement Therapy ◽  
Confidence Interval ◽  
Health Outcomes ◽  
Odds Ratio ◽  
Adjusted Odds Ratio ◽  
One Year ◽  
Maori Health

Māori are the indigenous people of New Zealand, and suffer disparate health outcomes compared to non-Māori. Waikato District Health Board provides level III intensive care unit services to New Zealand’s Midland region. In 2016, our institution formalised a corporate strategy to eliminate health inequities for Māori. Our study aimed to describe Māori health outcomes in our intensive care unit and identify inequities. We performed a retrospective audit of prospectively entered data in the Australian and New Zealand Intensive Care Society database for all general intensive care unit admissions over 15 years of age to Waikato Hospital from 2014 to 2018 ( n = 3009). Primary outcomes were in–intensive care unit and in-hospital mortality. The secondary outcome was one-year mortality. In our study, Māori were over-represented relative to the general population. Compared to non-Māori, Māori patients were younger (51 versus 61 years, P < 0.001), and were more likely to reside outside of the Waikato region (37.2% versus 28.0%, P < 0.001) and in areas of higher deprivation ( P < 0.001). Māori had higher admission rates for trauma and sepsis ( P < 0.001 overall) and required more renal replacement therapy ( P < 0.001). There was no difference in crude and adjusted mortality in–intensive care unit (16.8% versus 16.5%, P = 0.853; adjusted odds ratio 0.98 (95% confidence interval 0.68 to 1.40)) or in-hospital (23.7% versus 25.7%, P = 0.269; adjusted odds ratio 0.84 (95% confidence interval 0.60 to 1.18)). One-year mortality was similar (26.1% versus 27.1%, P=0.6823). Our study found significant ethnic inequity in the intensive care unit for Māori, who require more renal replacement therapy and are over-represented in admissions, especially for trauma and sepsis. These findings suggest upstream factors increasing Māori risk for critical illness. There was no difference in mortality outcomes.

scholarly journals Automated Detection of Short Optical Transients of Astrophysical Origin in Real Time

2010 ◽  
Vol 2010 ◽  
pp. 1-11 ◽  
Author(s):  
Marcin Sokołowski ◽  
Katarzyna Małek ◽  
Lech W. Piotrowski ◽  
Grzegorz Wrochna
Keyword(s):  
Real Time ◽  
Early Period ◽  
Automated Detection ◽  
Important Task ◽  
The Real ◽  
Optical Transients ◽  
Robotic Telescopes ◽  
Optical Flashes ◽  
Optical Transient

The detection of short optical transients of astrophysical origin in real time is an important task for existing robotic telescopes. The faster a new optical transient is detected, the earlier follow-up observations can be started. The sooner the object is identified, the more data can be collected before the source fades away, particularly in the most interesting early period of the transient. In this the real-time pipeline designed for identification of optical flashes with the “Pi of the Sky” project will be presented in detail together with solutions used by other experiments.

Deep learning for automated detection and numbering of permanent teeth on panoramic images

2021 ◽  
Author(s):  
Mohamed Estai ◽  
Marc Tennant ◽  
Dieter Gebauer ◽  
Andrew Brostek ◽  
Janardhan Vignarajan ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Detection System ◽  
Ground Truth ◽  
Automated Detection ◽  
Permanent Teeth ◽  
Automated Method ◽  
Step Procedure ◽  
Panoramic Images ◽  
Tooth Number

Objective: This study aimed to evaluate an automated detection system to detect and classify permanent teeth on orthopantomogram (OPG) images using convolutional neural networks (CNNs). Methods: In total, 591 digital OPGs were collected from patients older than 18 years. Three qualified dentists performed individual teeth labelling on images to generate the ground truth annotations. A three-step procedure, relying upon CNNs, was proposed for automated detection and classification of teeth. Firstly, U-Net, a type of CNN, performed preliminary segmentation of tooth regions or detecting regions of interest (ROIs) on panoramic images. Secondly, the Faster R-CNN, an advanced object detection architecture, identified each tooth within the ROI determined by the U-Net. Thirdly, VGG-16 architecture classified each tooth into 32 categories, and a tooth number was assigned. A total of 17,135 teeth cropped from 591 radiographs were used to train and validate the tooth detection and tooth numbering modules. 90% of OPG images were used for training, and the remaining 10% were used for validation. 10-folds cross-validation was performed for measuring the performance. The intersection over union (IoU), F1 score, precision, and recall (i.e. sensitivity) were used as metrics to evaluate the performance of resultant CNNs. Results: The ROI detection module had an IoU of 0.70. The tooth detection module achieved a recall of 0.99 and a precision of 0.99. The tooth numbering module had a recall, precision and F1 score of 0.98. Conclusion: The resultant automated method achieved high performance for automated tooth detection and numbering from OPG images. Deep learning can be helpful in the automatic filing of dental charts in general dentistry and forensic medicine.

A machine learning-based model for predicting intensive care unit length of stay in patients with cardiac surgery (Preprint)

2021 ◽  
Author(s):  
Nianyue Wu ◽  
Siru Liu ◽  
Haotian Zhang ◽  
Xiaomin Hou ◽  
Ping Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Length Of Stay ◽  
Confidence Interval ◽  
Medical Information ◽  
Lasso Regression ◽  
Icu Length Of Stay ◽  
Data Source ◽  
The Mean ◽  
Selection Operator

BACKGROUND The intensive care unit (ICU) length of stay is significant to evaluate the effect of cardiac surgical treatment inpatient. OBJECTIVE This research aims to accurately predict the ICU length of stay in patients with cardiac surgery. Methods: We used machine learning methods to construct the model, and the medical information mart for intensive care (MIMIC IV) database was used as the data source. A total of 7,567 patients were enrolled and the mean length of stay in the ICU was 3.12 days. A total of 126 predictors were included, and 44 important predictors were screened by least absolute shrinkage and selection operator (Lasso) regression. METHODS We used machine learning methods to construct the model, and the medical information mart for intensive care (MIMIC IV) database was used as the data source. A total of 7,567 patients were enrolled and the mean length of stay in the ICU was 3.12 days. A total of 126 predictors were included, and 44 important predictors were screened by least absolute shrinkage and selection operator (Lasso) regression. RESULTS The mean accuracy are 0.603 (95% confidence interval (CI): [0.602-0.604]), 0.687 (95% confidence interval (CI): [0.687-0.688]) and 0.688 (95% confidence interval (CI): [0.687-0.689]) for the logistic regression (LR) with all variables, the gradient boosted decision tree (GBDT) with important variables and the GBDT with all variables respectively. CONCLUSIONS The GBDT model with important predictors partly overestimated patients whose length of stay was less than 3 days and underestimated patients whose length of stay was longer than 3 days. But the better prediction performance of GBDT facilitates early intervention of ICU patients with a long period of hospitalization.

Automated detection of nosocomial infections: evaluation of different strategies in an intensive care unit 2000–2006

2011 ◽  
Vol 79 (1) ◽  
pp. 38-43 ◽  
Author(s):  
S. Bouzbid ◽  
Q. Gicquel ◽  
S. Gerbier ◽  
M. Chomarat ◽  
E. Pradat ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Nosocomial Infections ◽  
Automated Detection
Sign in / Sign up

Export Citation Format

Share Document