Patient's airway monitoring during cardiopulmonary resuscitation using deep networks.

Cardiopulmonary resuscitation (CPR) is a crucial life-saving technique commonly administered to individuals experiencing cardiac arrest. Among the important aspects of CPR is ensuring the correct airway position of the patient, which is typically monitored by human tutors or supervisors. This study aims to utilize deep transfer learning for the detection of the patient's correct and incorrect airway position during cardiopulmonary resuscitation. To address the challenge of identifying the airway position, we curated a dataset consisting of 198 recorded video sequences, each lasting 6-8 s, showcasing both correct and incorrect airway positions during mouth-to-mouth breathing and breathing with an Ambu Bag. We employed six cutting-edge deep networks, namely DarkNet19, EfficientNetB0, GoogleNet, MobileNet-v2, ResNet50, and NasnetMobile. These networks were initially pre-trained on computer vision data and subsequently fine-tuned using the CPR dataset. The validation of the fine-tuned networks in detecting the patient's correct airway position during mouth-to-mouth breathing achieved impressive results, with the best sensitivity (98.8 %), specificity (100 %), and F-measure (97.2 %). Similarly, the detection of the patient's correct airway position during breathing with an Ambu Bag exhibited excellent performance, with the best sensitivity (100 %), specificity (99.8 %), and F-measure (99.7 %).

Learning-to-augment incorporated noise-robust deep CNN for detection of COVID-19 in noisy X-ray images.

Deep convolutional neural networks (CNNs) are used for the detection of COVID-19 in X-ray images. The detection performance of deep CNNs may be reduced by noisy X-ray images. To improve the robustness of a deep CNN against impulse noise, we propose a novel CNN approach using adaptive convolution, with the aim to ameliorate COVID-19 detection in noisy X-ray images without requiring any preprocessing for noise removal. This approach includes an impulse noise-map layer, an adaptive resizing layer, and an adaptive convolution layer to the conventional CNN framework. We also used a learning-to-augment strategy using noisy X-ray images to improve the generalization of a deep CNN. We have collected a dataset of 2093 chest X-ray images including COVID-19 (452 images), non-COVID pneumonia (621 images), and healthy ones (1020 images). The architecture of pre-trained networks such as SqueezeNet, GoogleNet, MobileNetv2, ResNet18, ResNet50, ShuffleNet, and EfficientNetb0 has been modified to increase their robustness to impulse noise. Validation on the noisy X-ray images using the proposed noise-robust layers and learning-to-augment strategy-incorporated ResNet50 showed 2% better classification accuracy compared with state-of-the-art method.

Active deep learning from a noisy teacher for semi-supervised 3D image segmentation: Application to COVID-19 pneumonia infection in CT.

Supervised deep learning has become a standard approach to solving medical image segmentation tasks. However, serious difficulties in attaining pixel-level annotations for sufficiently large volumetric datasets in real-life applications have highlighted the critical need for alternative approaches, such as semi-supervised learning, where model training can leverage small expert-annotated datasets to enable learning from much larger datasets without laborious annotation. Most of the semi-supervised approaches combine expert annotations and machine-generated annotations with equal weights within deep model training, despite the latter annotations being relatively unreliable and likely to affect model optimization negatively. To overcome this, we propose an active learning approach that uses an example re-weighting strategy, where machine-annotated samples are weighted (i) based on the similarity of their gradient directions of descent to those of expert-annotated data, and (ii) based on the gradient magnitude of the last layer of the deep model. Specifically, we present an active learning strategy with a query function that enables the selection of reliable and more informative samples from machine-annotated batch data generated by a noisy teacher. When validated on clinical COVID-19 CT benchmark data, our method improved the performance of pneumonia infection segmentation compared to the state of the art.

Greedy Autoaugment for classification of mycobacterium tuberculosis image via generalized deep CNN using mixed pooling based on minimum square rough entropy.

Although tuberculosis (TB) is a disease whose cause, epidemiology and treatment are well known, some infected patients in many parts of the world are still not diagnosed by current methods, leading to further transmission in society. Creating an accurate image-based processing system for screening patients can help in the early diagnosis of this disease. We provided a dataset containing1078 confirmed negative and 469 positive Mycobacterium tuberculosis instances. An effective method using an improved and generalized convolutional neural network (CNN) was proposed for classifying TB bacteria in microscopic images. In the preprocessing phase, the insignificant parts of microscopic images are excluded with an efficient algorithm based on the square rough entropy (SRE) thresholding. Top 10 policies of data augmentation were selected with the proposed model based on the Greedy AutoAugment algorithm to resolve the overfitting problem. In order to improve the generalization of CNN, mixed pooling was used instead of baseline one. The results showed that employing generalized pooling, batch normalization, Dropout, and PReLU have improved the classification of Mycobacterium tuberculosis images. The output of classifiers such as Naïve Bayes-LBP, KNN-LBP, GBT-LBP, Naïve Bayes-HOG, KNN-HOG, SVM-HOG, GBT-HOG indicated that proposed CNN has the best results with an accuracy of 93.4%. The improvements of CNN based on the proposed model can yield promising results for diagnosing TB.

Internet of things in the management of chronic diseases during the COVID-19 pandemic: A systematic review.

Introduction: The use of new technologies such as the Internet of Things (IoT) in the management of chronic diseases, especially in the COVID pandemics, could be a life-saving appliance for public health practice. The purpose of the current study is to identify the applications and capability of IoT and digital health in the management of the COVID-19 pandemic. Methods: This systematic review was conducted by searching the online databases of PubMed, Scopus, and Web of Science using selected keywords to retrieve the relevant literature published until December 25th, 2021. The most relevant original English studies were included after initial screening based on the inclusion criteria. Results: Overall, 18 studies were included. Most of the studies reported benefits and positive responses in the form of patients' and healthcare providers' satisfaction and trust in the online systems. Many services were provided to the patients, including but not limited to training the patients on their conditions; monitoring vital signs and required actions when vital signs were altered; ensuring treatment adherence; monitoring and consulting the patients regarding diet, physical activity, and lifestyle. Conclusion: IoT is a new technology, which can help us improve health care services during the COVID-19 pandemic. It has a network of various sensors, obtaining data from patients. We have found several applications for this technology. Future studies can be conducted for the capability of other technologies in the management of chronic diseases.

Comparing the Effects of Pulsatile and Continuous Flushing on Time and Type of Peripheral Intravenous Catheters Patency: A Randomized Clinical Trial.

Introduction: Peripheral intravenous catheters (PICs) patency techniques such as flushing are being developed. According to some studies, flushing can be used continuously or in pulsatile forms. This study aimed to compare the effects of pulsatile flushing (PF) and continuous flushing (CF) on time and type of PICs patency. Methods: In this double-blind randomized clinical trial, 71 patients were randomly assigned into two groups of PF (n=35) and CF (n=36). The PF protocol was performed as successive injections of 1 mL normal saline (N/S) per second (sec) with a delay of less than 1 sec until the completion of 5 mL of solution. However, CF protocol was performed by injecting 5 mL N/S within 5 sec without any delay before and after each medicine administration. Data related to the time and type of PICs patency were collected using a patency checklist every 12 hours (h) up to 96 h. The statistical analysis was done by R statistical software (Version 3.5.1). Results: The results showed that the number of PICs remaining open was not significantly different between PF and CF groups during 96 h. The highest number of PICs excluded from the study was related to the time of 96 h as a result of partial patency in the two groups. Conclusion: There was no difference between CF and PF regarding the time and type of PICs patency. Thus, both techniques can be used to maintain the catheter patency.

Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images.

Chest X-ray images are used in deep convolutional neural networks for the detection of COVID-19, the greatest human challenge of the 21st century. Robustness to noise and improvement of generalization are the major challenges in designing these networks. In this paper, we introduce a strategy for data augmentation using the determination of the type and value of noise density to improve the robustness and generalization of deep CNNs for COVID-19 detection. Firstly, we present a learning-to-augment approach that generates new noisy variants of the original image data with optimized noise density. We apply a Bayesian optimization technique to control and choose the optimal noise type and its parameters. Secondly, we propose a novel data augmentation strategy, based on denoised X-ray images, that uses the distance between denoised and original pixels to generate new data. We develop an autoencoder model to create new data using denoised images corrupted by the Gaussian and impulse noise. A database of chest X-ray images, containing COVID-19 positive, healthy, and non-COVID pneumonia cases, is used to fine-tune the pre-trained networks (AlexNet, ShuffleNet, ResNet18, and GoogleNet). The proposed method performs better results compared to the state-of-the-art learning to augment strategies in terms of sensitivity (0.808), specificity (0.915), and F-Measure (0.737). The source code of the proposed method is available at https://github.com/mohamadmomeny/Learning-to-augment-strategy.

Comparison of Using Cold Versus Regular Temperature Tube on Successful Nasogastric Intubation for Patients in Toxicology Emergency Department: a Randomized Clinical Trial.

Introduction: In view of the contradictory results for the use of cold tubes for the purpose of enhancing nasogastric tube insertion success there is a pressing need for further research in this area. This study aimed to determine the effect of using cold versus regular temperature nasogastric tube on successful nasogastric tube insertion for patients referring to toxicology emergency department. Methods: This study is a clinical trial with two groups design of 65 patients admitted to toxicology emergency department who were divided into two groups by random allocation. Nasogastric tubes used in the intervention group had been stored in a refrigerator at 2°-8° C while the ones employed in the control group had been maintained at the room temperature of 22-28° C. Nasogastric tube insertions in both groups were done by the investigator according to standard methods. The data were analyzed using SPSS ver. 13. Results: The placement of nasogastric tube was done in the first attempt with 27 (%84.4) of the subjects in the control group and 33 (%100.0) in the intervention group. The chi-square test results showed that the frequency of the number of attempts for gastric intubation in subjects between the two groups was statistically significant. Conclusion: Cooling gastric tubes reduces the time required for nasogastric intubation. Thus, it is suggested that the gastric tubes be cooled before the application of the procedure so as to reduce complications, increase patient comfort and save nurses time.