Demographics, clinical characteristics, and recurrence rate of patients with primary spontaneous pneumothorax at a tertiary care center in Qatar.

INTRODUCTION: Primary spontaneous pneumothorax (PSP) is a common medical emergency. Its treatment includes simple observation, needle thoracentesis, pleural catheter, video-assisted thoracoscopy (VATS), and open surgery. We aimed to establish the demographic, clinical characteristics, and 12-month recurrence rate of patients with PSP in four hospitals of the Hamad Medical Corporation, Qatar. MATERIALS AND METHODS: We conducted a retrospective analysis of patients >14 years old who were admitted with PSP from January 1, 2017 to December 31, 2019. The patients were followed up for 12 months for the recurrence of PSP. RESULTS: Out of 246 patients enrolled in this study, 223 (90.7%) were males and 23 (9.3%) were females. Their mean age was 29.1 ± 9.59 years and their mean body mass index (BMI) was 21.7 ± 4.22 kg/m2. Of these, 123 (51.2%) patients were smokers. Chest pain was the most common presenting complaint (82.5%). A total of 59 (23.98%) patients had a small pneumothorax, whereas 187 (76.01%) patients had a large pneumothorax. Among the patients with small pneumothorax, 16 (28.33%) were managed through observation alone, 2 (3.33%) required needle aspiration, 15 (25%) required pleural catheter insertion, and 26 (44.06%) underwent surgical intervention for management. Out of 187 patients with large pneumothorax, 16 (8.6%) were managed through observation, 7 (3.76%) required needle aspiration, 73 (38.1%) required pleural catheter insertion, and 91 (48.6%) underwent surgery. During the 12-month follow-up, 58 patients were lost to follow-up and 5 patients (5/188; 2.66%) presented with a recurrence of PSP. Out of 108 patients who underwent VATS, 2 (1.85%) had a recurrence of PSP. CONCLUSION: PSP is more common in males than in females, with a tendency for younger age onset. The recurrence rate of PSP in our study was 2.66%. Furthermore, the recurrence rate in our patients who underwent VATS was 1.85%. Prospective studies are warranted to compare the success rates of different treatment interventions.

Blind ECG Restoration by Operational Cycle-GANs.

OBJECTIVE: ECG recordings often suffer from a set of artifacts with varying types, severities, and durations, and this makes an accurate diagnosis by machines or medical doctors difficult and unreliable. Numerous studies have proposed ECG denoising; however, they naturally fail to restore the actual ECG signal corrupted with such artifacts due to their simple and naive noise model. In this pilot study, we propose a novel approach for blind ECG restoration using cycle-consistent generative adversarial networks (Cycle-GANs) where the quality of the signal can be improved to a clinical level ECG regardless of the type and severity of the artifacts corrupting the signal. METHODS: To further boost the restoration performance, we propose 1D operational Cycle-GANs with the generative neuron model. RESULTS: The proposed approach has been evaluated extensively using one of the largest benchmark ECG datasets from the China Physiological Signal Challenge (CPSC-2020) with more than one million beats. Besides the quantitative and qualitative evaluations, a group of cardiologists performed medical evaluations to validate the quality and usability of the restored ECG, especially for an accurate arrhythmia diagnosis. SIGNIFICANCE: As a pioneer study in ECG restoration, the corrupted ECG signals can be restored to clinical level quality. CONCLUSION: By means of the proposed ECG restoration, the ECG diagnosis accuracy and performance can significantly improve.

COVID-19 infection map generation and detection from chest X-ray images.

Computer-aided diagnosis has become a necessity for accurate and immediate coronavirus disease 2019 (COVID-19) detection to aid treatment and prevent the spread of the virus. Numerous studies have proposed to use Deep Learning techniques for COVID-19 diagnosis. However, they have used very limited chest X-ray (CXR) image repositories for evaluation with a small number, a few hundreds, of COVID-19 samples. Moreover, these methods can neither localize nor grade the severity of COVID-19 infection. For this purpose, recent studies proposed to explore the activation maps of deep networks. However, they remain inaccurate for localizing the actual infestation making them unreliable for clinical use. This study proposes a novel method for the joint localization, severity grading, and detection of COVID-19 from CXR images by generating the so-called infection maps. To accomplish this, we have compiled the largest dataset with 119,316 CXR images including 2951 COVID-19 samples, where the annotation of the ground-truth segmentation masks is performed on CXRs by a novel collaborative human-machine approach. Furthermore, we publicly release the first CXR dataset with the ground-truth segmentation masks of the COVID-19 infected regions. A detailed set of experiments show that state-of-the-art segmentation networks can learn to localize COVID-19 infection with an F1-score of 83.20%, which is significantly superior to the activation maps created by the previous methods. Finally, the proposed approach achieved a COVID-19 detection performance with 94.96% sensitivity and 99.88% specificity.

Advance Warning Methodologies for COVID-19 Using Chest X-Ray Images.

Coronavirus disease 2019 (COVID-19) has rapidly become a global health concern after its first known detection in December 2019. As a result, accurate and reliable advance warning system for the early diagnosis of COVID-19 has now become a priority. The detection of COVID-19 in early stages is not a straightforward task from chest X-ray images according to expert medical doctors because the traces of the infection are visible only when the disease has progressed to a moderate or severe stage. In this study, our first aim is to evaluate the ability of recent state-of-the-art Machine Learning techniques for the early detection of COVID-19 from chest X-ray images. Both compact classifiers and deep learning approaches are considered in this study. Furthermore, we propose a recent compact classifier, Convolutional Support Estimator Network (CSEN) approach for this purpose since it is well-suited for a scarce-data classification task. Finally, this study introduces a new benchmark dataset called Early-QaTa-COV19, which consists of 1065 early-stage COVID-19 pneumonia samples (very limited or no infection signs) labeled by the medical doctors and 12544 samples for control (normal) class. A detailed set of experiments shows that the CSEN achieves the top (over 97%) sensitivity with over 95.5% specificity. Moreover, DenseNet-121 network produces the leading performance among other deep networks with 95% sensitivity and 99.74% specificity.

A series of unfortunate events: Mind the windpipe.

Since we started seeing post-COVID pneumonia patients in our clinics, tracheo-laryngeal stenosis should be kept in mind as an important sequela of prolonged intubation (>7 days) particularly in those who are persistently symptomatic.

Finite Element Analysis of the Mechanism of Traumatic Aortic Rupture (TAR).

As many as 80% of patients with TAR die on the spot while out of those reaching a hospital, 30% would die within 24 hours. Thus, it is essential to better understand and prevent this injury. The exact mechanics of TAR are unknown. Although most researchers approve it as a common-sense deceleration injury, the exact detailed mechanism of TRA still remains unidentified. In this work, a deceleration mechanism of TAR was carried out using finite element analysis (FEA). The FE analysis aimed to predict internal kinematics of the aorta and assist to comprehend the mechanism of aorta injury. The model contains the heart, lungs, thoracic aorta vessel, and rib cage. High-resolution computerized tomography (HR CT scan) was used to provide pictures that were reconstructed by MIMICS software. ANSYS FE simulation was carried out to investigate the behavior of the aorta in the thoracic interior after deceleration occurred during a car crash. The finite element analysis indicated that maximum stress and strain applied to the aorta were from 5.4819e5 to 2.614e6 Pa and 0.21048 to 0.62676, respectively, in the Y-direction when the initial velocity increased from 10 to 25 m/s. Furthermore, in the X-direction when the velocity changed from 15 to 25 m/s, the stress and strain values increased from 5.17771e5 to 2.3128e6 and from 0.22445 to 0.618, respectively.

"High Frequency/Small Tidal Volume Differential Lung Ventilation": A Technique of Ventilating the Nondependent Lung of One Lung Ventilation for Robotically Assisted Thoracic Surgery.

With the introduction of new techniques and advances in the thoracic surgery fields, challenges to the anesthesia techniques had became increasingly exponential. One of the great improvements that took place in the thoracic surgical field was the use of the robotically assisted thoracic surgical procedure and minimally invasive endoscopic thoracic surgery. One lung ventilation technique represents the core anesthetic management for the success of those surgical procedures. Even with the use of effective one lung ventilation, the patient hemodynamics and respiratory parameters could be deranged and could not be tolerating the procedure that could compromise the end result of surgery. We are presenting our experience in managing one patient who suffered persistent hypoxia and hemodynamic instability with one lung ventilation for robotically assisted thymectomy procedure and how it was managed till the completion of the surgery successfully.

An imported case of echinococcosis in a pregnant lady with unusual presentation.

A 31-year-old Syrian pregnant (25-week duration) patient who was managed as a case of bronchial asthma for one year because of chronic cough and progressive breathlessness presented to the Accident and Emergency Department at Hamad General Hospital, Doha, with cough and shortness of breath. On the day of admission, she coughed large amount of yellowish watery material which was salty and sour in taste. She was found by radiological investigations to have multiple giant hydatid cysts (three in the lungs and one in the liver), with ruptured cyst in the left lung. We report here an unusual case of giant multiple pulmonary hydatidosis localized in the lungs and masquerading as bronchial asthma in a pregnant lady. The case represents an uncommon situation of a common disease of rupture of hydatid cyst of the lung in a pregnant lady in her 3rd trimester.

Perioperative myocardial infraction following video-assisted thoracic surgery: A case report and review.

Perioperative myocardial infarction (PMI) during video-assisted thoracoscopy (VAT) surgery is rarely reported in the literature. ST-segment-elevated myocardial infarction (STEMI) is rare in the perioperative period. We report a case of STEMI, following VAT surgery, complicated by acute coronary syndrome. A 53-year male, admitted with recurrent left-sided pneumothorax, an intercostal chest drain was inserted and planned for VAT and lung resection. The intra-operative period was stable, minimal lung resection, and excision of bullae was done. Just before extubation, patient had acute myocardial infarction and cardiogenic shock. An immediate percutaneous coronary intervention (PCI) angiogram showed 90% blockage of the right coronary artery with thrombus. Export thrombectomy and balloon angioplasty was done. Weaned off from inotropes and ventilator. He was transferred to ward from there by day 12, discharged home on double antiplatelet therapy. The PMI can occur earlier than it is commonly thought, and in our patient, it was STEMI, which is rare and occurred during VAT Surgery. In our patient early detection and earlier PCI may have resulted in better outcome.