Prognostic Value of T wave Positivity in Lead aVR in COVID-19 Pneumonia (preprint)

Background: T wave positivity in the lead aVR is a marker of ventricular repolarization abnormality and provides information on short and long-term cardiovascular mortality in patients who have heart failure, anterior myocardial infarction, and receive hemodialysis for various reasons. The aim of this study was to investigate the relationship between T wave positivity in the lead aVR on superficial ECG and mortality from COVID-19 pneumonia. Methods: This study retrospectively included 130 patients who were diagnosed with COVID-19 and treated as an outpatient or in the thoracic diseases ward in a single center between January 2021 and June 2021. All patients included in the study had clinical and radiological features and signs of COVID-19 pneumonia. The COVID-19 diagnosis of all patients was confirmed by polymerase chain reaction (PCR) studied from an oropharyngeal swab Results: A total of 130 patients were included in this study. Patients were divided into 2 groups: survived and deceased. There were 55 patients (with a mean age of 64.76-14.93 years, 58.18% male, 41.12% female) in the survived group, while there were 75 patients (with a mean age of 65-15 years, 58.67% male, 41.33% female) in the deceased group. The univariate and multivariate regression analyses showed that positive TAVR (OR: 5.151, 95% CI: 1.001-26.504, p: 0.0012), lactate dehydrogenase (LDH) (OR: 1.006, 95% CI: 1.001-1.010, p: 0.012) and D-dimer (OR:1.436, 95% CI: 1.115-1.848, p: 0.005) were independent risk factors for mortality Conclusions: positive TAaVR is useful in risk stratification for COVID-19 pneumonia mortality. KEY WORLD:Electrocardıographıa, positive TAaVR, COVID-19 pneumonia, mortality

Improving Fairness of Automated Chest X-ray Diagnosis by Contrastive Learning (preprint)

Purpose: Limited studies exploring concrete methods or approaches to tackle and enhance model fairness in the radiology domain. Our proposed AI model utilizes supervised contrastive learning to minimize bias in CXR diagnosis. Materials and Methods: In this retrospective study, we evaluated our proposed method on two datasets: the Medical Imaging and Data Resource Center (MIDRC) dataset with 77,887 CXR images from 27,796 patients collected as of April 20, 2023 for COVID-19 diagnosis, and the NIH Chest X-ray (NIH-CXR) dataset with 112,120 CXR images from 30,805 patients collected between 1992 and 2015. In the NIH-CXR dataset, thoracic abnormalities include atelectasis, cardiomegaly, effusion, infiltration, mass, nodule, pneumonia, pneumothorax, consolidation, edema, emphysema, fibrosis, pleural thickening, or hernia. Our proposed method utilizes supervised contrastive learning with carefully selected positive and negative samples to generate fair image embeddings, which are fine-tuned for subsequent tasks to reduce bias in chest X-ray (CXR) diagnosis. We evaluated the methods using the marginal AUC difference ($\delta$ mAUC). Results: The proposed model showed a significant decrease in bias across all subgroups when compared to the baseline models, as evidenced by a paired T-test (p<0.0001). The $\delta$ mAUC obtained by our method were 0.0116 (95\% CI, 0.0110-0.0123), 0.2102 (95% CI, 0.2087-0.2118), and 0.1000 (95\% CI, 0.0988-0.1011) for sex, race, and age on MIDRC, and 0.0090 (95\% CI, 0.0082-0.0097) for sex and 0.0512 (95% CI, 0.0512-0.0532) for age on NIH-CXR, respectively. Conclusion: Employing supervised contrastive learning can mitigate bias in CXR diagnosis, addressing concerns of fairness and reliability in deep learning-based diagnostic methods.

Exploring the Impact of the COVID-19 Pandemic on Cancer-Related Distress Among Thoracic Oncology Patients at a Rural Cancer Center (preprint)

Purpose: Cancer-related distress (CRD) is frequently observed in rural settings and may have been exacerbated during the COVID-19 pandemic. We examined pre and post COVID-19 changes in CRD among individuals treated for thoracic cancers at a rural cancer center. Methods: Patient demographics, clinical information, and CRD measures derived from the National Comprehensive Cancer Network psychosocial distress problem list were abstracted from electronic medical records for thoracic oncology patients treated at a rural Michigan cancer center before (January 1, 2019-January 1, 2020; n=139) and during (January 20, 2020-January 31, 2021; n=84) the COVID-19 pandemic. CRD scores overall and by type (practical, emotional, social, and physical concerns) were calculated by summing the relevant problem list items. We assessed changes in CRD overall and by type using chi-square tests, Fisher’s exact tests, and multivariable logistic regression models. Results: CRD prevalence increased by 9.1% during vs. before the pandemic (97.6% vs. 88.5%; p=0.02), with largest increases evident for emotional (82.1% vs. 64.0%; p=0.004) and physical (82.1% vs. 67.6%; p=0.02) concerns. CRD scores were slightly higher during vs. before the pandemic but the differences were not significant (all p-values>0.05). Compared to those treated in the year prior, patients treated during the pandemic had higher odds of elevated CRD (OR (95% CI) =1.86 (1.1, 3.2)), and practical concerns (OR (95% CI) =2.19 (1.3, 3.8)). Conclusions: Findings from this preliminary study suggest an increased prevalence of CRD among rural thoracic oncology patients treated during compared to before the COVID-19 pandemic.

DualAttNet: Synergistic Fusion of Image-level and Fine-Grained Disease Attention for Multi-Label Lesion Detection in Chest X-rays (preprint)

Chest radiographs are the most commonly performed radiological examinations for lesion detection. Recent advances in deep learning have led to encouraging results in various thoracic disease detection tasks. Particularly, the architecture with feature pyramid network performs the ability to recognise targets with different sizes. However, such networks are difficult to focus on lesion regions in chest X-rays due to their high resemblance in vision. In this paper, we propose a dual attention supervised module for multi-label lesion detection in chest radiographs, named DualAttNet. It efficiently fuses global and local lesion classification information based on an image-level attention block and a fine-grained disease attention algorithm. A binary cross entropy loss function is used to calculate the difference between the attention map and ground truth at image level. The generated gradient flow is leveraged to refine pyramid representations and highlight lesion-related features. We evaluate the proposed model on VinDr-CXR, ChestX-ray8 and COVID-19 datasets. The experimental results show that DualAttNet surpasses baselines by 0.6% to 2.7% mAP and 1.4% to 4.7% AP50 with different detection architectures. The code for our work and more technical details can be found at https://github.com/xq141839/DualAttNet.

Enhancing thoracic disease detection using chest X-rays from PubMed Central Open Access.

Large chest X-rays (CXR) datasets have been collected to train deep learning models to detect thorax pathology on CXR. However, most CXR datasets are from single-center studies and the collected pathologies are often imbalanced. The aim of this study was to automatically construct a public, weakly-labeled CXR database from articles in PubMed Central Open Access (PMC-OA) and to assess model performance on CXR pathology classification by using this database as additional training data. Our framework includes text extraction, CXR pathology verification, subfigure separation, and image modality classification. We have extensively validated the utility of the automatically generated image database on thoracic disease detection tasks, including Hernia, Lung Lesion, Pneumonia, and pneumothorax. We pick these diseases due to their historically poor performance in existing datasets: the NIH-CXR dataset (112,120 CXR) and the MIMIC-CXR dataset (243,324 CXR). We find that classifiers fine-tuned with additional PMC-CXR extracted by the proposed framework consistently and significantly achieved better performance than those without (e.g., Hernia: 0.9335 vs 0.9154; Lung Lesion: 0.7394 vs. 0.7207; Pneumonia: 0.7074 vs. 0.6709; Pneumothorax 0.8185 vs. 0.7517, all in AUC with p< 0.0001) for CXR pathology detection. In contrast to previous approaches that manually submit the medical images to the repository, our framework can automatically collect figures and their accompanied figure legends. Compared to previous studies, the proposed framework improved subfigure segmentation and incorporates our advanced self-developed NLP technique for CXR pathology verification. We hope it complements existing resources and improves our ability to make biomedical image data findable, accessible, interoperable, and reusable.

Diaphragm Muscle Weakness Might Explain Exertional Dyspnea 15 Months after Hospitalization for COVID-19.

Rationale: Dyspnea is often a persistent symptom after acute coronavirus disease (COVID-19), even if cardiac and pulmonary function are normal. Objectives: This study investigated diaphragm muscle strength in patients after COVID-19 and its relationship to unexplained dyspnea on exertion. Methods: Fifty patients previously hospitalized with COVID-19 (14 female, age 58 ± 12 yr, half of whom were treated with mechanical ventilation, and half of whom were treated outside the ICU) were evaluated using pulmonary function testing, 6-minute-walk test, echocardiography, twitch transdiaphragmatic pressure after cervical magnetic stimulation of the phrenic nerve roots, and diaphragm ultrasound. Diaphragm function data were compared with values from a healthy control group. Measurements and Main Results: Moderate or severe dyspnea on exertion was present at 15 months after hospital discharge in approximately two-thirds of patients. No significant pulmonary function or echocardiography abnormalities were detected. Twitch transdiaphragmatic pressure was significantly impaired in patients previously hospitalized with COVID-19 compared with control subjects, independent of initial disease severity (14 ± 8 vs. 21 ± 3 cm H2O in mechanically ventilated patients vs. control subjects [P = 0.02], and 15 ± 8 vs. 21 ± 3 cm H2O in nonventilated patients vs. control subjects [P = 0.04]). There was a significant association between twitch transdiaphragmatic pressure and the severity of dyspnea on exertion (P = 0.03). Conclusions: Diaphragm muscle weakness was present 15 months after hospitalization for COVID-19 even in patients who did not require mechanical ventilation, and this weakness was associated with dyspnea on exertion. The current study, therefore, identifies diaphragm muscle weakness as a correlate for persistent dyspnea in patients after COVID-19 in whom lung and cardiac function are normal. Clinical trial registered with www.clinicaltrials.gov (NCT04854863).

Acute Myocardial Infarction, Subclavian Vein Thrombosis, and Pulmonary Embolism Secondary to COVID-19-A Case Report.

Introduction: Coronavirus disease 2019 (COVID-19) is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The majority of infected patients develop the clinical picture of a respiratory disease, although some may develop various complications, such as arterial or venous thrombosis. The clinical case presented herein is a rare example of sequential development and combination of acute myocardial infarction, subclavian vein thrombosis (Paget Schroetter syndrome), and pulmonary embolism in the same patient after COVID-19. Case presentation: A 57-year-old man with a 10-day history of a SARS-CoV-2 infection was hospitalized with a clinical, electrocardiographic, and laboratory constellation of an acute inferior-lateral myocardial infarction. He was treated invasively and had one stent implanted. Three days after implantation, the patient developed shortness of breath and palpitation on the background of a swollen and painful right hand. The signs of acute right-sided heart strain observed on the electrocardiogram and the elevated D-dimer levels strongly suggested pulmonary embolism. A Doppler ultrasound and invasive evaluation demonstrated thrombosis of the right subclavian vein. The patient was administered pharmacomechanical and systemic thrombolysis and heparin infusion. Revascularization was achieved 24 h later via successful balloon dilatation of the occluded vessel. Conclusion: Thrombotic complications of COVID-19 can develop in a significant proportion of patients. Concomitant manifestation of these complications in the same patient is extremely rare, presenting at the same time, quite a therapeutic challenge to clinicians due to the need for invasive techniques and simultaneous administration of dual antiaggregant therapy combined with an anticoagulant treatment. Such a combined treatment increases the hemorrhagic risk and requires a serious accumulation of data for the purpose of a long-term antithrombotic prophylaxis in patients with such pathology.

Isolated long thoracic nerve palsy following COVID-19 vaccine: a case report. (preprint)

Introduction: We report an adult man who developed an isolated long thoracic nerve palsy three days following vaccination against COVID-19. To the best of our knowledge this is the first well-documented case of this association. Case presentation: A 46-year-old white man developed back pain, followed by pain in the right axilla and scapular region, clumsiness of the right arm and unusual position of his shoulder blade, three days after receiving a second dose of the Pfizer-BioNTech COVID-19 vaccine. When he consulted a neurologist six months later, the pain had subsided, but the other symptoms persisted despite physiotherapy. Main clinical findings were right scapular winging and marked amyotrophy of the serratus anterior, with preservation of the other muscles of the shoulder and scapula. Nerve conduction studies yielded a low amplitude with a slightly prolonged latency of the right long thoracic nerve. Needle electromyography showed decreased compound motor action potentials on the right and was normal on the left. Main diagnosis and interventions: A diagnosis of post-immunisation long thoracic neuritis was made. The patient was treated with physiotherapy. Conclusions: Clinicians should be aware of the possibility of neuritis of any nerve after COVID-19 vaccination.

Microbial Pattern and Antibiotic Resistance of Severe Pneumonia in A National Referral Hospital in Indonesia (preprint)

Background: Patients hospitalized in the intensive care unit (ICU) have a higher susceptibility to infections. Respiratory infections are the most common nosocomial infections. Rising antibiotic resistance due to indiscriminate use of antibiotics and poor adherence to standard precaution in healthcare facilities compounds the problem. The main aim of this study is to assess microbial patterns and antibiotic resistance from bronchoalveolar lavage specimens in severe pneumonia patients. Methods: This retrospective study was conducted in an Indonesian tertiary care hospital from January 2016-December 2020. Written and verbal informed consent was obtained prior to bronchoscopy procedures. Patients were enrolled if they had severe community-acquired pneumonia (CAP) according to American Thoracic Society (ATS)/Infectious Disease Society of America (IDSA) criteria, had high-risk hospital-acquired pneumonia (HAP), late-onset ventilator-associated pneumonia (VAP), or pneumonia caused by Coronavirus disease (COVID-19). Respiratory specimens via bronchoscopy were inoculated on general semi-sloid thioglycolate media. Testing for antibiotic susceptibility was done using the disk diffusion method. Results: Two hundred and one patients’ data were analyzed. The majority of patients were males (65,17%) and above 60 years of age. The most common type of pneumonia was CAP (39,3%). Neurologic/cerebrovascular disease was the most common comorbidity (35,32%). Acinetobacter baumannii was the most frequently isolated microorganism. Ampicillin/sulbactam and amikacin were found to yield lower microbial resistance. Conclusion: Combination of ampicillin/sulbactam and amikacin appeared effective as initial empirical therapy in severe pneumonia patients. Further studies are needed to evaluate the feasibility and effectiveness of this combined therapy.

An explainable model of host genetic interactions linked to COVID-19 severity (preprint)

We employed a multifaceted computational strategy to identify the genetic factors contributing to increased risk of severe COVID-19 infection from a Whole Exome Sequencing (WES) dataset of a cohort of 2000 Italian patients. We coupled a stratified k -fold screening, to rank variants more associated with severity, with training of multiple supervised classifiers, to predict severity on the basis of screened features. Feature importance analysis from tree-based models allowed to identify a handful of 16 variants with highest support which, together with age and gender covariates, were found to be most predictive of COVID-19 severity. When tested on a follow-up cohort, our ensemble of models predicted severity with good accuracy (ACC=81.88%; ROC_AUC=96%; MCC=61.55%). Principal Component Analysis (PCA) and clustering of patients on important variants orthogonally identified two groups of individuals with a higher fraction of severe cases. Our model recapitulated a vast literature of emerging molecular mechanisms and genetic factors linked to COVID-19 response and extends previous landmark Genome Wide Association Studies (GWAS). It revealed a network of interplaying genetic signatures converging on established immune system and inflammatory processes linked to viral infection response, such as JAK-STAT, Cytokine, Interleukin, and C-type lectin receptor signaling. It also identified additional processes cross-talking with immune pathways, such as GPCR signalling, which might offer additional opportunities for therapeutic intervention and patient stratification. Publicly available PheWAS datasets revealed that several variants were significantly associated with phenotypic traits such as “Respiratory or thoracic disease”, confirming their link with COVID-19 severity outcome. Taken together, our analysis suggests that curated genetic information can be effectively integrated along with other patient clinical covariates to forecast COVID-19 disease severity and dissect the underlying host genetic mechanisms for personalized medicine treatments.

Fast and Accurate Detection of COVID-19 Along With 14 Other Chest Pathologies Using a Multi-Level Classification: Algorithm Development and Validation Study.

BACKGROUND: COVID-19 has spread very rapidly, and it is important to build a system that can detect it in order to help an overwhelmed health care system. Many research studies on chest diseases rely on the strengths of deep learning techniques. Although some of these studies used state-of-the-art techniques and were able to deliver promising results, these techniques are not very useful if they can detect only one type of disease without detecting the others. OBJECTIVE: The main objective of this study was to achieve a fast and more accurate diagnosis of COVID-19. This study proposes a diagnostic technique that classifies COVID-19 x-ray images from normal x-ray images and those specific to 14 other chest diseases. METHODS: In this paper, we propose a novel, multilevel pipeline, based on deep learning models, to detect COVID-19 along with other chest diseases based on x-ray images. This pipeline reduces the burden of a single network to classify a large number of classes. The deep learning models used in this study were pretrained on the ImageNet dataset, and transfer learning was used for fast training. The lungs and heart were segmented from the whole x-ray images and passed onto the first classifier that checks whether the x-ray is normal, COVID-19 affected, or characteristic of another chest disease. If it is neither a COVID-19 x-ray image nor a normal one, then the second classifier comes into action and classifies the image as one of the other 14 diseases. RESULTS: We show how our model uses state-of-the-art deep neural networks to achieve classification accuracy for COVID-19 along with 14 other chest diseases and normal cases based on x-ray images, which is competitive with currently used state-of-the-art models. Due to the lack of data in some classes such as COVID-19, we applied 10-fold cross-validation through the ResNet50 model. Our classification technique thus achieved an average training accuracy of 96.04% and test accuracy of 92.52% for the first level of classification (ie, 3 classes). For the second level of classification (ie, 14 classes), our technique achieved a maximum training accuracy of 88.52% and test accuracy of 66.634% by using ResNet50. We also found that when all the 16 classes were classified at once, the overall accuracy for COVID-19 detection decreased, which in the case of ResNet50 was 88.92% for training data and 71.905% for test data. CONCLUSIONS: Our proposed pipeline can detect COVID-19 with a higher accuracy along with detecting 14 other chest diseases based on x-ray images. This is achieved by dividing the classification task into multiple steps rather than classifying them collectively.

Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models (preprint)

Convolutional neural networks are showing promise in the automatic diagnosis of thoracic pathologies on chest x-rays. Their black-box nature has sparked many recent works to explain the prediction via input feature attribution methods (aka saliency methods). However, input feature attribution methods merely identify the importance of input regions for the prediction and lack semantic interpretation of model behavior. In this work, we first identify the semantics associated with internal units (feature maps) of the network. We proceed to investigate the following questions; Does a regression model that is only trained with COVID-19 severity scores implicitly learn visual patterns associated with thoracic pathologies? Does a network that is trained on weakly labeled data (e.g. healthy, unhealthy) implicitly learn pathologies? Moreover, we investigate the effect of pretraining and data imbalance on the interpretability of learned features. In addition to the analysis, we propose semantic attribution to semantically explain each prediction. We present our findings using publicly available chest pathologies (CheXpert, NIH ChestX-ray8) and COVID-19 datasets (BrixIA, and COVID-19 chest X-ray segmentation dataset). The Code is publicly available.

Reliable COVID-19 Detection Using Chest X-ray Images (preprint)

Coronavirus disease 2019 (COVID-19) has emerged the need for computer-aided diagnosis with automatic, accurate, and fast algorithms. Recent studies have applied Machine Learning algorithms for COVID-19 diagnosis over chest X-ray (CXR) images. However, the data scarcity in these studies prevents a reliable evaluation with the potential of overfitting and limits the performance of deep networks. Moreover, these networks can discriminate COVID-19 pneumonia usually from healthy subjects only or occasionally, from limited pneumonia types. Thus, there is a need for a robust and accurate COVID-19 detector evaluated over a large CXR dataset. To address this need, in this study, we propose a reliable COVID-19 detection network: ReCovNet, which can discriminate COVID-19 pneumonia from 14 different thoracic diseases and healthy subjects. To accomplish this, we have compiled the largest COVID-19 CXR dataset: QaTa-COV19 with 124,616 images including 4603 COVID-19 samples. The proposed ReCovNet achieved a detection performance with 98.57% sensitivity and 99.77% specificity.

Clinical and molecular practice of European thoracic pathology laboratories during the COVID-19 pandemic. The past and the near future.

BACKGROUND: This study evaluated the consequences in Europe of the COVID-19 outbreak on pathology laboratories orientated toward the diagnosis of thoracic diseases. MATERIALS AND METHODS: A survey was sent to 71 pathology laboratories from 21 European countries. The questionnaire requested information concerning the organization of biosafety, the clinical and molecular pathology, the biobanking, the workload, the associated research into COVID-19, and the organization of education and training during the COVID-19 crisis, from 15 March to 31 May 2020, compared with the same period in 2019. RESULTS: Questionnaires were returned from 53/71 (75%) laboratories from 18 European countries. The biosafety procedures were heterogeneous. The workload in clinical and molecular pathology decreased dramatically by 31% (range, 3%-55%) and 26% (range, 7%-62%), respectively. According to the professional category, between 28% and 41% of the staff members were not present in the laboratories but did teleworking. A total of 70% of the laboratories developed virtual meetings for the training of residents and junior pathologists. During the period of study, none of the staff members with confirmed COVID-19 became infected as a result of handling samples. CONCLUSIONS: The COVID-19 pandemic has had a strong impact on most of the European pathology laboratories included in this study. Urgent implementation of several changes to the organization of most of these laboratories, notably to better harmonize biosafety procedures, was noted at the onset of the pandemic and maintained in the event of a new wave of infection occurring in Europe.

Non-COVID Diseases during the Pandemic: Where Have All Other Emergencies Gone?

Background and objectives: the emergency department (ED) is frequently identified by patients as a possible solution for all healthcare problems, leading to a high rate of misuse of the ED, possibly causing overcrowding. The coronavirus disease 2019 (COVID-19) pandemic started in China; it then spread throughout Italy, with the first cases confirmed in Lombardy, Italy, in February 2020. This has totally changed the type of patients referred to EDs. The aim of this study was to analyze the reduction of ED admissions at a Second level urban teaching (Fondazione Policlinico Universitario Agostino Gemelli IRCCS) during the COVID-19 pandemic. Materials and Methods: in this retrospective observational cross-sectional study, we reviewed and compared clinical records of all the patients consecutively admitted to our ED over a 40-day period (21 February -31 March) in the last three years (2018-2019-2020). Mean age, sex, triage urgency level, day/night admission, main presentation symptom, and final diagnosis, according to different medical specialties, hospitalization, and discharge rate, were analyzed. Results: we analyzed 16,281 patient clinical records. The overall reduction in ED admissions in 2020 was 37.6% compared to 2019. In 2020, we observed an increase in triage urgency levels for ED admissions (the main presentation symptom was a fever). We noticed a significant drop in admissions for cardio-thoracic, gastroenterological, urological, otolaryngologic/ophthalmologic, and traumatological diseases. Acute neurological conditions registered only a slight, but significant, reduction. Oncology admissions were stable. Admissions for infectious diseases were 30% in 2020, compared to 5% and 6% in 2018 and 2019, respectively. In 2020, the hospitalization rate increased to 42.9% compared to 27.7%, and 26.4% in previous years. Conclusions: the drastic reduction of ED admissions during the pandemic may be associated with fear of the virus, suggesting that patients with serious illnesses did not go to the emergency room. Moreover, there was possible misuse of the ED in the previous year. In particular, worrisome data emerged regarding a drop in cardiology and neurology admissions. Those patients postponed medical attention, possibly with fatal consequences, just for fear of exposure to COVID-19, leading to unnecessary morbidity and mortality.

A Deep Neural Network to Distinguish COVID-19 from other Chest Diseases Using X-ray Images.

BACKGROUND: Scanning a patient's lungs to detect Coronavirus 2019 (COVID-19) may lead to similar imaging of other chest diseases. Thus, a multidisciplinary approach is strongly required to confirm the diagnosis. There are only a few works targeted at pathological x-ray images. Most of the works only target single disease detection which is not good enough. Some works have been provided for all classes. However, the results suffer due to lack of data for rare classes and data unbalancing problem. METHODS: Due to the rise in COVID-19 cases, medical facilities in many countries are overwhelmed and there is a need for an intelligent system to detect it. Few works have been done regarding the detection of the coronavirus but there are many cases where it can be misclassified as some techniques are not efficient and can only identify specific diseases. This work is a deep learning- based model to distinguish COVID-19 cases from other chest diseases. RESULTS: A Deep Neural Network model provides a significant contribution in terms of detecting COVID-19 and provides an effective analysis of chest-related diseases taking into account both age and gender. Our model achieves 87% accuracy in terms of GAN-based synthetic data and presents four different types of deep learning-based models that provide comparable results to other state-of-the-art techniques. CONCLUSION: The healthcare industry may face unfavorable consequences if the gap in the identification of all types of pneumonia is not filled with effective automation.

General thoracic surgery services across Asia during the 2020 COVID-19 pandemic.

The COVID-19 pandemic of 2020 posed an historic challenge to healthcare systems around the world. Besides mounting a massive response to the viral outbreak, healthcare systems needed to consider provision of clinical services to other patients in need. Surgical services for patients with thoracic disease were maintained to different degrees across various regions of Asia, ranging from significant reductions to near-normal service. Key determinants of robust thoracic surgery service provision included: preexisting plans for an epidemic response, aggressive early action to "flatten the curve", ability to dedicate resources separately to COVID-19 and routine clinical services, prioritization of thoracic surgery, and the volume of COVID-19 cases in that region. The lessons learned can apply to other regions during this pandemic, and to the world, in preparation for the next one.