CASE REPORT | doi:10.20944/preprints202002.0156.v1
Subject: Medicine And Pharmacology, Epidemiology And Infectious Diseases Keywords: 2019-nCoV; Chest CT; Epidemic; Diagnosis
Online: 12 February 2020 (09:14:56 CET)
An outbreak of novel coronavirus(2019-nCoV) that began in Wuhan, China, is rapidly spreading to all over China, and gradually to multiple countries. Regarding to put the epidemic prevention and spread under the control, early identification and diagnosis play a critical role. Patients with initially no or mild symptoms of Novel Coronavirus Pneumonia (2019-nCoV), namely “stealth” infection, often lack of typical clinical evidence to establish the diagnosis. Based on the clinical analysis of 4 cases in stealth infection, the results of this study highlight that early diagnosis requires a combination of epidemiological history, clinical manifestations, early chest CT examination, and 2019-nCoV RNA test (nucleic acid test), with particular emphasis on definite epidemiological history and early chest CT findings when positive nucleic acid tests lag behind.
ARTICLE | doi:10.20944/preprints202310.1128.v1
Subject: Public Health And Healthcare, Physical Therapy, Sports Therapy And Rehabilitation Keywords: covid-19; diaphragm; chest mobilization; respiratory fucntion
Online: 18 October 2023 (08:14:01 CEST)
This study aims to investigate the effects of chest mobilization and breathing exercises on respiratory function, trunk stability, and endurance in chronic stroke patients who have contracted coronavirus disease (COVID-19). Thirty inpatients of a tertiary hospital in South Korea, who had a history of COVID-19 and were diagnosed with stroke within the last 6 months were randomly assigned to either the Chest Mobilization Exercise with Breathing Exercise (CMEBE) or Conservative Physical Therapy with Breathing Exercise (CPTBE) groups. The respiratory function, trunk stability, and endurance were measured at baseline and 6 weeks after the interventions. Both CMEBE and CPTBE groups showed improvements in respiratory function, trunk stability, and endurance after the intervention (p<0.05). However, the CMEBE group showed significantly greater improvements in forced expiratory volume in 1 second (p<0.05), trunk stability (p<0.05), and endurance (p<0.05) than the CPTBE group. No significant intergroup difference was observed in forced vital capacity and peak expiratory flow. Conclusion: The combination of chest mobilization and breathing exercises improved respiratory muscle mobility and endurance, stabilized the trunk, and enhanced balance and transfer of weight. The findings suggest that this intervention could be beneficial in improving respiratory function and endurance in stroke patients.
ARTICLE | doi:10.20944/preprints202209.0185.v1
Subject: Medicine And Pharmacology, Pediatrics, Perinatology And Child Health Keywords: congenital heart disease; chest radiograph; electrocardiogram; echocardiography
Online: 14 September 2022 (02:55:41 CEST)
This study aimed to evaluate the role of chest radiographs and electrocardiograms in predicting the hemodynamics of congenital heart disease (CHD). This retrospective study included 50 patients with a diagnosis of CHD who had undergone any form of cardiac intervention, either surgical or nonsurgical between September 2019 and September 2020. Chest radiographs and electrocardiograms were evaluated and compared with the diagnostic gold standard echocardiography. Chest radiographs had the highest sensitivity, specificity, and accuracy, with all being 100%, in detecting situs and cardiac position. There was a very good agreement between chest radiographs and echocardiography in the detection of both situs and cardiac position (κ = 1.00, p < 0.001), while moderate agreement was observed for the detection of cardiomegaly, position of aortic knuckle, main pulmonary artery dilation, and right pulmonary artery dilation. Electrocardiograms had a high sensitivity (100.00%), but modest specificity and accuracy for the detection of left ventricle pressure overload. For the detection of left atrial enlargement and left ventricle volume overload, electrocardiograms had high specificity (94.12% and 94.29%, respectively) but low sensitivity and modest accuracy. There was a moderate agreement between electrocardiograms and echocardiography in the detection of right ventricle pressure overload (κ = 0.43, p = 0.002) and left ventricle volume overload (κ = 0.46, p < 0.001). The study findings indicate that chest radiographs and electrocardiograms alone are not adequate for the assessment of hemodynamics of CHD and reinstates the recommendation that in addition to routine chest radiographs and electrocardiograms, echocardiography should be performed.
ARTICLE | doi:10.20944/preprints202208.0189.v1
Subject: Medicine And Pharmacology, Other Keywords: chest-X ray; sddendum; missed finding; radiology
Online: 10 August 2022 (04:17:32 CEST)
Purpose: We assessed if a CXR AI algorithm can detect missed or mislabeled chest radiographs (CXRs) findings in radiology reports. Methods: We queried multi-institutional radiology reports search database of 13-million reports to identify all CXRs reports with addendums from 1999-2021. Of the 3469 CXR reports with an addendum, a thoracic radiologist excluded reports where addendum was created for typographic errors, wrong report template, missing sections, or uninterpreted signoffs. The remaining reports with addendum (279 patients) with errors related to side-discrepancy or missed findings such as pulmonary nodules, consolidation, pleural effusions, pneumothorax, and rib fractures. All CXRs were processed with an AI algorithm. Descriptive statistics were performed to determine the sensitivity, specificity, and accuracy of AI to detect missed or mislabeled findings. Results: AI had high sensitivity (96%), specificity (100%), and accuracy (96%) for detecting all missed and mislabeled CXR findings. The corresponding finding-specific statistics for AI were nodules (96%, 100%, 96%), pneumothorax (84%, 100%, 85%), pleural effusion (100%, 17%, 67%), consolidation (98%, 100%, 98%), and rib fractures (87%, 100%, 94%). Conclusion: The CXR AI could accurately detect mislabeled and missed findings. Clinical Relevance: The CXR AI can reduce the frequency of errors in detection and side-labeling of radiographic findings.
ARTICLE | doi:10.20944/preprints202311.1804.v1
Subject: Public Health And Healthcare, Public Health And Health Services Keywords: tuberculosis; active-case finding; mobile chest X-ray
Online: 28 November 2023 (10:25:24 CET)
Active-case finding (ACF) using chest X-ray is an essential method of finding and diagnosing TB cases that may be missed in Indonesia's routine TB case finding. This study compares active and passive TB case-finding strategies. A retrospective study of TB case notification was conducted. Data between January 1 and December 31, 2021, was used. The population in this study were TB cases notified from Kulon Progo District health facilities, including those found through routine activities or active-case finding. A total of 255 TB cases were diagnosed in Kulon Progo in 2021, and 106 (41.6%) were bacteriologically confirmed. The TB patients' mean age was 46.3 (SD 21.4, range 0-85 years). The majority of cases were male (58.8%) and mostly among people aged 16-60 years old (63.5%). ACF diagnosed 91 TB cases (35.7% total cases, 91/255). The proportion of clinical TB cases (n=68, 74.7%) among those found through ACF was higher than found through passive-case finding. Use of chest X-ray in ACF likely contributed to the detection of a higher proportion of clinical TB than bacteriologically confirmed.
ARTICLE | doi:10.20944/preprints202307.1979.v1
Subject: Medicine And Pharmacology, Internal Medicine Keywords: artificial intelligence; chest radiograph; corticosteroid responsiveness; COVID-19
Online: 28 July 2023 (11:50:44 CEST)
The prediction of corticosteroid responses in coronavirus disease 2019 (COVID-19) patients is crucial in clinical practice, and exploring the role of artificial intelligence (AI)-assisted analysis of chest radiographs (CXR) is warranted. This retrospective case-control study involving hospitalized COVID-19 patients treated with corticosteroids was conducted from September 4th, 2021, to August 30th, 2022. The primary endpoint of the study was corticosteroid responsiveness, defined as the advancement of two or more of the eight-categories-ordinal scale. Serial abnormality scores for consolidation and pleural effusion on CXR were obtained using a commercial AI-based software based on days from onset of symptoms. Amongst the 258 participants included in the analysis, 147 (57%) were male. Multivariable logistic regression analysis revealed that high pleural effusion score at 6–9 days from onset of symptoms (adjusted odds ratio of [aOR]: 1.022, 95% confidence interval [CI]: 1.003-1.042, p=0.020) and consolidation scores up to 9 days from onset of symptoms (0-2 days: aOR: 1.025, 95% CI: 1.006-1.045, p=0.010; 3-5 days: aOR: 1.03 95% CI: 1.011-1.051, p=0.002; 6-9 days: aOR; 1.052, 95% CI: 1.015-1.089, p=0.005) were associated with an unfavorable corticosteroid response. AI-generated scores could help intervene in the use of corticosteroids in COVID-19 patients who would not benefit from them
ARTICLE | doi:10.20944/preprints202304.0906.v1
Subject: Medicine And Pharmacology, Pulmonary And Respiratory Medicine Keywords: sarcoidosis; bronchoalveolar lavage; chest computed tomography; biological markers
Online: 25 April 2023 (09:27:52 CEST)
The search for biological markers, which allow a relatively accurate assessment of the individual course of pulmonary sarcoidosis at the time of diagnosis remains one of the research priorities in this field of pulmonary medicine. The aim of our study was to investigate possible prognostic factors for pulmonary sarcoidosis with a special focus on cellular immune inflammation markers. 2 years follow-up of the study population after initial prospective and simultaneous analysis of lymphocyte activation markers expression in the blood, as well as bronchoalveolar lavage fluid (BALF), and lung biopsy tissue of patients with newly diagnosed pulmonary sarcoidosis, was done. We found that some blood and BAL fluid immunological markers and lung computed tomography (CT) patterns have been associated with a different course of sarcoidosis. We revealed five markers that had a significant negative association with the course of sarcoidosis (worsening pulmonary function tests and/or the chest CT changes) – blood CD4+CD31+ and CD4+CD44+ T lymphocytes, BALF CD8+CD31+ and CD8+CD103+ T lymphocytes and a number of lung nodules on chest CT at the time of the diagnosis. Cut-off values, sensitivity, specificity, and odds ratio for predictors of sarcoidosis progression were calculated. These markers may be reasonable predictors of sarcoidosis progression.
REVIEW | doi:10.20944/preprints201810.0027.v1
Subject: Medicine And Pharmacology, Pediatrics, Perinatology And Child Health Keywords: Infants, Newborn, Neonatal Resuscitation, Chest compressions, Delivery room
Online: 2 October 2018 (14:58:58 CEST)
Annually, an estimated 13-26 million newborns need respiratory support and 2-3 million newborns need extensive resuscitation, defined as chest compression and 100% oxygen with or without epinephrine in the delivery room. Despite such care, there is a high incidence of mortality and short-term neurologic morbidity. The poor prognosis associated with receiving chest compression alone or with medications in the delivery room raises questions as to whether improved cardiopulmonary resuscitation methods specifically tailored to the newborn could improve outcomes. This review discusses the current recommendations, mode of action, different compression to ventilation ratio, continuous chest compression with asynchronous ventilations, chest compression and sustained inflation optimal depth, and oxygen concentration during cardiopulmonary resuscitation.
ARTICLE | doi:10.20944/preprints202110.0352.v1
Subject: Medicine And Pharmacology, Epidemiology And Infectious Diseases Keywords: COVID-19; Diagnostic imaging; Chest; CT-scan; Radiation Dose
Online: 25 October 2021 (12:56:57 CEST)
The COVID-19 pandemic caused an unprecedented effect on national radiological investigations. Since the World Health Organization officially declared the COVID-19 as a global pandemic, health policies have been rapidly organized to limit the spread of the virus and decrease the risk of exposure. These restrictions, in combination with home-stay arrangements and the onset of economic recession. As a result of public policies, financial difficulties and patient fear, many radiology departments have suffered a significant reduction in diagnostic examinations with important implications for their economic stability. The aim of this work is to evaluate the economic impact of the COVID-19 pandemic in the Radiology Department of an infectious disease hospital.
ARTICLE | doi:10.20944/preprints202308.1818.v1
Subject: Medicine And Pharmacology, Cardiac And Cardiovascular Systems Keywords: Chest Pain; Percutaneous Coronary Intervention; Outcomes; Cardiovascular Disease; Emergency Department
Online: 28 August 2023 (09:23:50 CEST)
This study aimed to investigate the characteristics and outcomes of patients who underwent per-cutaneous coronary intervention (PCI) and visited an emergency department (ED) with chest pain in Saudi Arabia. A retrospective analysis of patient data was conducted, focusing on demographics, risk factors, pain assessment, triage, diagnostic testing, and management. The results revealed a young adult population (40-59 years old) at risk for coronary heart disease (CHD), highlighting the need for increased awareness and education. Gender differences in cardiovascular disease (CVD) presentation and underdiagnoses in women also require attention for effective prevention and treatment. Accurate pain assessment during triage was found to be essential to prevent mistriage and negative patient outcomes. Chest pain and shortness of breath were common symptoms, emphasizing the importance of recognizing acute myocardial infarction (AMI) symptoms for proper triage, diagnostic testing, and prompt treatment. The study identified modifiable CVD risk factors, including diabetes (51.1%), hypertension (43.8%), and smoking (25.9%), stressing the importance of lifestyle modifications to reduce CVD risk. Saudi Arabia faces significant challenges in addressing cardiovascular disorders, but efforts to improve healthcare access and establish specialized centers are promising. In conclusion, this study underscores the need for increased awareness of CHD among young adults, accurate pain assessment during triage, and lifestyle modifications to address modifiable CVD risk factors. Furthermore, healthcare teams must stay updated on new chest pain guidelines in the ED and prioritize early detection of implicated arteries and prompt reperfusion. Further research investigating chest pain patient triage and assessments across Saudi Arabia is recommended to identify areas of improvement and implement necessary changes in clinical practice.
ARTICLE | doi:10.20944/preprints202307.2032.v1
Subject: Public Health And Healthcare, Public Health And Health Services Keywords: COVID-19; post-COVID-19; pulmonary manifestations; spirometry; chest tomography.
Online: 28 July 2023 (12:48:47 CEST)
COVID-19 generated a scenario for global health with multiple systemic impairments. This retrospective study evaluated the clinical, radiological, and pulmonary functional evolution in 302 post-COVID-19 patients. Regarding post-COVID-19 pulmonary symptoms, dry cough, dyspnea, and chest pain were the most frequent. Of the associated comorbidities, asthma was more frequent (23.5%). Chest Tomography (CT) initially showed a mean pulmonary involvement of 69.7%, and the evaluation in the subsequent months showed an improvement in the evolutionary image, and with less than six months post-pathology, there was a commitment of 37 .7%, from six to twelve months, 20% and after 12 months, 9.9%. And as for most of the sample, 50.3% of the patients presented CT normalization in less than six months after infection, 23% normalized between six and twelve months, and 5.2% normalized the images after twelve months, with one remaining. Percentage of 17.3% who maintained post-COVID-19 pulmonary residual sequelae. Regarding spirometry, in less than six months after the pathology, 59.3% of the patients already showed a regular exam; 12.3% normalized their function within six to twelve months, and 6.3% concluded a normal exam after twelve months of post-pathology evaluation. Only 3.6% of the patients still showed some alteration in this period.
ARTICLE | doi:10.20944/preprints202306.0755.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Convolutional neural network; Chest CT images; Classification; Adaptive Feature Extraction
Online: 12 June 2023 (04:29:17 CEST)
Deep convolutional neural networks (CNN) are favored methods widely used in medical image processing due to their assured shown performance. Recently, the emergence of new lung diseases and the possibility of early detection of their symptoms has attracted many researchers to classify diseases by training deep CNNs on lung CT images. The trained networks are expected to distinguish between lung indications in diﬀerent diseases, especially at the early stages of them. With the hope of achieving this purpose, we proposed an eﬃcient deep CNN called AFEX-Net with adaptive feature extraction layers that successfully extract distinguishing features and classify chest CT images. The eﬃciency of the proposed network has two aspects: it is a lightweight network with low number of parameters and fast training and it has adaptive pooling layers and adaptive activation functions to increase its level of compatibility to the input data. The proposed network has been evaluated on a dataset with more than 10K chest CT slices, while an eﬃcient pre-processing method is developed to remove any bias from the images. Additionally, we evaluated the performance of the proposed model on the public COVID-CTset dataset to prove the generalisability of our model. The obtained results conﬁrm the competence of the proposed network in confronting medical images, where prompt and accurate learning is required.
ARTICLE | doi:10.20944/preprints202312.0003.v1
Subject: Medicine And Pharmacology, Pediatrics, Perinatology And Child Health Keywords: Respiratory Distress Syndrome; Chest X-ray; Diagnostics; Image Segmentation; Performance Evaluation
Online: 1 December 2023 (04:59:28 CET)
This research addresses the respiratory distress syndrome (RDS) in preterm newborns, caused by insufficient surfactant synthesis, which can lead to serious complications, including pneumothorax, pulmonary hypertension, and pulmonary hemorrhage, increasing the risk of a fatal outcome. By analyzing chest radiographs and blood gases, we specifically focus on the significant contributions of these parameters to the diagnosis and analysis of the recovery of patients with RDS. The study involved 32 preterm newborns, and the analysis of gas parameters before and after the administration of surfactants and inhalation corticosteroid therapy revealed statistically significant changes in values of parameters such as FiO2, pH, pCO2, HCO3 and BE (Sig.<0.05), ehile the pO2 parameter showed a potential change (Sig.=0.061). Parallel to this, the research emphasizes the development of a lung segmentation algorithm implemented in the MATLAB programming environment. The key steps of the algorithm include preprocessing, segmentation, and visualization for a more detailed understanding of the recovery dynamics after RDS. These algorithms have achieved promising results, with a global accuracy of 0.93±0.06, precision 0.81±0.16 and an F-score of 0.82±0.14. These results highlight the potential application of algorithms in the analysis and monitoring of recovery in newborns with RDS, also underscoring the need for further development of software solutions in medicine, particularly in neonatology, to enhance the diagnosis and treatment of preterm newborns with respiratory distress syndrome.
ARTICLE | doi:10.20944/preprints202307.1857.v1
Subject: Medicine And Pharmacology, Pulmonary And Respiratory Medicine Keywords: COVID-19; pneumonia; hospitalized patients; chest physiotherapy; positive expiratory pressure; threshold valve
Online: 27 July 2023 (07:24:20 CEST)
Background: COVID-19 pneumonia caused by SARS-Cov-2 virus induces alveolar collapse and hypoxia that may become severe. The aim of the study is to analyze the effects of chest physiotherapy using a threshold valve in patients with acute respiratory failure due to COVID-19 pneumonia. Methods; Retrospective observational study, in hospitalized patients from March to May 2020. Breathing exercises were performed with a threshold valve of 10 cmH2O. Fraction of inspired oxygen, oxygen saturation, heart rate, respiratory rate and dyspnea were collected before and after the first session and at the end of the 5th day of chest physiotherapy treatment. Results: The final sample included 125 patients. Significant differences (p<0.01) were found in the pre-post intervention SpO2/FiO2 ratio (250±88.4 vs 275.6±97.5, p<0.001), reaching 354.4±110.2 after 5 days of therapy (p<0.001 with respect to baseline). Mean baseline respiratory, heart rate and level of dyspnea measure by the Borg scale did not change during the technique performance. In patient maneuvers with FiO2>0.4, the SaO2/FiO2 ratio increase was higher than in patients with milder severity (46.85 ± 77.69, p<0.01). Conclusions: Chest physiotherapy with a 10 cmH2O threshold valve is a safe and tolerated intervention with short-term improvement in oxygenation in patients with COVID-19 pneumonia.
ARTICLE | doi:10.20944/preprints202102.0481.v1
Subject: Medicine And Pharmacology, Immunology And Allergy Keywords: Anxiety, Depression; Chest Pain; Covid-19; Dyspnea; Emergency Department; Coronavirus; Decision-Making.
Online: 22 February 2021 (15:19:53 CET)
Background We intend to examine whether the COVID-19 outbreak influences medical decision-making (MDM) among Non-COVID patients. Method We recruit 287 patients who admit to ER department due to cardiovascular complaints. Anxiety level was measured using three questionnaires (GAD-7, Beck Inventory, and the cardiac anxiety questionnaire). A fourth survey was designed to assess MDM considerations. Results 64% of patients were male (median age 54). Almost half of the patients were found to have moderate to severe levels of anxiety.79.3% of patients reported that the outbreak influenced their MDM. 44.5% of patients sought medical care 2-3 from the onset of symptoms. Coronary artery disease was found in only 26 patients (9.1%). Almost half of the patients stated that they would have gone earlier if not for the current pandemic. Conclusion Non-COVID patients seeking medical care had a high anxiety level that directly affected decision-making and put them at unnecessary risk.
ARTICLE | doi:10.20944/preprints202107.0636.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Generative Adversarial Networks; Transfer Learning; Medical Imaging; Deep Learning Classification; Chest X-ray’s
Online: 28 July 2021 (17:12:31 CEST)
Data sets for medical images are generally imbalanced and limited in sample size because of high data collection costs, time-consuming annotations, and patient privacy concerns. The training of deep neural network classification models on these data sets to improve the generalization ability does not produce the desired results for classifying the medical condition accurately and often overfit the data on the majority of class samples. To address the issue, we propose a framework for improving the classification performance metrics of deep neural network classification models using transfer learning: pre-trained models, such as Xception, InceptionResNet, DenseNet along with the Generative Adversarial Network (GAN) – based data augmentation. Then, we trained the network by combining traditional data augmentation techniques, such as randomly flipping the image left to right and GAN-based data augmentation, and then fine-tuned the hyper-parameters of the transfer learning models, such as the learning rate, batch size, and the number of epochs. With these configurations, the Xception model outperformed all other pre-trained models achieving a test accuracy of 98.7%, the precision of 99%, recall of 99.3%, f1-score of 99.1%, receiver operating characteristic (ROC) - area under the curve (AUC) of 98.2%.
CASE REPORT | doi:10.20944/preprints202103.0192.v1
Subject: Medicine And Pharmacology, Immunology And Allergy Keywords: COVID-19; shortness of breath; chest pain; radial extracorporeal shock wave therapy; rESWT
Online: 5 March 2021 (17:02:02 CET)
Many patients with Coronavirus disease 2019 (COVID-19) suffer from shortness of breath and severe chest pain. Here we report successful therapy of a patient with diagnosis of COVID-19, severe chest pain and significant shortness of breath, using radial extracorporeal shock wave therapy (rESWT). The latter started seven days after beginning of symptoms and drug therapy without success, and involved daily application of 15.000 to 20.000 radial extracorporeal shock waves over the intercostal muscles as well as the paravertebral muscles of the thoracic and lumbar spine, diaphragm and flanks. Immediately after the first rESWT session the patient experienced significant pain relief and improvement of breathing. Four days later the pain had completely subsided and breathing was largely normalized. This type of noninvasive, non-pharmacologic treatment could help many COVID-19 patients or patients who still suffer from breathing problems weeks after having been infected with SARS-CoV-2, giving them back quality of life.
ARTICLE | doi:10.20944/preprints202306.0261.v1
Subject: Medicine And Pharmacology, Clinical Medicine Keywords: COVID-19; early rehabilitation; computed tomography; physical exercises; chest massage in an electrostatic field.
Online: 5 June 2023 (08:06:38 CEST)
Background: Early rehabilitation is an important strategy for the treatment of severe diseases. The study aimed to assess the efficacy of early rehabilitation of patients with mild-to-moderate COVID-19. Methods: The retrospective single-center study with propensity score matching. Results: 180 patients (54 (44 - 62.3) yo) divided into three equal groups: 1 - physical exercises; 2 - physical exercises and chest massage in an electrostatic field; 3 - no rehabilitation. The length of stay (LOS) in the hospital in group 1 was 14 (11-15) days, group 2 - 13 (11-15) days, group 3 - 15 (13-18) days, p=0.0026. Physical exercises for patients with CT-1 improved the quality of life, assessed by the EQ-5D questionnaire, by reducing the level of anxiety and depression. The Hazard Ratio (HR) for desaturation (<93%) was 2.34 (95% Confidence Interval (CI) 1.18-4.63) for group 2, p=0.001. The HR for C-reactive protein level above 50 mg/l in patients with CT-2 was 2.33 (95% CI 1.56-3.47), p=0.0001. Conclusions: Rehabilitation programs are safe for СOVID-19-patients; reduce hospital LOS; improve the quality of life. Continuous monitoring of a patient's condition during rehabilitation is essential. ClinicalTrials.gov ID: NCT0580836
ARTICLE | doi:10.20944/preprints202211.0515.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Deep Learning; COVID-19; ResNet50; ResNet101; DenseNet121; DenseNet169; InceptionV3; Transfer Learning; Chest X-Rays
Online: 28 November 2022 (12:34:06 CET)
Coronavirus disease since December 2019 has significantly affected millions of people. Given the effect this disease has on the pulmonary systems of humans, there is a need for chest radiographic imaging (CXR) for monitoring the disease and preventing further deaths. Several studies have been shown that Deep Learning models can achieve promising results for COVID-19 diagnosis towards the CXR perspective. However, this research field is at an initial stage since there is a limited number of large CXR repositories regarding COVID-19. In this study, five deep learning models were analyzed and evaluated with the aim of identifying COVID-19 from chest X-Ray images. More specifically, we utilized the ResNet50, ResNet101, DenseNet121, DenseNet169 and InceptionV3 using Transfer Learning. All models were trained and validated on the largest publicly available repository for COVID-19 CXR images. Furthermore, they were evaluated on unknown data as well, that was not used for training or validation, authenticating their performance, and clarifying their usage in a medical scenario. All models achieved satisfactory performance where ResNet101 was the superior model achieving 96% in Precision, Recall, and Accuracy. Our outcomes show the potential of deep learning models on COVID-19 medical offering a promising way for the deeper understanding of COVID-19.
REVIEW | doi:10.20944/preprints202101.0575.v1
Subject: Medicine And Pharmacology, Immunology And Allergy Keywords: wearable respiratory monitors; smart garment; lung volume; respiratory inductance plethysmography; chest expansion; inhalation topography
Online: 27 January 2021 (21:27:53 CET)
Background: Natural environment inhalation topography provides useful information for toxicant exposure, risk assessment and cardiopulmonary performance. Commercially available Wearable Respiratory Monitors (WRM), which are currently used to measure a variety of physiological parameters such as heart rate and breathing frequency, can be leveraged to obtain inhalation topography, yet little work has been done. This paper assesses the feasibility of adapting these WRMs for measuring inhalation topography. Methods: Commercially available WRMs were compiled and assessed for the ability to report chest motion, data analysis software features, ambulatory observation capabilities, participant acceptability, purchasing constraints and affordability. Results: The following WRMs were found: LifeShirt, Equivital EQ02 LifeMonitor, Smartex WWS, Hexoskin Smart Garment, Zephyr BioHarness, Nox T3&A1, BioRadio, SleepSense Inductance Band, and ezRIP & zRIP Durabelt. None of the WRMs satisfied all six assessment criteria in a manner enabling them to be used for inhalation topography without modification and development. Conclusion: The results indicate that there are WRMs with core technologies and characteristics that can be built upon for ambulatory inhalation topography measurement in the NE.
ARTICLE | doi:10.20944/preprints202009.0524.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: COVID-19; chest X-ray images; deep convolutional neural network; COV-MCNet; deep learning
Online: 23 September 2020 (03:31:30 CEST)
The COVID-19 pandemic situation has created even more difficulties in the quick identification and screening of the COVID-19 patients for the medical specialists. Therefore, a significant study is necessary for detecting COVID-19 cases using an automated diagnosis method, which can aid in controlling the spreading of the virus. In this paper, the study suggests a Deep Convolutional Neural Network-based multi-classification approach (COV-MCNet) using eight different pre-trained architectures such as VGG16, VGG19, ResNet50V2, DenseNet201, InceptionV3, MobileNet, InceptionResNetV2, Xception which are trained and tested on the X-ray images of COVID-19, Normal, Viral Pneumonia, and Bacterial Pneumonia. The results from 3-class (Normal vs. COVID-19 vs. Viral Pneumonia) showed that only the ResNet50V2 model provides the highest classification performance (accuracy: 95.83%, precision: 96.12%, recall: 96.11%, F1-score: 96.11%, specificity: 97.84%) compared to rest of the models. The results from 4-class (Normal vs. COVID-19 vs. Viral Pneumonia vs. Bacterial Pneumonia) demonstrated that the pre-trained model DenseNet201 provides the highest classification performance (accuracy: 92.54%, precision: 93.05%, recall: 92.81%, F1-score: 92.83%, specificity: 97.47%). Notably, the ResNet50V2 (3-class) and DenseNet201 (4-class) models in the proposed COV-MCNet framework showed higher accuracy compared to the rest six models. This indicates that the designed system can produce promising results to detect the COVID-19 cases on the availability of more data. The proposed multi-classification network (COV-MCNet) significantly speeds up the existing radiology-based method, which will be helpful to the medical community and clinical specialists for early diagnosis of the COVID-19 cases during this pandemic.
ARTICLE | doi:10.20944/preprints201905.0225.v1
Subject: Medicine And Pharmacology, Pathology And Pathobiology Keywords: GeneXpert; TB Expert Panel; Smear Negatives; Clinically Diagnosed TB; TB DOTS; Chest X-ray
Online: 17 May 2019 (11:18:34 CEST)
Setting A high proportion of notified tuberculosis cases in the Philippines are clinically diagnosed (63%) as opposed to bacteriologically confirmed. Better understanding of this phenomenon is required to improve tuberculosis control. Objectives To determine the percentage of Smear Negative Presumptive Tuberculosis patients that would be diagnosed by GeneXpert; compare clinical characteristics of patients diagnosed as tuberculosis cases; and review the impact that the current single government physician and a reconstituted Tuberculosis Diagnostic committee (Expert Panel) may have on tuberculosis over-diagnosis. Design This is a cross-sectional study of 152 patients 15-85 years old with two negative Direct Sputum Smear Microscopy results, with abnormal chest X-ray who underwent GeneXpert testing and review by an Expert Panel. Results 31% (48/152) of the sample were Xpert positive. 93% (97/104) of GeneXpert negatives were clinically diagnosed by a Single Physician. Typical symptoms and X-ray findings were higher in bacteriologically confirmed tuberculosis. When compared to GeneXpert results, the Expert panel’s sensitivity for active tuberculosis was high (97.5%, 39/40) but specificity was low (40.2%, 35/87). Conclusion Using the GeneXpert would increase the level of bacteriologically confirmed tuberculosis substantially among presumptive Tuberculosis. An Expert panel will greatly reduce over-diagnosis usually seen when a decision is made by a Single Physician.
REVIEW | doi:10.20944/preprints202302.0177.v1
Subject: Medicine And Pharmacology, Pathology And Pathobiology Keywords: Sickle cell disease; cardiopulmonary complications; inflammation; acute chest syndrome; cardiac hypertrophy; cardiac fibrosis; diastolic dysfunction; pulmonary hypertension
Online: 10 February 2023 (03:13:42 CET)
Cardiopulmonary complications remain the major cause of mortality despite newer therapies and improvements in lifespan of patients with sickle cell disease (SCD). Inflammation has been identified as a major risk modifier in the pathogenesis of SCD associated cardiopulmonary complications in recent mechanistic and observational studies. In this review, we discuss recent cellular and molecular mechanisms of cardiopulmonary complications in SCD and summarize the most recent evidence from clinical and laboratory studies. We emphasize the role of inflammation in the onset and progression of these complications to better understand the underlying pathobiological processes. We also discuss future basic and translational research in addressing questions about the complex role of inflammation in the development of SCD cardiopulmonary complications, which may lead to promising therapies and reduce morbidity and mortality in this vulnerable population.
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: automatic detection; chest X-ray; convolutional neural network; COVID-19; deep learning; feature extraction; image classification; pneumonia
Online: 27 April 2021 (14:08:53 CEST)
One of the critical tools for early detection and subsequent evaluation of the incidence of lung diseases is chest radiography. At a time when the speed and reliability of results, especially for COVID-19 positive patients, is important, the development of applications that would facilitate the work of untrained staff involved in the evaluation is also crucial. Our model takes the form of a simple and intuitive application, into which you only need to upload X-rays: tens or hundreds at once. In just a few seconds, the physician will determine the patient's diagnosis, including the percentage accuracy of the estimate. While the original idea was a mere binary classifier that could tell if a patient was suffering from pneumonia or not, in this paper we present a model that distinguishes between a bacterial disease, a viral infection, or a finding caused by COVID-19. The aim of this research is to demonstrate whether pneumonia can be detected or even spatially localized using a uniform, supervised classification.
ARTICLE | doi:10.20944/preprints202007.0656.v1
Subject: Medicine And Pharmacology, Epidemiology And Infectious Diseases Keywords: COVID-19 infection; Chest X-ray image; generalized regression neural network; probabilistic neural network and detection accuracy
Online: 27 July 2020 (00:52:49 CEST)
Corona virus disease (COVID-19) has infected over more than 10 million people around the globe and killed at least 500K worldwide by the end of June 2020. As this disease continues to evolve and scientists and researchers around the world now trying to find out the way to combat this disease in most effective way. Chest X-rays are widely available modality for immediate care in diagnosing COVID-19. Precise detection and diagnosis of COVID-19 from these chest X-rays would be practical for the current situation. This paper proposes one shot cluster based approach for the accurate detection of COVID-19 chest x-rays. The main objective of one shot learning (OSL) is to mimic the way humans learn in order to make classification or prediction on a wide range of similar but novel problems. The core constraint of this type of task is that the algorithm should decide on the class of a test instance after seeing just one test example. For this purpose we have experimented with widely known Generalized Regression and Probabilistic Neural Networks. Experiments conducted with publicly available chest x-ray images demonstrate that the method can detect COVID-19 accurately with high precision. The obtained results have outperformed many of the convolutional neural network based existing methods proposed in the literature.
ARTICLE | doi:10.20944/preprints202304.0971.v1
Subject: Medicine And Pharmacology, Pulmonary And Respiratory Medicine Keywords: 2019-nCoV; COVID-19; RT-PCR; SARS-CoV-2; Community-acquired pneumonia; Chest CT; microwave radiometry; temperature measurement
Online: 26 April 2023 (08:02:32 CEST)
Background. Chest CT is widely regarded as a dependable imaging technique for detecting pneumonia in COVID-19 patients, but there is growing interest in microwave radiometry (MWR) of the lungs as a possible substitute for diagnosing lung involvement. Aim. The aim of the study is to examine the utility of the MWR approach as a screening tool for diagnosing pneumonia with complications in patients with COVID-19. Methods. Our study involved two groups of participants. The control group consisted of 50 individuals (24 male and 26 female) between the ages of 20 to 70 years who underwent clinical evaluations and had no known medical conditions. The main group included 142 participants (67 men and 75 women) between the ages of 20 to 87 years who were diagnosed with COVID-19 complicated by pneumonia and were admitted to the emergency department between June 2020 to June 2021. Skin and lung temperatures were measured at 14 points, including 2 additional reference points, using a previously established method. Lung temperature data were obtained with the MWR2020 (RTM-01-RES) (MMWR LTD, Edinburgh, UK), a CE Class I device. All participants underwent clinical evaluations, laboratory tests, chest CT scans, MWR of the lungs, and reverse transcriptase polymerase chain reaction (RT-PCR) testing for SARS-CoV-2. Results. The MWR exhibits a high predictive capacity as demonstrated by its sensitivity of 98.6% and specificity of 84.0%. Conclusions. MWR of the lungs can be a valuable substitute for chest CT in diagnosing pneumonia in patients with COVID-19, especially in situations where chest CT is unavailable or impractical.
REVIEW | doi:10.20944/preprints202212.0066.v1
Subject: Medicine And Pharmacology, Pathology And Pathobiology Keywords: Sickle Cell Disease; COVID-19; SARS-CoV-2; Vaso-occlusive Crisis; Pain; Thromboxane; Prostaglandin D2; Thrombo-inflammation; Acute Chest Syndrome; Ramatroban
Online: 5 December 2022 (08:00:45 CET)
People with sickle cell disease (SCD) are at greater risk of severe illness and death from respiratory infections, including COVID-19 than people without SCD (Centers for Disease Control and Prevention, USA). Vaso-occlusive crises (VOC) in SCD and severe SARS-CoV-2 infection are both characterized by thrombo-inflammation mediated by endothelial injury, complement activation, inflammatory lipid storm, platelet activation, platelet-leukocyte adhesion, and activation of the coagulation cascade. Notably, lipid mediators, including thromboxane A2, significantly increase in severe COVID-19 and SCD. In addition, the release of thromboxane A2 from endothelial cells and macrophages stimulates platelets to release microvesicles which are harbingers of multicellular adhesion and thrombo-inflammation. Currently, there are limited therapeutic strategies targeting platelet-neutrophil activation and thrombo-inflammation in either SCD or COVID-19 during acute crisis. However, due to many similarities between the pathobiology of thrombo-inflammation in SCD and COVID-19, therapies targeting one disease may likely be effective in the other. Therefore, the preclinical and clinical research spurred by the COVID-19 pandemic, including clinical trials of anti-thrombotic agents, are potentially applicable to VOC. Here, we first outline the parallels between SCD and COVID-19; second, review the role of lipid mediators in the pathogenesis of these diseases and lastly, examine the therapeutic targets and potential treatments for the two diseases.
REVIEW | doi:10.20944/preprints202307.1198.v1
Subject: Medicine And Pharmacology, Cardiac And Cardiovascular Systems Keywords: myocarditis; sudden death; chest pain; autopsy; necropsy; COVID-19; COVID-19 vaccines; mRNA; SARS-CoV-2 vaccination; death; excess mortality; spike protein; organ system
Online: 18 July 2023 (09:34:51 CEST)
Background: COVID-19 vaccines have been linked to myocarditis which in some circumstances can be fatal. This systematic review aims to investigate potential causal links between COVID-19 vaccines and death from myocarditis using post-mortem analysis. Methods: We performed a systematic review of all published autopsy reports involving COVID-19 vaccination-related myocarditis through July 3rd, 2023. All autopsy studies that include COVID-19 vaccine-induced myocarditis as a possible cause of death were included, without imposing any additional restrictions. Causality in each case was determined by three independent reviewers with cardiac pathology experience and expertise. Results: We initially identified 1,691 studies and, after screening for our inclusion criteria, included 14 papers that contained 28 autopsy cases. The cardiovascular system was the only organ system affected in 26 cases. In 2 cases, myocarditis was characterized as a consequence from multisystem inflammatory syndrome (MIS). The mean and median number of days from last COVID-19 vaccination until death was 6.2 and 3 days, respectively. Most of the deaths occurred within a week from the last injection. We established that all 28 deaths were causally linked to COVID-19 vaccination by independent adjudication. Conclusions: The temporal relationship, internal and external consistency seen among cases in this review with known COVID-19 vaccine-induced myocarditis, its pathobiological mechanisms and related excess death, complemented with autopsy confirmation, independent adjudication, and application of the Bradford Hill criteria to the overall epidemiology of vaccine myocarditis, suggests there is a high likelihood of a causal link between COVID-19 vaccines and death from suspected myocarditis in cases where sudden, unexpected death has occurred in a vaccinated person. Urgent investigation is required for the purpose of risk stratification and mitigation in order to reduce the population occurrence of fatal COVID-19 vaccine-induced myocarditis.
REVIEW | doi:10.20944/preprints202308.1866.v1
Subject: Medicine And Pharmacology, Surgery Keywords: breast reconstruction; reconstruction following mastectomy; prophylactic mastectomy; chest feminization; transgender; implant reconstruction of breast; immediate reconstruction; delayed reconstruction; two-stage breast reconstruction; autologous breast reconstruction
Online: 29 August 2023 (03:19:28 CEST)
(1) Importance of problem: Breast cancer accounted for 685.000 deaths globally in 2020, and half of all cases occur in women with no specific risk factor beside gender and age-group. During last 4 decades we see a reduction by 40% of age-standardized breast cancer , which in turn means that the number of mastectomies performed for younger women increased, raising the need for adequate breast reconstructive surgery. Advances in oncological treatment have made it possible to limit the extent of what represents radical surgery for breast cancer, yet in the past decade, we see a marked trend toward mastectomy in breast conserving surgery eligible patients . Prophylactic mastectomy has also registered an upward trend [3,4]. This trend together with new indication for breast reconstruction like chest feminization in transgender patients  have increased the need for breast reconstruction surgery. (2) Purpose: The purpose of this study is to analyze the types of reconstructive procedures, their indications, their limitations, their functional results and the safety profiles when used during the integrated treatment plan of the oncologic patient; (3) Methods: We conducted an extensive literature review of the main reconstructive techniques, especially the autologous procedures, summarized the findings and presented a few cases from our own experience for exemplification of the usage of breast reconstruction in oncologic patients. (4) Conclusions: Breast reconstruction has become a necessary step in the treatment of most breast cancers and many reconstructive techniques are now routinely practiced. Microsurgical techniques are considered the "gold standard", but they are not accessible to all services, from a technical or financial point of view, so pediculated flaps remain the safe and reliable option, along with alloplastic procedures, to improve the quality of life of these patients.
ARTICLE | doi:10.20944/preprints202209.0291.v1
Subject: Biology And Life Sciences, Virology Keywords: COVID-19; Multidimensional Analysis; HCA; Hierarchical cluster analysis; regression analysis; mild; moderate; severe; Age; Score index of the chest X-ray; percentage and quantity of neutrophils; Albumin; C reactive protein; ratio of Lymphocytes
Online: 20 September 2022 (04:50:36 CEST)
INTRODUCTION: The purpose of the study was to determine (a) the overall preclinical character; (b) the cumulative cutoff values and the risk ratio, and (c) the factors associated with severity by a unidimensional and multidimensional analysis on 2173 Sars-Cov2 patients. METHODS: The machine learning study population consisted of 2173 patients (1587 mild and non symptoms patients, 377 moderate patients, 209 severe patients). The status of the patients was recorded from September 2021 to March 2022. RESULTS: The Covid19 Severity directly links with a significant correlation to Age, Score index of the chest X-ray, percentage and quantity of neutrophils, Albumin, C reactive protein, and ratio of Lymphocytes. Their important cut off values (from regression analysis) respectively are: 77.56 years old (the mild-moderate group), 5.53 (the mild-moderate group) and 10.51 (the moderate-severe group), 84.80% (the mild-moderate group) and 87.74%(the moderate-severe group), 11.77G/L (the moderate-severe group), 29.73g/L (the moderate-severe group), 7.46mg/dL (the mild-moderate group), 6.32% (the moderate-severe group). Their significant (p<0.0001) R score correlation with the severity of Covid19, are: 0.44, 0.52 and 0.52, 0.33 and 0.44, 0.42, -0.43, 0.40, -0.41. Their significant risk ratio (p<0.00001) from the meta-analysis, respectively are: 4.19 [3.58-4.95], 3.29 [2.76-3.92] and 3.03 [2.4023;3.8314], 3.18 [2.73-3.70] and 3.32 [2.6480;4.1529], 3.15 [2.6153;3.8025], 3.4[2.91-3.97], 0.46 [0.3650;0.5752] (p<0.00001), 0.34 [0.2743;0.4210]. The pair ALT – Leucocytes and Transferrin – Anion Chloride get the most important correlation shift. ALT – Leucocytes show the important negative link (R=-1, p<0.00001) in the mild group to the significant positive correlation in the moderate group (R=1, p<0.00001). Transferrin–anion Chloride has an important positive association (R=1, p<0.00001) in the mild group with a significant negative correlation in the moderate group (R=-0.59, p<0.00001). The network map and HCA show that in the mild-moderate group, the closest neighbors with the Covid19 severity are ferritins, Age. Then there is C-reactive protein, SI of X-ray, Albumin, and Lactate dehydrogenase, which are the next close neighbors of these three factors. In the moderate-severe group, the closest neighbors with the Covid19 severity are Ferritin, Fibrinogen, Albumin, the quantity of Lymphocytes, SI of X-ray, white blood cells count, Lactate dehydrogenase, and quantity of neutrophils. CONCLUSIONS: Complete multidimensional study in 2173 Covid19 patients in Vietnam shows the whole picture of all the preclinical factors, which may become the clinical reference marker for surveillance and diagnostic management