DKPNet41: Directed knight pattern network-based cough sound classification model for automatic disease diagnosis.

PROBLEM: Cough-based disease detection is a hot research topic for machine learning, and much research has been published on the automatic detection of Covid-19. However, these studies are useful for the diagnosis of different diseases. AIM: In this work, we collected a new and large (n=642 subjects) cough sound dataset comprising four diagnostic categories: 'Covid-19', 'heart failure', 'acute asthma', and 'healthy', and used it to train, validate, and test a novel model designed for automatic detection. METHOD: The model consists of four main components: novel feature generation based on a specifically directed knight pattern (DKP), signal decomposition using four pooling methods, feature selection using iterative neighborhood analysis (INCA), and classification using the k-nearest neighbor (kNN) classifier with ten-fold cross-validation. Multilevel multiple pooling decomposition combined with DKP yielded 41 feature vectors (40 extracted plus one original cough sound). From these, the ten best feature vectors were selected. Based on each vector's misclassification rate, redundant feature vectors were eliminated and then merged. The merged vector's most informative features automatically selected using INCA were input to a standard kNN classifier. RESULTS: The model, called DKPNet41, attained a high accuracy of 99.39% for cough sound-based multiclass classification of the four categories. CONCLUSIONS: The results obtained in the study showed that the DKPNet41 model automatically and efficiently classifies cough sounds for disease diagnosis.

Using artificial intelligence to improve the diagnostic efficiency of pulmonologists in differentiating COVID-19 pneumonia from community-acquired pneumonia.

Coronavirus disease 2019 (COVID-19) has quickly turned into a global health problem. Computed tomography (CT) findings of COVID-19 pneumonia and community-acquired pneumonia (CAP) may be similar. Artificial intelligence (AI) is a popular topic among medical imaging techniques and has caused significant developments in diagnostic techniques. This retrospective study aims to analyze the contribution of AI to the diagnostic performance of pulmonologists in distinguishing COVID-19 pneumonia from CAP using CT scans. A deep learning-based AI model was created to be utilized in the detection of COVID-19, which extracted visual data from volumetric CT scans. The final data set covered a total of 2496 scans (887 patients), which included 1428 (57.2%) from the COVID-19 group and 1068 (42.8%) from the CAP group. CT slices were classified into training, validation, and test datasets in an 8:1:1. The independent test data set was analyzed by comparing the performance of four pulmonologists in differentiating COVID-19 pneumonia both with and without the help of the AI. The accuracy, sensitivity, and specificity values of the proposed AI model for determining COVID-19 in the independent test data set were 93.2%, 85.8%, and 99.3%, respectively, with the area under the receiver operating characteristic curve of 0.984. With the assistance of the AI, the pulmonologists accomplished a higher mean accuracy (88.9% vs. 79.9%, p < 0.001), sensitivity (79.1% vs. 70%, p < 0.001), and specificity (96.5% vs. 87.5%, p < 0.001). AI support significantly increases the diagnostic efficiency of pulmonologists in the diagnosis of COVID-19 via CT. Studies in the future should focus on real-time applications of AI to fight the COVID-19 infection.

COVID-19: vaccination vs. hospitalization.

OBJECTIVE: Vaccination is the most efficient way to control the coronavirus disease 2019 (COVID-19) pandemic, but vaccination rates remain below the target level in most countries. This multicenter study aimed to evaluate the vaccination status of hospitalized patients and compare two different booster vaccine protocols. SETTING: Inoculation in Turkey began in mid-January 2021. Sinovac was the only available vaccine until April 2021, when BioNTech was added. At the beginning of July 2021, the government offered a third booster dose to healthcare workers and people aged > 50 years who had received the two doses of Sinovac. Of the participants who received a booster, most chose BioNTech as the third dose. METHODS: We collected data from 25 hospitals in 16 cities. Patients hospitalized between August 1 and 10, 2021, were included and categorized into eight groups according to their vaccination status. RESULTS: We identified 1401 patients, of which 529 (37.7%) were admitted to intensive care units. Nearly half (47.8%) of the patients were not vaccinated, and those with two doses of Sinovac formed the second largest group (32.9%). Hospitalizations were lower in the group which received 2 doses of Sinovac and a booster dose of BioNTech than in the group which received 3 doses of Sinovac. CONCLUSION: Effective vaccinations decreased COVID-19-related hospitalizations. The efficacy after two doses of Sinovac may decrease over time; however, it may be enhanced by adding a booster dose. Moreover, unvaccinated patients may be persuaded to undergo vaccination.

Can copeptin predict the severity of coronavirus disease 2019 infection?

OBJETIVE: Coronavirus disease 2019 (COVID-19) has quickly turned into a health problem globally. Early and effective predictors of disease severity are needed to improve the management of the patients affected with COVID-19. Copeptin, a 39-amino acid glycopeptide, is known as a C-terminal unit of the precursor pre-provasopressin (pre-proAVP). Activation of AVP system stimulates copeptin secretion in equimolar amounts with AVP. This study aimed to determine serum copeptin levels in the patients with COVID-19 and to examine the relationship between serum copeptin levels and the severity of the disease. METHODS: The study included 90 patients with COVID-19. The patients with COVID-19 were divided into two groups according to disease severity as mild/moderate disease (n=35) and severe disease (n=55). All basic demographic and clinical data of the patients were recorded and blood samples were collected. RESULTS: Copeptin levels were significantly higher in the patients with severe COVID-19 compared with the patients with mild/moderate COVID-19 (p<0.001). Copeptin levels were correlated with ferritin and fibrinogen levels positively (r=0.32, p=0.002 and r=0.25, p=0.019, respectively), and correlated with oxygen saturation negatively (r=-0.37, p<0.001). In the multivariate logistic regression analysis, it was revealed that copeptin (OR: 2.647, 95%CI 1.272-5.510; p=0.009) was an independent predictor of severe COVID-19 disease. A cutoff value of 7.84 ng/mL for copeptin predicted severe COVID-19 with a sensitivity of 78% and a specificity of 80% (AUC: 0.869, 95%CI 0.797-0.940; p<0.001). CONCLUSION: Copeptin could be used as a favorable prognostic biomarker while determining the disease severity in COVID-19.

Automatic COVID-19 Detection Using Exemplar Hybrid Deep Features with X-ray Images.

COVID-19 and pneumonia detection using medical images is a topic of immense interest in medical and healthcare research. Various advanced medical imaging and machine learning techniques have been presented to detect these respiratory disorders accurately. In this work, we have proposed a novel COVID-19 detection system using an exemplar and hybrid fused deep feature generator with X-ray images. The proposed Exemplar COVID-19FclNet9 comprises three basic steps: exemplar deep feature generation, iterative feature selection and classification. The novelty of this work is the feature extraction using three pre-trained convolutional neural networks (CNNs) in the presented feature extraction phase. The common aspects of these pre-trained CNNs are that they have three fully connected layers, and these networks are AlexNet, VGG16 and VGG19. The fully connected layer of these networks is used to generate deep features using an exemplar structure, and a nine-feature generation method is obtained. The loss values of these feature extractors are computed, and the best three extractors are selected. The features of the top three fully connected features are merged. An iterative selector is used to select the most informative features. The chosen features are classified using a support vector machine (SVM) classifier. The proposed COVID-19FclNet9 applied nine deep feature extraction methods by using three deep networks together. The most appropriate deep feature generation model selection and iterative feature selection have been employed to utilise their advantages together. By using these techniques, the image classification ability of the used three deep networks has been improved. The presented model is developed using four X-ray image corpora (DB1, DB2, DB3 and DB4) with two, three and four classes. The proposed Exemplar COVID-19FclNet9 achieved a classification accuracy of 97.60%, 89.96%, 98.84% and 99.64% using the SVM classifier with 10-fold cross-validation for four datasets, respectively. Our developed Exemplar COVID-19FclNet9 model has achieved high classification accuracy for all four databases and may be deployed for clinical application.

The effect of radiological distribution on the COVID-19 disease.

INTRODUCTION: The aim of the study was to investigate the effects of radiological distribution on COVID-19 clinic and prognosis and to determine the relationship between laboratory parameters and thorax CT findings. MATERIALS AND METHODS: Patients with COVID-19 were evaluated retrospectively. Laboratory parameters were obtained from medical records. Ground-glass opacities (GGO) and consolidation were evaluated on thorax CT. The presence of a single lobe lesion was considered as limited while multiple lobe lesions were considered as diffuse involvement for both GGO and consolidation. RESULT: A total 200 patients with COVID-19 were evaluated. 178 of them (89%) were discharged, 17 patients (8.5%) were transferred to the ICU and five patients died (2.5%). The ratios of mortality and transfer to the ICU in patients with diffused GGO were significantly higher compared to patients with limited GGOs. It was observed that troponin ≥0.06 µg/L, platelet <140 and fibrinogen ≥350 mg/dl were independent predictors of the presences of diffused GGOs in thorax CT. CONCLUSIONS: Diffused GGOs on thorax CT are correlated with the rate of mortality and transfer to the ICU in patients with COVID-19. Also, troponin, fibrinogen, and platelet levels can be used while predicting extensive parenchymal disease on thorax CT.

The Glasgow Prognostic Score and fibrinogen to albumin ratio as prognostic factors in hospitalized patients with COVID-19.

Aim: This study aims to determine the prognostic value of the Glasgow Prognostic Score (GPS) and fibrinogen to albumin ratio (FAR) in patients with COVID-19.Methods: Electronic database records of 400 patients with COVID-19 were retrospectively analyzed and the initial levels of CRP, albumin, fibrinogen values were recorded. The ground-glass opacities (GGO) and consolidations were evaluated on thorax CT. Hospital mortality and the need for intensive care unit (ICU) transfer were determined as adverse outcomes.Results: It was determined that 345 patients (86.25%) were discharged while 31 patients (7.75%) were transferred to ICU in addition to 24 patients who died (6%). The rates of deaths and transfers to ICU were significantly increased in GPS 2 group compared to both GPS 0 and 1 groups. Additionally, increased FAR was observed in patients who died and transferred to ICU compared to the discharged patients. The FAR was significantly increased in patients with diffuse GGO. Logistic regression analysis indicated that FAR ≥144.59 and the presence of GPS 2 were independent predictors of the adverse outcomes in COVID-19 patients.Conclusion: Our results demonstrated that the GPS and FAR could possess a predictive value for adverse outcomes in patients with COVID-19.

Efficacy of copeptin in distinguishing COVID-19 pneumonia from community-acquired pneumonia.

The clinical symptoms of community-acquired pneumonia (CAP) and coronavirus disease 2019 (COVID-19)-associated pneumonia are similar. Effective predictive markers are needed to differentiate COVID-19 pneumonia from CAP in the current pandemic conditions. Copeptin, a 39-aminoacid glycopeptide, is a C-terminal part of the precursor pre-provasopressin (pre-proAVP). The activation of the AVP system stimulates copeptin secretion in equimolar amounts with AVP. This study aims to determine serum copeptin levels in patients with CAP and COVID-19 pneumonia and to analyze the power of copeptin in predicting COVID-19 pneumonia. The study consists of 98 patients with COVID-19 and 44 patients with CAP. The basic demographic and clinical data of all patients were recorded, and blood samples were collected. The receiver operating characteristic (ROC) curve was generated and the area under the ROC curve (AUC) was measured to evaluate the discriminative ability. Serum copeptin levels were significantly higher in COVID-19 patients compared to CAP patients (10.2 ± 4.4 ng/ml and 7.1 ± 3.1 ng/ml; p < .001). Serum copeptin levels were positively correlated with leukocyte, neutrophil, and platelet count (r = -.21, p = .012; r = -.21, p = .013; r = -.20, p = .018; respectively). The multivariable logistic regression analysis revealed that increased copeptin (odds ratio [OR] = 1.183, 95% confidence interval [CI], 1.033-1.354; p = .015) and CK-MB (OR = 1.052, 95% CI, 1.013-1.092; p = .008) levels and decreased leukocyte count (OR = 0.829, 95% CI, 0.730-0.940; p = .004) were independent predictors of COVID-19 pneumonia. A cut-off value of 6.83 ng/ml for copeptin predicted COVID-19 with a sensitivity of 78% and a specificity of 73% (AUC: 0.764% 95 Cl: 0.671-0.856, p < .001). Copeptin could be a promising and useful biomarker to be used to distinguish COVID-19 patients from CAP patients.