This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
With the recent outbreak of COVID-19, ultrasound is fast becoming an inevitable diagnostic tool for regular and continuous monitoring of the lung. However, lung ultrasound (LUS) is unique in the perspective that, the artefacts created by acoustic wave propagation is aiding clinicians in diagnosis. In this work, a novel approach is presented to extract acoustic wave propagation driven features such as acoustic shadows, local phase-based feature symmetry, and integrated backscattering to automatically detect the pleura and to aid a pretrained neural network to classify the severity of lung infection based on the region below pleura. A detailed analysis of the proposed approach on LUS images over the infection to full recovery period of ten confirmed COVID-19 subjects across 400 videos shows an average five-fold crossvalidation accuracy, sensitivity, and specificity of 97%, 92%, and 98% respectively over randomly selected 5000 frames. The results and analysis show that, when the input dataset is limited and diverse as in the case of COVID-19 pandemic, an aided effort of combining acoustic propagation-based features along with the gray scale images, as proposed in this work, improves the performance of the neural network significantly even when tested against a completely new data acquisition.
BACKGROUND Chronic obstructive pulmonary disease (COPD) is a chronic respiratory disease characterised by progressive dyspnoea on exertion and cough. COPD is associated with comorbidities that influence mortality and hospitalizations independently. Metabolic syndrome (MS) consists of central obesity, hypertriglyceridemia, low levels of high-density lipoprotein (HDL), hyperglycaemia and hypertension. Presence of metabolic syndrome in patients with COPD increases the frequency of exacerbations and their duration. This study was done to find out prevalence of metabolic syndrome in COPD patients and its influence on exacerbations. METHODS This prospective observational study was conducted in a tertiary care teaching hospital in South India. 174 patients meeting the inclusion criteria were recruited for this prospective observational study, out of which 13 were excluded due to various reasons. Selected patients underwent detailed clinical examination and investigations including chest X-ray, spirometry, fasting blood sugar, fasting lipid profile, electrocardiogram (ECG) etc. Patients were further grouped in to those with metabolic syndrome and those without. They were followed up for one year with review on every two months for assessing exacerbation of COPD. Data was evaluated at the end of the study, statistical evaluation was done using Statistical Package for Social Sciences (SPSS software version18). RESULTS A total of 174 patients were recruited for the study, among which 13 were excluded. 161 patients were included in the final evaluation, out of which 157 patients were male (97.5 %). 44.7 % were belonging to global initiative for obstructive lung disease (GOLD stage III), 37.3 % stage IV and 18 % stage II. 70 (43.5 %) had metabolic syndrome. 51.6 % had normal body mass index (BMI), 23.6 % over weight and 3.7 % were obese. Mean number of exacerbations were 3.20 in those with metabolic syndrome, whereas 1.52 in those without, during the follow up period. CONCLUSIONS Prevalence of metabolic syndrome among COPD patients was 43.5 % in this study. COPD patients with metabolic syndrome had more mean number of exacerbations than those without metabolic syndrome. KEYWORDS COPD, Exacerbations, Metabolic Syndrome, Co-morbidities
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.