RESUMEN
PurposeThe coronavirus disease 2019 (COVID-19) has caused a crisis worldwide. Amounts of efforts have been made to prevent and control COVID-19s transmission, from early screenings to vaccinations and treatments. Recently, due to the spring up of many automatic disease recognition applications based on machine listening techniques, it would be fast and cheap to detect COVID-19 from recordings of cough, a key symptom of COVID-19. To date, knowledge on the acoustic characteristics of COVID-19 cough sounds is limited, but would be essential for structuring effective and robust machine learning models. The present study aims to explore acoustic features for distinguishing COVID-19 positive individuals from COVID-19 negative ones based on their cough sounds. MethodsWith the theory of computational paralinguistics, we analyse the acoustic correlates of COVID-19 cough sounds based on the COMPARE feature set, i. e., a standardised set of 6,373 acoustic higher-level features. Furthermore, we train automatic COVID-19 detection models with machine learning methods and explore the latent features by evaluating the contribution of all features to the COVID-19 status predictions. ResultsThe experimental results demonstrate that a set of acoustic parameters of cough sounds, e. g., statistical functionals of the root mean square energy and Mel-frequency cepstral coefficients, are relevant for the differentiation between COVID-19 positive and COVID-19 negative cough samples. Our automatic COVID-19 detection model performs significantly above chance level, i. e., at an unweighted average recall (UAR) of 0.632, on a data set consisting of 1,411 cough samples (COVID-19 positive/negative: 210/1,201). ConclusionsBased on the acoustic correlates analysis on the COMPARE feature set and the feature analysis in the effective COVID-19 detection model, we find that the machine learning method to a certain extent relies on acoustic features showing higher effects in conventional group difference testing.
RESUMEN
BackgroundAs the novel coronavirus triggering COVID-19 has broken out in Wuhan, China and spread rapidly worldwide, it threatens the lives of thousands of people and poses a global threat on the economies of the entire world. However, infection with COVID-19 is currently rare in children. ObjectiveTo discuss the latest findings and research focus on the basis of characteristics of children confirmed with COVID-19, and provide an insight into the future treatment and research direction. MethodsWe searched the terms "COVID-19 OR coronavirus OR SARS-CoV-2" AND "Pediatric OR children" on PubMed, Embase, Cochrane library, NIH, CDC, and CNKI. The authors also reviewed the guidelines published on Chinese CDC and Chinese NHC. ResultsWe included 25 published literature references related to the epidemiology, clinical manifestation, accessary examination, treatment, and prognosis of pediatric patients with COVID-19. ConclusionThe numbers of children with COVID-19 pneumonia infection are small, and most of them come from family aggregation. Symptoms are mainly mild or even asymptomatic, which allow children to be a risk factor for transmission. Thus, strict epidemiological history screening is needed for early diagnosis and segregation. This holds especially for infants, who are more susceptible to infection than other age groups in pediatric age, but have most likely subtle and unspecific symptoms. They need to be paid more attention to. CT examination is a necessity for screening the suspected cases, because most of the pediatric patients are mild cases, and plain chest X-ray do not usually show the lesions or the detailed features. Therefore, early chest CT examination combined with pathogenic detection is a recommended clinical diagnosis scheme in children. The risk factors which may suggest severe or critical progress for children are: Fast respiratory rate and/or; lethargy and drowsiness mental state and/or; lactate progressively increasing and/or; imaging showed bilateral or multi lobed infiltration, pleural effusion or rapidly expending of lesions in a short period of time and/or; less than 3 months old or those who underly diseases. For those critical pediatric patients with positive SARS-CoV-2 diagnosis, polypnea may be the most common symptom. For treatment, the elevated PCT seen in children in contrast to adults suggests that the underlying coinfection/secondary infection may be more common in pediatric patients and appropriate antibacterial treatment should be considered. Once cytokine storm is found in these patients, anti-autoimmune or blood-purifying therapy should be given in time. Furthermore, effective isolation measures and appropriate psychological comfort need to be provided timely.