The authors concluded that CA appears ready for implementation of (pre-) diagnosis and monitoring tools. The automatic recognition and monitoring of breathing, dry and wet coughing or sneezing sounds, speech under cold, eating behavior, sleepiness, or pain is used. The overview concern to the potential for computer audition (CA), i.e., the usage of speech and sound analysis by artificial intelligence to help in COVID-19 diagnostics. In the case of real data, the results show the feasibility of using the developed mobile health system in clinical no controlled environment to help the expert in evaluating the pulmonary state of a subject. The detection of coarse crackles was found to be a more challenging task in the simulated scenarios. In simulated scenarios, for fine crackles, an accuracy ranging from 84.86% to 89.16%, a sensitivity ranging from 93.45% to 97.65%, and a specificity ranging from 99.82% to 99.84% were found. The performance of the automated detector was analyzed using: (1) synthetic fine and coarse crackle sounds randomly inserted to the basal respiratory sounds acquired from healthy subjects with different signal to noise ratios, and (2) real bedside acquired respiratory sounds from patients with interstitial diffuse pneumonia. Reyes and co-authors used a smartphone-based system for automated bedside detection of crackle sounds in diffuse interstitial pneumonia patients. Nemecio Olvera-Montes and co-authors used the detection of respiratory crackle sounds via an android smartphone-based system for diagnostics of pneumonia and monitoring of the patient state.īersain A. The automated adventitious sound detection or/and their classification is a promising solution to overcome the limitations of conventional auscultation and to assist in the monitoring of relevant diseases, such as asthma, Chronic Obstructive Pulmonary Disease (COPD), and pneumonia. The objectivity of auscultatory diagnostics can be significantly enhanced by using digitized audio signals and computer processing of these signals. One of these methods can be based on computer-assistance analysis of respiratory sounds of a patient and on comparison of the sound characteristics of a patient and a healthy volunteer. Due to very high contagiousness of COVID-19, development of screening diagnostic methods, including contactless and remote, is very relevant. Detection of the characteristic respiratory sounds (cough, wheezes, asthma wheezing, shortness of breath, etc.) is a widely used way of diagnostic of pulmonary diseases.Īt present diagnosis of COVID-19 is based on clinical symptoms, and Chest X-ray / computer tomography, coronavirus tests (PCR (polymerase chain reaction) – molecular test, antigen test and specific antibodies to SARS CoV19). The defeat of various airways, caused by coronavirus, alters the sound formation of a patient and changes characteristics of respiratory sounds. Coronavirus SARS-CoV-2 can penetrate into smallest airways, where it infects cells and causes bilateral pneumonia, and often with respiratory failure. Anatomically a dry cough can be associated with the effect of the virus on the cough receptors of the larynx due to infection with COVID-19. It is known that the highest density of cough receptors is in the larynx. Intense cough is one of the main symptoms of COVID-19 disease. The virus is able to actively multiply in the epithelium of airways. It is known that coronavirus SARS-CoV-2 causes severe lower respiratory disease with high mortality and evidence of systemic spread. COVID – 19 is a public health problem in countries regardless of their level of development. WHO estimates that more than 18 000 000 people in the world are currently suffering from the novel coronavirus disease (COVID-19).
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |