Abstract
Mechanically ventilated patients typically exhibit abnormal respiratory sounds. Squawks are short inspiratory adventitious sounds that may occur in patients with pneumonia, such as COVID-19 patients. In this work we devised a method for squawk detection in mechanically ventilated patients by developing algorithms for respiratory cycle estimation, squawk candidate identification, feature extraction, and clustering. The best classifier reached an F1 of 0.48 at the sound file level and an F1 of 0.66 at the recording session level. These preliminary results are promising, as they were obtained in noisy environments. This method will give health professionals a new feature to assess the potential deterioration of critically ill patients.
Highlights
Coronavirus disease 2019 (COVID-19) is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)
The addition of pink noise was inspired by the ensemble empirical mode decomposition (EEMD) approach, which consists of sifting an ensemble of white noise-added signal and considering the mean as the final result [21]
At the sound files (SF) level, the algorithm with the best performance had a threshold of 50%, attaining a F1 of 0.48 and a MCC of 0.42
Summary
Coronavirus disease 2019 (COVID-19) is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Adventitious sounds are additional respiratory sounds superimposed on normal breath sounds [20]. They are mainly composed by continuous (wheezes) or discontinuous (crackles) sounds [12]. Several methods have been devised to detect squawks. Neural networks have been used to classify squawks along with other classes of adventitious sounds [9], [2], reaching accuracies higher than 90%. All those works used very small datasets containing less than 10 squawks. We developed a method for the detection of squawks in respiratory sounds of mechanically ventilated patients with COVID-19. Our method encompasses several steps: respiratory cycle estimation, identification of possible squawks, feature extraction, and clustering
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
