2020
DOI: 10.2196/18082
|View full text |Cite
|
Sign up to set email alerts
|

Automatic Recognition, Segmentation, and Sex Assignment of Nocturnal Asthmatic Coughs and Cough Epochs in Smartphone Audio Recordings: Observational Field Study

Abstract: Background Asthma is one of the most prevalent chronic respiratory diseases. Despite increased investment in treatment, little progress has been made in the early recognition and treatment of asthma exacerbations over the last decade. Nocturnal cough monitoring may provide an opportunity to identify patients at risk for imminent exacerbations. Recently developed approaches enable smartphone-based cough monitoring. These approaches, however, have not undergone longitudinal overnight testing nor have… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

1
44
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
2
1

Relationship

2
6

Authors

Journals

citations
Cited by 36 publications
(45 citation statements)
references
References 55 publications
1
44
0
Order By: Relevance
“…It is noted that many published results have shown very high specificity (90.9% -99.8%) at the cost of significantly lower sensitivity (70.5% -88%) [7], [19]. Although the models introduced in [8] has shown an overall accuracy of 99.8%, its dataset only consists of night-time recordings of participants during their sleep, which include very little noise to cope with. Some other studies have achieved similar model performance only with the addition of other device data, such as contact microphones, respiratory inductance plethysmography, ECG sensors, and accelerometers [20].…”
Section: Discussion a Cough Detection And Extractionmentioning
confidence: 99%
See 1 more Smart Citation
“…It is noted that many published results have shown very high specificity (90.9% -99.8%) at the cost of significantly lower sensitivity (70.5% -88%) [7], [19]. Although the models introduced in [8] has shown an overall accuracy of 99.8%, its dataset only consists of night-time recordings of participants during their sleep, which include very little noise to cope with. Some other studies have achieved similar model performance only with the addition of other device data, such as contact microphones, respiratory inductance plethysmography, ECG sensors, and accelerometers [20].…”
Section: Discussion a Cough Detection And Extractionmentioning
confidence: 99%
“…Besides the noise handling, audio segmentation and accurate extraction of cough episodes is a pivotal algorithmic step that can characterize the cough signatures and effectively quantify associated metrics such as cough frequency, cough duration, cough intensity, etc. There have been some research reports on cough segmentation and extraction [7], [8]. However, their algorithmic performances have been often reported based on simple counting of cough episodes and evaluation metrics for classification tasks rather than conducting systematic performance evaluations involving episodic and duration performance metrics.…”
Section: Introductionmentioning
confidence: 99%
“…For example, we were able to show that deep learning models trained on data from this study can detect and count nocturnal cough automatically with a comparable accuracy to human annotators. 36 …”
Section: Discussionmentioning
confidence: 99%
“…For example, we were able to show that deep learning models trained on data from this study can detect and count nocturnal cough automatically with a comparable accuracy to human annotators. 36 However, the accuracies presented in this paper for detecting and predicting relevant asthma outcomes do not warrant the use of nocturnal cough and sleep quality as selfcontained biomarkers for asthma management. The limiting factors for marker performance remain unclear.…”
mentioning
confidence: 84%
“…There is another line of research inquiry which mainly focuses on cough event detection (i.e., to identify the presence of cough events) in audio recordings [ 19 , 20 , 21 , 22 , 23 , 24 ]; however, in this investigation, we manually segment the cough epochs, and thus review of such studies is outside the scope of this report. Having said that, with the advent of deep learning, there is good progress made in the cough event detection from smartphone recordings, and incorporating such techniques at the preprocessing stage in the cough screening system could bypass the tedious manual segmentation process altogether [ 25 , 26 , 27 ].…”
Section: Introductionmentioning
confidence: 99%