Computerized acoustical techniques for respiratory flow-sound analysis: a systematic review

Muthusamy, Priya Devi; Sundaraj, Kenneth; Manap, Nurulfajar Abd

doi:10.1007/s10462-019-09769-6

Cited by 14 publications

(10 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, a practitioner wearing personal protective equipment finds it difficult to perform auscultation without breaching the protection [8], which limits the use of auscultation on a patient with an airborne or droplet-transmitted pulmonary disease, such as coronavirus disease 2019 (COVID-19) [9][10][11]. To overcome the aforementioned limitations, computerized respiratory sound analysis [12] is required. Furthermore, a tele-auscultation system [13,14] with automated respiratory sound analysis can be realized in the form of a mobile app or web service with proper infrastructure supports, which can facilitate remote respiratory monitoring not only in a clinical setting but in a homecare setting.…”

Section: Introductionmentioning

confidence: 99%

Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database—HF_Lung_V1

Hsu

Huang²,

Huang³

et al. 2021

PLoS ONE

View full text Add to dashboard Cite

A reliable, remote, and continuous real-time respiratory sound monitor with automated respiratory sound analysis ability is urgently required in many clinical scenarios—such as in monitoring disease progression of coronavirus disease 2019—to replace conventional auscultation with a handheld stethoscope. However, a robust computerized respiratory sound analysis algorithm for breath phase detection and adventitious sound detection at the recording level has not yet been validated in practical applications. In this study, we developed a lung sound database (HF_Lung_V1) comprising 9,765 audio files of lung sounds (duration of 15 s each), 34,095 inhalation labels, 18,349 exhalation labels, 13,883 continuous adventitious sound (CAS) labels (comprising 8,457 wheeze labels, 686 stridor labels, and 4,740 rhonchus labels), and 15,606 discontinuous adventitious sound labels (all crackles). We conducted benchmark tests using long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional LSTM (BiLSTM), bidirectional GRU (BiGRU), convolutional neural network (CNN)-LSTM, CNN-GRU, CNN-BiLSTM, and CNN-BiGRU models for breath phase detection and adventitious sound detection. We also conducted a performance comparison between the LSTM-based and GRU-based models, between unidirectional and bidirectional models, and between models with and without a CNN. The results revealed that these models exhibited adequate performance in lung sound analysis. The GRU-based models outperformed, in terms of F1 scores and areas under the receiver operating characteristic curves, the LSTM-based models in most of the defined tasks. Furthermore, all bidirectional models outperformed their unidirectional counterparts. Finally, the addition of a CNN improved the accuracy of lung sound analysis, especially in the CAS detection tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database—HF_Lung_V1

Hsu

Huang²,

Huang³

et al. 2021

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Previous studies on automated and computerised respiratory sound analysis have been conducted using several Machine Learning algorithms. This section provides a discussion of the few prominent works on computerised respiratory sound analysis [19].…”

Section: Review Of Previous Workmentioning

confidence: 99%

“…An observational study in Italy showed that 37.9% of COPD patients were receiving appropriate treatment, in 54.9% there was over-prescription. Over and above that, 66.8% were prescribed Inhaled corticosteroids (ICS) along with long-acting bronchodilators and 15.2% used ICS alone [19]. The evidence of benefit of ICS in COPD is limited by methodological problems and have not shown any survival benefit independent of the effect of long-acting bronchodilator.…”

Section: Mistreatment and Misdiagnosis Of Lung Diseasesmentioning

confidence: 99%

Development of Classification Methods for Wheeze and Crackle Using Mel Frequency Cepstral Coefficient (MFCC): A Deep Learning Approach

Sadi¹,

Hassan²

2020

IJPCC

View full text Add to dashboard Cite

The most common method used by physicians and pulmonologists to evaluate the state of the lung is by listening to the acoustics of the patient's breathing by a stethoscope. Misdiagnosis and eventually, mistreatment are rampant if auscultation is not done properly. There have been efforts to address this problem using a myriad of machine learning algorithms, but little has been done using deep learning. A CNN model with MFCC is expected to mitigate these problems. The problem has been in the paucity of large enough datasets. Results show 0.76 and 0.60 for recall for wheeze and crackle respectively, these number are set to increase with optimization.

show abstract

“…Other methods based on artificial neural networks have been proposed, such as by Lei et al [ 16 ]. A complete review of TS processing methods is presented in Muthusamy et al [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

Respiratory Monitoring Based on Tracheal Sounds: Continuous Time-Frequency Processing of the Phonospirogram Combined with Phonocardiogram-Derived Respiration

Coste

Niérat

et al. 2020

Sensors

View full text Add to dashboard Cite

Patients with central respiratory paralysis can benefit from diaphragm pacing to restore respiratory function. However, it would be important to develop a continuous respiratory monitoring method to alert on apnea occurrence, in order to improve the efficiency and safety of the pacing system. In this study, we present a preliminary validation of an acoustic apnea detection method on healthy subjects data. Thirteen healthy participants performed one session of two 2-min recordings, including a voluntary respiratory pause. The recordings were post-processed by combining temporal and frequency detection domains, and a new method was proposed—Phonocardiogram-Derived Respiration (PDR). The detection results were compared to synchronized pneumotachograph, electrocardiogram (ECG), and abdominal strap (plethysmograph) signals. The proposed method reached an apnea detection rate of 92.3%, with 99.36% specificity, 85.27% sensitivity, and 91.49% accuracy. PDR method showed a good correlation of 0.77 with ECG-Derived Respiration (EDR). The comparison of R-R intervals and S-S intervals also indicated a good correlation of 0.89. The performance of this respiratory detection algorithm meets the minimal requirements to make it usable in a real situation. Noises from the participant by speaking or from the environment had little influence on the detection result, as well as body position. The high correlation between PDR and EDR indicates the feasibility of monitoring respiration with PDR.

show abstract

Computerized acoustical techniques for respiratory flow-sound analysis: a systematic review

Cited by 14 publications

References 62 publications

Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database—HF_Lung_V1

Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database—HF_Lung_V1

Development of Classification Methods for Wheeze and Crackle Using Mel Frequency Cepstral Coefficient (MFCC): A Deep Learning Approach

Respiratory Monitoring Based on Tracheal Sounds: Continuous Time-Frequency Processing of the Phonospirogram Combined with Phonocardiogram-Derived Respiration

Contact Info

Product

Resources

About