Literature DB >> 33374363

Automatic Classification of Adventitious Respiratory Sounds: A (Un)Solved Problem?

Bruno Machado Rocha1, Diogo Pessoa1, Alda Marques2,3, Paulo Carvalho1, Rui Pedro Paiva1.   

Abstract

(1) Background: Patients with respiratory conditions typically exhibit adventitious respiratory sounds (ARS), such as wheezes and crackles. ARS events have variable duration. In this work we studied the influence of event duration on automatic ARS classification, namely, how the creation of the Other class (negative class) affected the classifiers' performance. (2)
Methods: We conducted a set of experiments where we varied the durations of the other events on three tasks: crackle vs. wheeze vs. other (3 Class); crackle vs. other (2 Class Crackles); and wheeze vs. other (2 Class Wheezes). Four classifiers (linear discriminant analysis, support vector machines, boosted trees, and convolutional neural networks) were evaluated on those tasks using an open access respiratory sound database. (3)
Results: While on the 3 Class task with fixed durations, the best classifier achieved an accuracy of 96.9%, the same classifier reached an accuracy of 81.8% on the more realistic 3 Class task with variable durations. (4)
Conclusion: These results demonstrate the importance of experimental design on the assessment of the performance of automatic ARS classification algorithms. Furthermore, they also indicate, unlike what is stated in the literature, that the automatic classification of ARS is not a solved problem, as the algorithms' performance decreases substantially under complex evaluation scenarios.

Entities:  

Keywords:  adventitious respiratory sounds; experimental design; machine learning

Mesh:

Year:  2020        PMID: 33374363      PMCID: PMC7795327          DOI: 10.3390/s21010057

Source DB:  PubMed          Journal:  Sensors (Basel)        ISSN: 1424-8220            Impact factor:   3.576


  27 in total

Review 1.  Computerized adventitious respiratory sounds as outcome measures for respiratory therapy: a systematic review.

Authors:  Alda Marques; Ana Oliveira; Cristina Jácome
Journal:  Respir Care       Date:  2013-09-17       Impact factor: 2.258

2.  Validation of an automatic crackle (rale) counter.

Authors:  R L Murphy; E A Del Bono; F Davidson
Journal:  Am Rev Respir Dis       Date:  1989-10

3.  Detection of crackle events using a multi-feature approach.

Authors:  L Mendes; I M Vogiatzis; E Perantoni; E Kaimakamis; I Chouvarda; N Maglaveras; J Henriques; P Carvalho; R P Paiva
Journal:  Conf Proc IEEE Eng Med Biol Soc       Date:  2016-08

4.  Lung sounds classification using convolutional neural networks.

Authors:  Dalal Bardou; Kun Zhang; Sayed Mohammad Ahmad
Journal:  Artif Intell Med       Date:  2018-05-01       Impact factor: 5.326

5.  Application of semi-supervised deep learning to lung sound analysis.

Authors:  Daniel Chamberlain; Rahul Kodgule; Daniela Ganelin; Vivek Miglani; Richard Ribon Fletcher
Journal:  Conf Proc IEEE Eng Med Biol Soc       Date:  2016-08

6.  Method for automatic detection of wheezing in lung sounds.

Authors:  R J Riella; P Nohama; J M Maia
Journal:  Braz J Med Biol Res       Date:  2009-07       Impact factor: 2.590

Review 7.  Computerized respiratory sounds in patients with COPD: a systematic review.

Authors:  Cristina Jácome; Alda Marques
Journal:  COPD       Date:  2014-06-10       Impact factor: 2.409

8.  Scalogram based prediction model for respiratory disorders using optimized convolutional neural networks.

Authors:  S Jayalakshmy; Gnanou Florence Sudha
Journal:  Artif Intell Med       Date:  2020-01-20       Impact factor: 5.326

9.  Analysis of respiratory sounds: state of the art.

Authors:  Sandra Reichert; Raymond Gass; Christian Brandt; Emmanuel Andrès
Journal:  Clin Med Circ Respirat Pulm Med       Date:  2008-05-16

10.  COVID-19 pandemic and the stethoscope: Do not forget to sanitize.

Authors:  Mark A Marinella
Journal:  Heart Lung       Date:  2020-04-11       Impact factor: 2.210

View more
  6 in total

1.  VECTOR: An algorithm for the detection of COVID-19 pneumonia from velcro-like lung sounds.

Authors:  Fabrizio Pancaldi; Giuseppe Stefano Pezzuto; Giulia Cassone; Marianna Morelli; Andreina Manfredi; Matteo D'Arienzo; Caterina Vacchi; Fulvio Savorani; Giovanni Vinci; Francesco Barsotti; Maria Teresa Mascia; Carlo Salvarani; Marco Sebastiani
Journal:  Comput Biol Med       Date:  2022-01-06       Impact factor: 4.589

2.  Pilot study on nocturnal monitoring of crackles in children with pneumonia.

Authors:  Wilfried Nikolaizik; Lisa Wuensch; Monika Bauck; Volker Gross; Keywan Sohrabi; Andreas Weissflog; Olaf Hildebrandt; Ulrich Koehler; Stefanie Weber
Journal:  ERJ Open Res       Date:  2021-11-29

3.  Automated Lung Sound Classification Using a Hybrid CNN-LSTM Network and Focal Loss Function.

Authors:  Georgios Petmezas; Grigorios-Aris Cheimariotis; Leandros Stefanopoulos; Bruno Rocha; Rui Pedro Paiva; Aggelos K Katsaggelos; Nicos Maglaveras
Journal:  Sensors (Basel)       Date:  2022-02-06       Impact factor: 3.576

4.  CoCross: An ICT Platform Enabling Monitoring Recording and Fusion of Clinical Information Chest Sounds and Imaging of COVID-19 ICU Patients.

Authors:  Vassilis Kilintzis; Nikolaos Beredimas; Evangelos Kaimakamis; Leandros Stefanopoulos; Evangelos Chatzis; Edison Jahaj; Militsa Bitzani; Anastasia Kotanidou; Aggelos K Katsaggelos; Nicos Maglaveras
Journal:  Healthcare (Basel)       Date:  2022-01-30

5.  A Wearable Multimodal Sensing System for Tracking Changes in Pulmonary Fluid Status, Lung Sounds, and Respiratory Markers.

Authors:  Jesus Antonio Sanchez-Perez; John A Berkebile; Brandi N Nevius; Goktug C Ozmen; Christopher J Nichols; Venu G Ganti; Samer A Mabrouk; Gari D Clifford; Rishikesan Kamaleswaran; David W Wright; Omer T Inan
Journal:  Sensors (Basel)       Date:  2022-02-02       Impact factor: 3.576

6.  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.

Authors:  Fu-Shun Hsu; Shang-Ran Huang; Chien-Wen Huang; Chao-Jung Huang; Yuan-Ren Cheng; Chun-Chieh Chen; Jack Hsiao; Chung-Wei Chen; Li-Chin Chen; Yen-Chun Lai; Bi-Fang Hsu; Nian-Jhen Lin; Wan-Ling Tsai; Yi-Lin Wu; Tzu-Ling Tseng; Ching-Ting Tseng; Yi-Tsun Chen; Feipei Lai
Journal:  PLoS One       Date:  2021-07-01       Impact factor: 3.240

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.