The use of spectrograms improves the classification of wheezes and crackles in an educational setting
Abstract Chest auscultation is a widely used method in the diagnosis of lung diseases. However, the interpretation of lung sounds is a subjective task and disagreements arise. New technological developments like the use of visSual representation of sounds through spectrograms could improve the agree...
Published in: | Scientific Reports |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Nature Portfolio
2020
|
Subjects: | |
Online Access: | https://doi.org/10.1038/s41598-020-65354-w https://doaj.org/article/6bd738086c0349eba422d297057c8c48 |
id |
ftdoajarticles:oai:doaj.org/article:6bd738086c0349eba422d297057c8c48 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:6bd738086c0349eba422d297057c8c48 2023-05-15T18:49:27+02:00 The use of spectrograms improves the classification of wheezes and crackles in an educational setting J. C. Aviles-Solis I. Storvoll Sophie Vanbelle H. Melbye 2020-05-01T00:00:00Z https://doi.org/10.1038/s41598-020-65354-w https://doaj.org/article/6bd738086c0349eba422d297057c8c48 EN eng Nature Portfolio https://doi.org/10.1038/s41598-020-65354-w https://doaj.org/toc/2045-2322 doi:10.1038/s41598-020-65354-w 2045-2322 https://doaj.org/article/6bd738086c0349eba422d297057c8c48 Scientific Reports, Vol 10, Iss 1, Pp 1-8 (2020) Medicine R Science Q article 2020 ftdoajarticles https://doi.org/10.1038/s41598-020-65354-w 2022-12-31T11:18:17Z Abstract Chest auscultation is a widely used method in the diagnosis of lung diseases. However, the interpretation of lung sounds is a subjective task and disagreements arise. New technological developments like the use of visSual representation of sounds through spectrograms could improve the agreement when classifying lung sounds, but this is not yet known. In this study, we tested if the use of spectrograms improves the agreement when classifying wheezes and crackles. To do this, we asked twenty-three medical students at UiT the Arctic University of Norway to classify 30 lung sounds recordings for the presence of wheezes and crackles. The sample contained 15 normal recordings and 15 with wheezes or crackles. The students classified the recordings in a random order twice. First sound only, then sound with spectrograms. We calculated kappa values for the agreement between each student and the expert classification with and without display of spectrograms and tested for significant improvement between these two coefficients. We also calculated Fleiss kappa for the 23 observers with and without the spectrogram. In an individual analysis comparing each student to an expert annotated reference standard we found that 13 out of 23 students had a positive change in kappa when classifying wheezes with the help of spectrograms. When classifying crackles 16 out of 23 showed improvement when spectrograms were used. In a group analysis we observed that Fleiss kappa values were k = 0.51 and k = 0.56 (p = 0.63) for classifying wheezes without and with spectrograms. For crackles, these values were k = 0.22 and k = 0.40 (p = <0.01) in the same order. Thus, we conclude that the use of spectrograms had a positive impact on the inter-rater agreement and the agreement with experts. We observed a higher improvement in the classification of crackles compared to wheezes. Article in Journal/Newspaper Arctic University of Norway UiT The Arctic University of Norway Directory of Open Access Journals: DOAJ Articles Arctic Norway Scientific Reports 10 1 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q J. C. Aviles-Solis I. Storvoll Sophie Vanbelle H. Melbye The use of spectrograms improves the classification of wheezes and crackles in an educational setting |
topic_facet |
Medicine R Science Q |
description |
Abstract Chest auscultation is a widely used method in the diagnosis of lung diseases. However, the interpretation of lung sounds is a subjective task and disagreements arise. New technological developments like the use of visSual representation of sounds through spectrograms could improve the agreement when classifying lung sounds, but this is not yet known. In this study, we tested if the use of spectrograms improves the agreement when classifying wheezes and crackles. To do this, we asked twenty-three medical students at UiT the Arctic University of Norway to classify 30 lung sounds recordings for the presence of wheezes and crackles. The sample contained 15 normal recordings and 15 with wheezes or crackles. The students classified the recordings in a random order twice. First sound only, then sound with spectrograms. We calculated kappa values for the agreement between each student and the expert classification with and without display of spectrograms and tested for significant improvement between these two coefficients. We also calculated Fleiss kappa for the 23 observers with and without the spectrogram. In an individual analysis comparing each student to an expert annotated reference standard we found that 13 out of 23 students had a positive change in kappa when classifying wheezes with the help of spectrograms. When classifying crackles 16 out of 23 showed improvement when spectrograms were used. In a group analysis we observed that Fleiss kappa values were k = 0.51 and k = 0.56 (p = 0.63) for classifying wheezes without and with spectrograms. For crackles, these values were k = 0.22 and k = 0.40 (p = <0.01) in the same order. Thus, we conclude that the use of spectrograms had a positive impact on the inter-rater agreement and the agreement with experts. We observed a higher improvement in the classification of crackles compared to wheezes. |
format |
Article in Journal/Newspaper |
author |
J. C. Aviles-Solis I. Storvoll Sophie Vanbelle H. Melbye |
author_facet |
J. C. Aviles-Solis I. Storvoll Sophie Vanbelle H. Melbye |
author_sort |
J. C. Aviles-Solis |
title |
The use of spectrograms improves the classification of wheezes and crackles in an educational setting |
title_short |
The use of spectrograms improves the classification of wheezes and crackles in an educational setting |
title_full |
The use of spectrograms improves the classification of wheezes and crackles in an educational setting |
title_fullStr |
The use of spectrograms improves the classification of wheezes and crackles in an educational setting |
title_full_unstemmed |
The use of spectrograms improves the classification of wheezes and crackles in an educational setting |
title_sort |
use of spectrograms improves the classification of wheezes and crackles in an educational setting |
publisher |
Nature Portfolio |
publishDate |
2020 |
url |
https://doi.org/10.1038/s41598-020-65354-w https://doaj.org/article/6bd738086c0349eba422d297057c8c48 |
geographic |
Arctic Norway |
geographic_facet |
Arctic Norway |
genre |
Arctic University of Norway UiT The Arctic University of Norway |
genre_facet |
Arctic University of Norway UiT The Arctic University of Norway |
op_source |
Scientific Reports, Vol 10, Iss 1, Pp 1-8 (2020) |
op_relation |
https://doi.org/10.1038/s41598-020-65354-w https://doaj.org/toc/2045-2322 doi:10.1038/s41598-020-65354-w 2045-2322 https://doaj.org/article/6bd738086c0349eba422d297057c8c48 |
op_doi |
https://doi.org/10.1038/s41598-020-65354-w |
container_title |
Scientific Reports |
container_volume |
10 |
container_issue |
1 |
_version_ |
1766243041718304768 |