TY - JOUR
T1 - Machine Learning for Automated Classification of Abnormal Lung Sounds Obtained from Public Databases
T2 - A Systematic Review
AU - Garcia-Mendez, Juan P.
AU - Lal, Amos
AU - Herasevich, Svetlana
AU - Tekin, Aysun
AU - Pinevich, Yuliya
AU - Lipatov, Kirill
AU - Wang, Hsin Yi
AU - Qamar, Shahraz
AU - Ayala, Ivan N.
AU - Khapov, Ivan
AU - Gerberi, Danielle J.
AU - Diedrich, Daniel
AU - Pickering, Brian W.
AU - Herasevich, Vitaly
N1 - Publisher Copyright:
© 2023 by the authors.
PY - 2023/10
Y1 - 2023/10
N2 - Pulmonary auscultation is essential for detecting abnormal lung sounds during physical assessments, but its reliability depends on the operator. Machine learning (ML) models offer an alternative by automatically classifying lung sounds. ML models require substantial data, and public databases aim to address this limitation. This systematic review compares characteristics, diagnostic accuracy, concerns, and data sources of existing models in the literature. Papers published from five major databases between 1990 and 2022 were assessed. Quality assessment was accomplished with a modified QUADAS-2 tool. The review encompassed 62 studies utilizing ML models and public-access databases for lung sound classification. Artificial neural networks (ANN) and support vector machines (SVM) were frequently employed in the ML classifiers. The accuracy ranged from 49.43% to 100% for discriminating abnormal sound types and 69.40% to 99.62% for disease class classification. Seventeen public databases were identified, with the ICBHI 2017 database being the most used (66%). The majority of studies exhibited a high risk of bias and concerns related to patient selection and reference standards. Summarizing, ML models can effectively classify abnormal lung sounds using publicly available data sources. Nevertheless, inconsistent reporting and methodologies pose limitations to advancing the field, and therefore, public databases should adhere to standardized recording and labeling procedures.
AB - Pulmonary auscultation is essential for detecting abnormal lung sounds during physical assessments, but its reliability depends on the operator. Machine learning (ML) models offer an alternative by automatically classifying lung sounds. ML models require substantial data, and public databases aim to address this limitation. This systematic review compares characteristics, diagnostic accuracy, concerns, and data sources of existing models in the literature. Papers published from five major databases between 1990 and 2022 were assessed. Quality assessment was accomplished with a modified QUADAS-2 tool. The review encompassed 62 studies utilizing ML models and public-access databases for lung sound classification. Artificial neural networks (ANN) and support vector machines (SVM) were frequently employed in the ML classifiers. The accuracy ranged from 49.43% to 100% for discriminating abnormal sound types and 69.40% to 99.62% for disease class classification. Seventeen public databases were identified, with the ICBHI 2017 database being the most used (66%). The majority of studies exhibited a high risk of bias and concerns related to patient selection and reference standards. Summarizing, ML models can effectively classify abnormal lung sounds using publicly available data sources. Nevertheless, inconsistent reporting and methodologies pose limitations to advancing the field, and therefore, public databases should adhere to standardized recording and labeling procedures.
KW - deep learning (DL)
KW - electronic auscultation
KW - lung sounds
KW - machine learning (ML)
KW - public databases
UR - http://www.scopus.com/inward/record.url?scp=85175482527&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85175482527&partnerID=8YFLogxK
U2 - 10.3390/bioengineering10101155
DO - 10.3390/bioengineering10101155
M3 - Review article
AN - SCOPUS:85175482527
SN - 2306-5354
VL - 10
JO - Bioengineering
JF - Bioengineering
IS - 10
M1 - 1155
ER -