Machine Learning for Automated Classification of Abnormal Lung Sounds Obtained from Public Databases: A Systematic Review

Abstract

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.

Keywords: deep learning (DL); electronic auscultation; lung sounds; machine learning (ML); public databases.

Figure 1

Process of automatic lung sound classification.

Figure 2

Preferred Reporting Items for Systematic Reviews and Meta-Analyses flow diagram.

Figure 3

Number of included publications by year, absolute values.

Figure 4

Quality assessment summary plots for the risk of bias (top) and applicability concerns (bottom). Presented as the number of articles with high, unclear, or low risk/concerns across each domain of the modified QUADAS-2 tool. (Green: low risk of bias; red: high risk of bias; yellow: unclear risk of bias).