A Progressively Expanded Database for Automated Lung Sound Analysis: An Update

Abstract

We previously established an open-access lung sound database, HF_Lung_V1, and developed deep learning models for inhalation, exhalation, continuous adventitious sound (CAS), and discontinuous adventitious sound (DAS) detection. The amount of data used for training contributes to model accuracy. In this study, we collected larger quantities of data to further improve model performance and explored issues of noisy labels and overlapping sounds. HF_Lung_V1 was expanded to HF_Lung_V2 with a 1.43× increase in the number of audio files. Convolutional neural network–bidirectional gated recurrent unit network models were trained separately using the HF_Lung_V1 (V1_Train) and HF_Lung_V2 (V2_Train) training sets. These were tested using the HF_Lung_V1 (V1_Test) and HF_Lung_V2 (V2_Test) test sets, respectively. Segment and event detection performance was evaluated. Label quality was assessed. Overlap ratios were computed between inhalation, exhalation, CAS, and DAS labels. The model trained using V2_Train exhibited improved performance in inhalation, exhalation, CAS, and DAS detection on both V1_Test and V2_Test. Poor CAS detection was attributed to the quality of CAS labels. DAS detection was strongly influenced by the overlapping of DAS with inhalation and exhalation. In conclusion, collecting greater quantities of lung sound data is vital for developing more accurate lung sound analysis models.

Respiratory Diseases Diagnosis Using Audio Analysis and Artificial Intelligence: A Systematic Review

“…The authors employed 11 experienced paediatric physicians to annotate it, using a custom-made software. “HF_Lung” [ 96 ] database stands as the last identified database for lung sound analysis. This database originally had lung sounds recorded from 18 patients between August 2018 and October 2019.…”

A review on lung disease recognition by acoustic signal analysis with deep learning networks

“…A 2011 review [62] emphasizes that previous studies can identify signs like wheezes or crackles. As earlier declared, the performance of classification and sound detection has significantly increased with the advent of deep and machine learning [42,43], and research about lung sound analysis has benefited from this development [65,110,150]. Lung sound analysis may be converted into a classification problem [29] with the help of identified markers, which is a problem class that machine learning excels at resolving.…”