Hsu F.-SFEI-PEI LAI et al.2022-04-252022-04-25202119326203https://www.scopus.com/inward/record.uri?eid=2-s2.0-85110382476&doi=10.1371%2fjournal.pone.0254134&partnerID=40&md5=fae8b5ec690cfa592d0050ee9ac58a0chttps://scholars.lib.ntu.edu.tw/handle/123456789/607544A reliable, remote, and continuous real-time respiratory sound monitor with automated respiratory sound analysis ability is urgently required in many clinical scenarios-such as in monitoring disease progression of coronavirus disease 2019-to replace conventional auscultation with a handheld stethoscope. However, a robust computerized respiratory sound analysis algorithm for breath phase detection and adventitious sound detection at the recording level has not yet been validated in practical applications. In this study, we developed a lung sound database (HF_Lung_V1) comprising 9,765 audio files of lung sounds (duration of 15 s each), 34,095 inhalation labels, 18,349 exhalation labels, 13,883 continuous adventitious sound (CAS) labels (comprising 8,457 wheeze labels, 686 stridor labels, and 4,740 rhonchus labels), and 15,606 discontinuous adventitious sound labels (all crackles). We conducted benchmark tests using long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional LSTM (BiLSTM), bidirectional GRU (BiGRU), convolutional neural network (CNN)-LSTM, CNN-GRU, CNN-BiLSTM, and CNN-BiGRU models for breath phase detection and adventitious sound detection. We also conducted a performance comparison between the LSTM-based and GRU-based models, between unidirectional and bidirectional models, and between models with and without a CNN. The results revealed that these models exhibited adequate performance in lung sound analysis. The GRU-based models outperformed, in terms of F1 scores and areas under the receiver operating characteristic curves, the LSTM-based models in most of the defined tasks. Furthermore, all bidirectional models outperformed their unidirectional counterparts. Finally, the addition of a CNN improved the accuracy of lung sound analysis, especially in the CAS detection tasks. ? 2021 Hsu et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.abnormal respiratory soundadultadventitious sound detectionagedArticleaudio filebenchmarkingbidirectional gated recurrent unit modelbidirectional long short term memory modelbreath phase detectionclinical articlecontinuous adventitious sound labelcontrolled studyconvolutional neural network bidirectional gated recurrent unit modelconvolutional neural network bidirectional long short term memory modelconvolutional neural network gated recurrent unit modelconvolutional neural network long short term memory modelcrackledata basedata processingdiagnostic accuracydiagnostic test accuracy studydiscontinuous adventitious sound labelexhalation labelfemalegated recurrent unit modelhumaninhalation labelintermethod comparisonlong short term memory modellung sound databasemalemodelpredictive valuereceiver operating characteristicrecurrent neural networkrespiratory tract parametersrhonchussensitivity and specificitysound analysissound detectionstridorwheezingbreathingdiagnosisdisease exacerbationfactual databaselungmiddle agedpathophysiologyvery elderlyAdultAgedAged, 80 and overBenchmarkingCOVID-19Databases, FactualDisease ProgressionFemaleHumansLungMaleMiddle AgedNeural Networks, ComputerRespirationRespiratory Sounds[SDGs]SDG3journal article10.1371/journal.pone.0254134341975562-s2.0-85110382476