Lung sounds are either normal or abnormal. In addition, chronic obstructive pulmonary disease (COPD) is expected to be the third leading cause of death by 2030 (World Health Organization 2017b). According to the world health organization (WHO) report in 2017 (World Health Organization 2017a), more than 235 million people are suffering from asthma worldwide. Through a stethoscope, the sound of air moving inside and outside the lungs during breathing can be auscultated through chest walls allowing a physiotherapist to identify any pulmonary diseases such as asthma, pneumonia, or bronchiectasis (BRON) (Andrès et al. It is considered as a safe, non-invasive, and cost-effective clinical method to monitor the overall condition of the lungs and surrounding respiratory organs (Bardou et al. Pulmonary auscultation is one of the oldest techniques used in the diagnosis of the respiratory system. This study paves the way towards implementing deep learning models in clinical settings to assist clinicians in decision making related to the recognition of pulmonary diseases. Furthermore, a total agreement of 98.26% was obtained between the predictions and original classes within the training scheme. The developed algorithm achieved the highest average accuracy of 99.62% with a precision of 98.85% in classifying patients based on the pulmonary disease types using CNN + BDLSTM. The training of the model was evaluated based on a k-fold cross-validation scheme of tenfolds using several performance evaluation metrics including Cohen’s kappa, accuracy, sensitivity, specificity, precision, and F1-score. The deep learning network architecture consisted of two stages convolutional neural networks and bidirectional long short-term memory units. These steps included wavelet smoothing, displacement artifact removal, and z-score normalization. Then, several preprocessing steps were undertaken to ensure smoother and less noisy signals. Initially, all signals were checked to have a sampling frequency of 4 kHz and segmented into 5 s segments. on Biomedical Health Informatics publicly available challenge database. In addition, 110 patients data were added to the data-set from the Int. The selected data-set included a total of 103 patients obtained from locally recorded stethoscope lung sounds acquired at King Abdullah University Hospital, Jordan University of Science and Technology, Jordan. In this paper, a study is conducted to explore the ability of deep learning in recognizing pulmonary diseases from electronically recorded lung sounds.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |