2/24/2024 0 Comments Lungs soundsPrevious studies have been performed in the attempt to classify abnormal lung sounds by using machine learning techniques 11, 12. Wheezing may be heard during bronchiolitis, asthma exacerbation, or other obstructive airway disorders, and crackles may suggest pulmonary edema, pneumonia, or interstitial lung diseases 10. Crackles typically appear as rapidly dampened wave deflections, with typical frequencies and durations of 650 Hz and 5 ms, respectively, for fine crackles, and 350 Hz and 15 ms, respectively, for coarse crackles. Crackles are short, explosive, nonmusical sounds, heard upon inspiration and sometimes during expiration, suggesting intermittent airway closure and opening of small airways. Wheezes typically appear as sinusoidal oscillations with sound energies in the range of 100 Hz to 1000 Hz, and lasting for longer than 80 ms. A wheeze is defined as a musical, high-pitched sound that can be heard upon inspiration and/or expiration, suggesting airway narrowing and airflow limitation. The two most commonly noted abnormal lung sounds are wheezes and crackles. However, with the use of electronic stethoscopes, lung sounds can be stored, shared, and analyzed with various methods 7, 8, 9. Auscultation with a stethoscope has certain limitations: it usually requires an in-person encounter, and lung sounds are prone to subjective interpretation and cannot be reviewed or shared between clinicians 6. Its role is especially important in children, who have more frequent respiratory infections and wheezing events than adults 2, 3, 4, 5. Auscultation is quick, cost-effective, non-invasive, and radiation-free compared to other modes of diagnosis. Since the development of the first stethoscope by René Laennec in 1816, auscultation has been essential in the diagnosis of respiratory disorders 1. An automated classification model of pediatric lung sounds is feasible and maybe utilized as a screening tool for respiratory disorders in this pandemic era. The prospective validation (n = 90) accuracies were 82.22%, 67.74%, 67.80%, and 81.36%, respectively, which were comparable to pediatrician and non-pediatrician performance. The model accuracies during internal validation for normal vs. Total 680 clips were used for training and internal validation. Model performance on a prospective validation set (June to July 2021) was compared with those of pediatricians and non-pediatricians. wheezing) using K-fold cross-validation ( K = 10). Ensemble support vector machine models were trained and evaluated for four classification tasks (normal vs. Lung sounds were digitally recorded during routine physical examinations at a pediatric pulmonology outpatient clinic from July to November 2019 and labeled as normal, crackles, or wheezing. We aimed to develop a machine learning model to classify pediatric respiratory sounds. Electronic stethoscopes allow transmission, storage, and analysis of lung sounds. Auscultation, a cost-effective and non-invasive part of physical examination, is essential to diagnose pediatric respiratory disorders.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |