An accurate deep learning model for wheezing in children using real world data
Abstract Auscultation is an important diagnostic method for lung diseases. However, it is a subjective modality and requires a high degree of expertise. To overcome this constraint, artificial intelligence models are being developed. However, these models require performance improvements and do not...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-25953-1 |
| _version_ | 1797973736078442496 |
|---|---|
| author | Beom Joon Kim Baek Seung Kim Jeong Hyeon Mun Changwon Lim Kyung Hoon Kim |
| author_facet | Beom Joon Kim Baek Seung Kim Jeong Hyeon Mun Changwon Lim Kyung Hoon Kim |
| author_sort | Beom Joon Kim |
| collection | DOAJ |
| description | Abstract Auscultation is an important diagnostic method for lung diseases. However, it is a subjective modality and requires a high degree of expertise. To overcome this constraint, artificial intelligence models are being developed. However, these models require performance improvements and do not reflect the actual clinical situation. We aimed to develop an improved deep-learning model learning to detect wheezing in children, based on data from real clinical practice. In this prospective study, pediatric pulmonologists recorded and verified respiratory sounds in 76 pediatric patients who visited a university hospital in South Korea. In addition, structured data, such as sex, age, and auscultation location, were collected. Using our dataset, we implemented an optimal model by transforming it based on the convolutional neural network model. Finally, we proposed a model using a 34-layer residual network with the convolutional block attention module for audio data and multilayer perceptron layers for tabular data. The proposed model had an accuracy of 91.2%, area under the curve of 89.1%, precision of 94.4%, recall of 81%, and F1-score of 87.2%. The deep-learning model proposed had a high accuracy for detecting wheeze sounds. This high-performance model will be helpful for the accurate diagnosis of respiratory diseases in actual clinical practice. |
| first_indexed | 2024-04-11T04:07:46Z |
| format | Article |
| id | doaj.art-cb1b834b38424399bcdf1474246b1ea0 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T04:07:46Z |
| publishDate | 2022-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-cb1b834b38424399bcdf1474246b1ea02023-01-01T12:16:47ZengNature PortfolioScientific Reports2045-23222022-12-011211810.1038/s41598-022-25953-1An accurate deep learning model for wheezing in children using real world dataBeom Joon Kim0Baek Seung Kim1Jeong Hyeon Mun2Changwon Lim3Kyung Hoon Kim4Department of Pediatrics, College of Medicine, The Catholic University of KoreaDepartment of Applied Statistics, Chung-Ang UniversityDepartment of Applied Statistics, Chung-Ang UniversityDepartment of Applied Statistics, Chung-Ang UniversityDepartment of Pediatrics, Seoul National University Bundang HospitalAbstract Auscultation is an important diagnostic method for lung diseases. However, it is a subjective modality and requires a high degree of expertise. To overcome this constraint, artificial intelligence models are being developed. However, these models require performance improvements and do not reflect the actual clinical situation. We aimed to develop an improved deep-learning model learning to detect wheezing in children, based on data from real clinical practice. In this prospective study, pediatric pulmonologists recorded and verified respiratory sounds in 76 pediatric patients who visited a university hospital in South Korea. In addition, structured data, such as sex, age, and auscultation location, were collected. Using our dataset, we implemented an optimal model by transforming it based on the convolutional neural network model. Finally, we proposed a model using a 34-layer residual network with the convolutional block attention module for audio data and multilayer perceptron layers for tabular data. The proposed model had an accuracy of 91.2%, area under the curve of 89.1%, precision of 94.4%, recall of 81%, and F1-score of 87.2%. The deep-learning model proposed had a high accuracy for detecting wheeze sounds. This high-performance model will be helpful for the accurate diagnosis of respiratory diseases in actual clinical practice.https://doi.org/10.1038/s41598-022-25953-1 |
| spellingShingle | Beom Joon Kim Baek Seung Kim Jeong Hyeon Mun Changwon Lim Kyung Hoon Kim An accurate deep learning model for wheezing in children using real world data Scientific Reports |
| title | An accurate deep learning model for wheezing in children using real world data |
| title_full | An accurate deep learning model for wheezing in children using real world data |
| title_fullStr | An accurate deep learning model for wheezing in children using real world data |
| title_full_unstemmed | An accurate deep learning model for wheezing in children using real world data |
| title_short | An accurate deep learning model for wheezing in children using real world data |
| title_sort | accurate deep learning model for wheezing in children using real world data |
| url | https://doi.org/10.1038/s41598-022-25953-1 |
| work_keys_str_mv | AT beomjoonkim anaccuratedeeplearningmodelforwheezinginchildrenusingrealworlddata AT baekseungkim anaccuratedeeplearningmodelforwheezinginchildrenusingrealworlddata AT jeonghyeonmun anaccuratedeeplearningmodelforwheezinginchildrenusingrealworlddata AT changwonlim anaccuratedeeplearningmodelforwheezinginchildrenusingrealworlddata AT kyunghoonkim anaccuratedeeplearningmodelforwheezinginchildrenusingrealworlddata AT beomjoonkim accuratedeeplearningmodelforwheezinginchildrenusingrealworlddata AT baekseungkim accuratedeeplearningmodelforwheezinginchildrenusingrealworlddata AT jeonghyeonmun accuratedeeplearningmodelforwheezinginchildrenusingrealworlddata AT changwonlim accuratedeeplearningmodelforwheezinginchildrenusingrealworlddata AT kyunghoonkim accuratedeeplearningmodelforwheezinginchildrenusingrealworlddata |