It is well-known that the results of traditional auscultation are subjective and depend on the clinical experience and auditory perception ability of the physician additional limitations of traditional auscultation include the inability to save or share the sound signal, its poor repeatability, and the inability to continuously monitor the breath sounds, among others. The stethoscope has the advantages of being non-invasive, easy to use, affordable, and non-radioactive, and stethoscope-based examinations can be repeated quickly, making the device especially suitable for use for pediatric patients. The ability of the AI algorithm to analyze adventitious breath sounds was better than that of the general pediatricians.Īlthough non-invasive methods for the diagnosis and follow-up of lung diseases have undergone rapid development, the auscultation of breath sounds with a stethoscope remains a key part of the initial examination of lung diseases. Performance varied according to the age of the patient, with patients younger than 12 months yielding the highest accuracy (81.3%, p < 0.001) among the age groups.Ĭonclusion: In a real clinical environment, children's breath sounds were collected and transmitted remotely by an electronic stethoscope these breath sounds could be recognized by both pediatricians and an AI algorithm. The sensitivity, specificity, and F1-score in the detection of crackles and wheeze from the AI algorithm were higher than those from the general pediatricians (crackles 81.1 vs. The accuracy of the detection of adventitious breath sounds by the AI algorithm and general pediatricians with respect to the GS were 77.7% and 59.9% ( p < 0.001), respectively. A total of 672 breath sounds were collected, and 627 (93.3%) breath sounds, including 159 crackles (23.1%), 264 wheeze (38.4%), and 264 normal breath sounds (38.4%), were fully analyzed by the AI algorithm. Result: A total of 112 hospitalized children with pulmonary diseases were recruited for the study from May to December 2019. Meanwhile, the performance of the AI algorithm for different patient ages and recording locations was evaluated. The accuracy, sensitivity, specificity, precision, and F1-score of the AI algorithm and general pediatricians with respect to the GS were evaluated. The discrimination results for all chest locations with respect to a gold standard (GS) established by 2 experienced pediatric pulmonologists from SCMC and 6 general pediatricians were recorded. Method: The auscultations of breath sounds were collected in the respiratory department of Shanghai Children's Medical Center (SCMC) by using an electronic stethoscope. The objective of this study was to evaluate the use of an artificial intelligence (AI) algorithm for the detection of breath sounds in a real clinical environment among children with pulmonary diseases. Objective: Lung auscultation plays an important role in the diagnosis of pulmonary diseases in children. 4Tuoxiao Intelligent Technology Company, Shanghai, China.3Child Health Advocacy Institute, China Hospital Development Institute of Shanghai Jiao Tong University, Shanghai, China.2Paediatric AI Clinical Application and Research Center, Shanghai Children's Medical Center, Shanghai, China. 1Department of Respiratory Medicine, Shanghai Children's Medical Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China.Jing Zhang 1 Han-Song Wang 2,3 Hong-Yuan Zhou 4 Bin Dong 2 Lei Zhang 1 Fen Zhang 1 Shi-Jian Liu 2 Yu-Fen Wu 1 Shu-Hua Yuan 1 Ming-Yu Tang 1 Wen-Fang Dong 1 Jie Lin 1 Ming Chen 1 Xing Tong 1 Lie-Bin Zhao 2,3 * Yong Yin 1 *
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |