Lee HY, et al. Allergy Asthma Immunol Res. 2023 Nov;15(6):725-756. https://doi.org/10.4168/aair.2023.15.6.725

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.

Moon HJ, et al. J Korean Med Sci. 2021 Aug;36(35):e248. https://doi.org/10.3346/jkms.2021.36.e248

The total number of pediatric emergency department (PED) visitors has decreased worldwide since the coronavirus disease (COVID-19) outbreak. We hypothesized that this might also affect the number of PED visits due to injuries. Therefore, we investigated these changes in PED visits after the COVID-19 outbreak through a long-term multicenter observational study. We assessed the changes in the proportion of injured pediatric patients’ weekly visits and the trend in the rate changes since the COVID-19 epidemic began by segmented regression analysis. We also evaluated the weekly change in the distribution of detailed diagnostic codes among pediatric patients with injuries before and after the COVID-19 pandemic. The proportion of injury-related PED visits increased when COVID-19 was first confirmed in Korea. After the COVID-19 epidemic, the proportion of foreign body ingestions and fracture patients among all pediatric patients with injuries increased significantly every week. The changes in the proportion of injured pediatric patients after the COVID-19 outbreak may have been the result of social distancing to prevent the spread of the virus. The risk of pediatric infections decreased but the risk of injury remained. Therefore, parents should take precautions to prevent infectious diseases and be careful to prevent children’s injuries at home.