Elaboration of selected respiratory system diseases in children in the pediatric hospital Bielsko-Biala In years 2015-2022. / Omówienie wybranych chorób ukladu oddechowego u dzieci na terenie szpitala pediatrycznego w Bielska-Bialej w latach 2015-2022.

INTRODUCTION: Respiratory tract infections in children are an interdisciplinary problem that pediatricians, allergists, laryngologists and immunologists encounter on a daily basis. In the youngest children, these diseases are caused by the structure of the respiratory tract, which is shorter and narrower than in an adult, as well as the immaturity of the immune system. Among all children under 5 years of age hospitalized due to respiratory diseases, 20% of cases are acute respiratory infections. OBJECTIVE: The aim of the study is to discuss selected respiratory diseases in children aged 0-18 years hospitalized at the Pediatric Hospital in Bielsko-Biala. MATERIAL AND METHODS: In June 2023, statistical data from the Pediatric Hospital was received regarding the number of hospitalized children aged 0-18 in 2015-2022. This article covers the following respiratory diseases: acute laryngitis, acute pharyngitis, pneumonia, bronchitis and bronchiolitis, bronchial asthma, adenoid hypertrophy and palatine tonsil hypertrophy coexisting with adenoid hypertrophy. Then, a table was prepared illustrating the trends of individual disease entities in the discussed time period. RESULTS: A total of 5,573 hospitalizations were analyzed for the period from 2015-2022. The largest group of children (1,583) were hospitalized due to acute bronchitis and bronchiolitis (28.41%), due to hypertrophy of the adenoid (1,093) and palatine tonsils (1,039), which is 19.6% and 18.64% respectively. The smallest number of children and adolescents were hospitalized due to acute laryngotracheitis (474) and pharyngitis (361), which is 8.51% and 6.47%, respectively, and due to asthma (54), which is 0.97%. It has been observed that from 2017 to 2022 the number of hospitalized patients is constantly increasing due to acute pharyngitis and pneumonia, and from 2018 to 2022 due to acute laryngotracheitis. CONCLUSIONS: In the analyzed Pediatric Hospital in Bielsko-Biala, the number of hospitalized children (from 0 to 18 years of age) due to pharyngitis, laryngotracheitis and pneumonia increased during the COVID-19 pandemic (2020-2022). The number of hospitalized patients due to pneumonia increased by as many as 70 from 2021 (197) to 2022 (267). In the case of hospitalizations for pharyngitis during the COVID-19 period, the number ranged from 46 in 2019 to 69 in 2022. Also in the case of acute laryngotracheitis in the period 2019-2022, the number of hospitalized young patients increases and ranges from 61 to 76. Respiratory tract infections are an important and common health problem for children. The vast majority of respiratory infections are caused by viruses.

CNN-Based Classifier as an Offline Trigger for the CREDO Experiment.

Gamification is known to enhance users' participation in education and research projects that follow the citizen science paradigm. The Cosmic Ray Extremely Distributed Observatory (CREDO) experiment is designed for the large-scale study of various radiation forms that continuously reach the Earth from space, collectively known as cosmic rays. The CREDO Detector app relies on a network of involved users and is now working worldwide across phones and other CMOS sensor-equipped devices. To broaden the user base and activate current users, CREDO extensively uses the gamification solutions like the periodical Particle Hunters Competition. However, the adverse effect of gamification is that the number of artefacts, i.e., signals unrelated to cosmic ray detection or openly related to cheating, substantially increases. To tag the artefacts appearing in the CREDO database we propose the method based on machine learning. The approach involves training the Convolutional Neural Network (CNN) to recognise the morphological difference between signals and artefacts. As a result we obtain the CNN-based trigger which is able to mimic the signal vs. artefact assignments of human annotators as closely as possible. To enhance the method, the input image signal is adaptively thresholded and then transformed using Daubechies wavelets. In this exploratory study, we use wavelet transforms to amplify distinctive image features. As a result, we obtain a very good recognition ratio of almost 99% for both signal and artefacts. The proposed solution allows eliminating the manual supervision of the competition process.