Predicting the Risk of Asthma Development in Youth Using Machine Learning Models DOI Creative Commons

Matthew Xie,

Chenliang Xu

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: June 26, 2024

Asthma is a chronic respiratory disease characterized by wheezing and difficulty breathing, which disproportionally affects 4.7 million children in the U.S. Currently, there lack of asthma predictive models for youth with good performance. This study aims to build machine learning better predict development using easily accessible national survey data. We analyzed cross-sectional combined 2021 2022 National Health Interview Survey (NHIS) data from 9,716 subjects their corresponding parent information. built several various sampling techniques (under- or over-sampling) prediction youth, including XGBoost, Neural Networks, Random Forest, Support Vector Machine (SVM), Logistic Regression. examined associations potential risk factors identified both Forest Least Absolute Shrinkage Selection Operator (LASSO) youth. Between different techniques, undersampling major class (subjects without asthma) yielded best results terms area under curve (AUC) F1 scores models. The Regression performed under-sampled data, yielding an AUC score 0.7654 0.3452. In addition, we have additional important associated such as low family poverty ratio parents ever had asthma. successfully model will be early screening detection

Language: Английский

Research Progress in the Understanding and Treatment of Pediatric Bronchial Asthma in Traditional Chinese and Western Medicine DOI

梦玲 王

Nursing Science, Journal Year: 2025, Volume and Issue: 14(02), P. 235 - 242

Published: Jan. 1, 2025

Language: Английский

Citations

0
The association between COVID-19 vaccine/infection and new-onset asthma in children - based on the global TriNetX database DOI Creative Commons
C.-F.J. Yang, Yu‐Hsiang Shih, Chia-Chi Lung

et al.

Infection, Journal Year: 2024, Volume and Issue: unknown

Published: June 21, 2024

The COVID-19 pandemic has underscored the importance of its potential long-term health effects, including link to new-onset asthma in children. Asthma significantly impacts children's health, causing adverse outcomes and increased absenteeism. Emerging evidence suggests a association between infection higher rates adults, raising concerns about impact on respiratory health.

Language: Английский

Citations

1
Treatment of Severe Asthma: Case Report of Fast Action of Mepolizumab in a Patient with Recent SARS-CoV-2 Infection DOI Creative Commons
Cristiana Indolfi, Giulio Dinardo, Angela Klain

et al.

Life, Journal Year: 2024, Volume and Issue: 14(9), P. 1063 - 1063

Published: Aug. 25, 2024

Asthma is one of the most common chronic inflammatory diseases childhood with a heterogeneous impact on health and quality life. Mepolizumab an antagonist interleukin-5, indicated as adjunct therapy for severe refractory eosinophilic asthma in adolescents children aged >6 years old. We present case 9 year-old boy who experienced several asthmatic exacerbations following SARS-CoV-2 infection, necessitating short-acting bronchodilators, oral corticosteroids, hospitalization. follow patient using validated questionnaires evaluation control: Children Control Test, Questionnaire, respiratory function tests, exhaled nitric oxide fraction. After 12 weeks from start mepolizumab, we found significant improvements lung function, reduction degree bronchial inflammation, No have been reported since initiation treatment mepolizumab. Respiratory infections, such those related to SARS-CoV-2, represent risk factor patients moderate forms asthma. In our experience, new episodes exacerbation, mepolizumab has allowed us improve control enhance life first doses. Although showed promise this child during results single cannot be generalized. Further studies are needed confirm its safety effectiveness.

Language: Английский

Citations

1
Predicting the Risk of Asthma Development in Youth Using Machine Learning Models DOI Creative Commons

Matthew Xie,

Chenliang Xu

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: June 26, 2024

Asthma is a chronic respiratory disease characterized by wheezing and difficulty breathing, which disproportionally affects 4.7 million children in the U.S. Currently, there lack of asthma predictive models for youth with good performance. This study aims to build machine learning better predict development using easily accessible national survey data. We analyzed cross-sectional combined 2021 2022 National Health Interview Survey (NHIS) data from 9,716 subjects their corresponding parent information. built several various sampling techniques (under- or over-sampling) prediction youth, including XGBoost, Neural Networks, Random Forest, Support Vector Machine (SVM), Logistic Regression. examined associations potential risk factors identified both Forest Least Absolute Shrinkage Selection Operator (LASSO) youth. Between different techniques, undersampling major class (subjects without asthma) yielded best results terms area under curve (AUC) F1 scores models. The Regression performed under-sampled data, yielding an AUC score 0.7654 0.3452. In addition, we have additional important associated such as low family poverty ratio parents ever had asthma. successfully model will be early screening detection

Language: Английский

Citations

0