Document Type : Original Paper
Authors
1 1 Department of Statistics, Faculty of Mathematical Sciences, Tarbiat Modares University, Tehran, Islamic Republic of Iran
2 2 Department of Mathematics, Faculty of Mathematics and Computer Science, Kharazmi University, Tehran, Islamic Republic of Iran
Abstract
The objective of this study is to investigate the factors influencing asthma attacks in children under six years old using machine learning (ML) methods. There are many statistical methods for data classification that can be used to classify medical data. But using the data itself as well as a set of different methods in machine learning can provide vast and more comparable results. Hence, this study applied ML approaches to predict asthma and second anoxic tonic seizures due to asthma (ATSA) based on variables such as first ATSA, age, region of residence, parent smoking status, and parents' asthma history. The results revealed that children's age and place of residence significantly affected the duration of asthma attacks, with children living in certain areas of Tehran experiencing shorter intervals between attacks due to high air pollution. Machine learning techniques proved useful in predicting ATSA based on age, gender, living region, parents' smoking status, and asthma history, with the AdaBoost method highlighting the importance of the child's age and living area in predicting ATSA.
Keywords
- The objective of this study is to investigate the factors influencing asthma attacks in children under six years old using machine learning (ML) methods. There are many statistical methods for data classification that can be used to classify medical
- this study applied ML approaches to predict asthma and second anoxic tonic seizures due to asthma (ATSA) based on variables such as first ATSA
- age
- region of residence
- parent smoking status
- and parents' asthma history. The results revealed that children's age and place of residence significantly affected the duration of asthma attacks
- with children living in certain areas of Tehran experiencing shorter intervals between attacks due to high air pollution. Machine learning techniques proved useful in predicting ATSA based on age
- gender
- living region
- parents' smoking status
- and asthma history
- with the AdaBoost method highlighting the importance of the child's age and living area in predicting ATSA
Main Subjects
- Malveaux FJ. The state of childhood asthma: introduction. Pediatrics. 2009;123 Suppl 3:S129–30
- Roemer M. Health care expenditures for the five most common children’s conditions. 2008: estimates for U.S. civilian non institutionalized children, ages 0–17. MEPS statistical brief 349. Rockville, MD: AHRQ; 2011
3. Yunginger JW, Reed CE, O’Connell EJ, Melton 3rd LJ, O’Fallon WM, Silverstein MD. A community-based study of the epidemiology of asthma. Incidence rates, 1964–1983. Am Rev Respir Dis. 1992;146(4):888–94
- Hafkamp-de Groen E, Lingsma HF, Caudri D, Levie D, Wijga A, Koppelman GH, et al. Predicting asthma in preschool children with asthma-like symptoms: validating and updating the PIAMA risk score. J Allergy Clin Immunol. 2013;132(6):1303–10
- Martinez FD. Development of wheezing disorders and asthma in preschool children. Pediatrics. 2002;109(2 Suppl):362–7
- Frey U, von Mutius E. The challenge of managing wheezing in infants. N Engl J Med. 2009;360(20):2130–3
- Haahtela T, Tamminen K, Kava T, Malmberg LP, Rytilä P, Nikander K, et al. Thirteen-year follow-up of early intervention with an inhaled corticosteroid in patients with asthma. J Allergy Clin Immunol. 2009;124(6):1180–5
- Van Wonderen KE, van der Mark LB, Mohrs J, Geskus RB, van der Wal WM, van Aalderen WM, et al. Prediction and treatment of asthma in preschool children at risk: study design and baseline data of a prospective cohort study in general practice (ARCADE). BMC Pulm Med. 2009;9:13
- Li D, Abhadiomhen SE, Zhou D, Shen XJ, Shi L, Cui Y. Asthma prediction via affinity graph enhanced classifier: a machine learning approach based on routine blood biomarkers. Journal of Translational Medicine. 2024 Jan 24;22(1):100.
- Sills MR, Ozkaynak M, Jang H. Predicting hospitalization of pediatric asthma patients in emergency departments using machine learning. Int J Med Inform. 2021; 151: 104468.
- Deliu M, Yavuz TS, Sperrin M, et al. Features of asthma which provide meaningful insights for understanding the disease heterogeneity. Clin Exp Allergy. 2018;48(1):39-47
- Su MW, Lin WC, Tsai CH, et al. Childhood asthma clusters reveal neutrophil-predominant phenotype with distinct gene expression. Allergy. 2018;73(10):2024-2032.
- Fitzpatrick AM, Bacharier LB, Jackson DJ, et al. Heterogeneity of mild to moderate persistent asthma in children: confirmation by latent class analysis and association with 1-year outcomes. J Allergy Clin Immunol Pract. 2020;8(8):2617-2627.e4
- Motarjem, K., Mohammadzadeh, M., and Abyar, A. Bayesian Analysis of Spatial Survival Model with Non-Gaussian Random Effect. 2018.Journal of Mathematical Sciences, 237(5), 692–701.
- Yoav Freund and Robert E. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1):119–139, August 1997
- Friedman, J. Greedy boosting approximation: agradient boosting machine.Ann.Stat. 2021; 29, 1189–1232.
)