Asthma Disease Prediction Using Regression Tree Method
Abstract
Asthma is a common, chronic inflammatory disorder of the airways that affects an estimated 339 million people worldwide. Diagnostic approaches for asthma usually fail in clinical practice, partly owing to the multifactorial spectrum of the disease. This study reveals a new diagnostic algorithm where regression trees along with entropy-based subset selection(E-SS) are combined for more reliable and accurate asthma diagnosis. E-SS helps to filter out the most important features from high-dimensional datasets and avoids possible overfitting of the rate up to 91.304%, which is higher than other algorithms like Bayesian Network of 83.3%. The strength of this model is that it can capture complex (non-linear) interactions efficiently between the variables and therefore would be efficient, in particular for asthma prediction. Moreover, it is a more patient-centered methodology where risk factors of each individual are targeted. The model could aid in the diagnosis and treatment of other chronic diseases outside asthma, further alleviating global health care systems.
References
[2] M. A, L, Hwang, “Environmental and LifeStyle Factors in Asthma,” J. Asthma Res., vol. 58, no. 3, pp. 231–244, 2023.
[3] S. A, M, P and R. J, Brown, “Pathogenesis of Asthma: An Overview,” Allergy Clin. Immunol. Rev., vol. 58, no. 3, pp. 150–165, 2022.
[4] S. Jhonson, “Asthma in Low and Middle-Income Countries: Challenge and Solutions,” Glob. Heal. J., vol. 10, no. 4, pp. 407–420, 2021.
[5] J. L, Ramirez and C. E, Thompson, “Economic Burden of Asthma: A Comprehensive Review,” Health Econ. Rev., vol. 13, no. 1, pp. 75–85, 2023.
[6] L. G, Lee, “Regression Tree Analysis: Techniques and Applications,” Stat. Methods Med. Res., vol. 30, no. 1, pp. 12–25, 2022.
[7] E. K, White and M. S, Zhang, “Using Regression Trees to Understand Asthma Risk Factors,” J. Clin. Epidemology, vol. 89, pp. 45–55, 2024.
[8] T. C, Miller, “Identifying Asthma Phenotypes with Regression Trees,” Am. J. Respir. Crit. Care Med., vol. 207, no. 4, pp. 484–493, 2023.
[9] B. N, Kim, “Personalized Treatment Plans for Asthma: The Role of Regression Trees,” Eur. Respir. Rev., vol. 32, no. 167, pp. 220–230, 2023.
[10] R. J, Allen and M. P, Davis, “Biomarkers and Environmental Triggers of Severe Asthma,” Clin. Immunol., vol. 208, pp. 13–21, 2022.
[11] H. J, Stevens, “Handling High-Dimensional Data in Asthma Research,” J. Comput. Biol., vol. 30, no. 5, pp. 789–800, 2024.
[12] K. E, Robinson, “Integrating Genetic and Environmental Data in Asthma,” Nat. Rev. Genet., vol. 25, no. 8, pp. 532–546, 2023.
[13] P. J, Patel and R. T, Kumar, “Advancements in Asthma Research with Regression Trees,” Med. Data Anal., vol. 14, no. 2, pp. 102–115, 2024.
[14] L. H, Zhang, “Machine Learning in Healthcare: Applications to Asthma,” J. Biomed. Inform., vol. 112, pp. 103–116, 2024.
[15] N. P, Clark, “Transforming Asthma Management with Personalized Approach,” Lancet Respir. Med., vol. 12, no. 7, pp. 678–690, 2023.
[16] Y. Zhang and X. Zhao, “A comprehensive review of ensmble-based feature selection methods,” J. Mach. Learn., vol. 20, no. 1, pp. 1–25, 2019.
[17] F. Smarra and A. D. Innocenzo, “Learning methods for structural damage detection via entropy-based sensors selection,” no. September 2021, pp. 6035–6067, 2022, doi: 10.1002/rnc.6124.
[18] T. Jimmy, “Identifikasi Parameter Kualitas Bahan Pangan dengan Metode Entropy-Based Subset Selection (E-SS) (Studi Kasus: Minuman Anggur),” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 1, pp. 47–54, 2024.
[19] P. He et al., “Early prediction of pediatric asthma in the Canadian Healthy Infant Longitudinal Development ( CHILD ) birth cohort using machine learning,” no. May 2023, 2024, doi: 10.1038/s41390-023-02988-2.
Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.