AN ENSEMBLE ASTHMA PREDICTION MODEL FOR EARLY DETECTION OF ASTHMA IN CHILDREN USING STACKING AND BLENDING

Raphael Ekpo; Ambrose  Azeta; Olukunle Adebayo; Akinrinlola Akinfolajimi; Ojo Aderibigbe; Bassey Ewa

doi:10.4314/njt.v44i3.9

Authors

R. H. Ekpo Lagos State University of Science and Technology
A.A. Azeta Namibia University of Science and Technology, Namibia
O. J. Adebayo Crawford University, Nigeria
A. I. Akinfolajimi Lagos State University of Science and Technology, Nigeria
O.S Aderibigbe Lagos State University of Science and Technology, Nigeria
B. Ewa Landmark Hospital, Km 2 Itokin Rd, Ikorodu Lagos State, Nigeria

DOI:

https://doi.org/10.4314/njt.v44i3.9

Keywords:

Asthma Prediction model, Asthma in Children, Blended Stacking, Ensemble Model, Grid Optimization

Abstract

Asthma disease is a serious worldwide health challenge affecting every age bracket, particularly amongst children. Its widespread has extended to numerous countries. Childhood asthma remains underdiagnosed and insufficiently treated in Nigeria, affecting more than 20,000 children, including adults. It was discovered that there is a notable incidence of wheezing, with an approximation of 13 million or more individuals suffering from asthma. The objective of this study is to build an ensemble asthma prediction model for early detection of asthma in children using stacking and blending. The methodology involved combining several techniques, including Relief feature selection, grid search optimization, and a blended stacking ensemble model. This study used the Nigerian dataset comprising the Hospital Record System (HRS) of six Nigerian hospitals and the administrative data from patients' history. The findings indicate that the proposed model attained a notably high precision of 96%, a recall rate of 94%, and an F1-score of 95% for the non-asthmatic category (0). Furthermore, it achieved a precision of 96%, a recall of 97%, and an F1-score of 97% for the asthmatic positive category (1). The study concludes that the model demonstrates effective capability in distinguishing between asthmatic and non-asthmatic patients. Consequently, this could contribute to improved patient outcomes and enhanced healthcare delivery systems. This work proposes further exploration, such as external validation, incorporating more diverse datasets and enhancing interpretability or explainability of the model.

Author Biographies

A.A. Azeta, Namibia University of Science and Technology, Namibia

Department of Software Engineering, Namibia University of Science and Technology, Namibia
O. J. Adebayo, Crawford University, Nigeria

Department of Computer and Mathematical Sciences
A. I. Akinfolajimi, Lagos State University of Science and Technology, Nigeria

Department of Computer Sciences
O.S Aderibigbe, Lagos State University of Science and Technology, Nigeria

Department of Computer Sciences

References

[1] Ekpo, R. H., Osamor, V. C., Azeta, A. A., Ikeakanam, E. and Amos, B. O. “Machine learning classification approach for asthma prediction models in children,” Health and Technology, vol. 13, no. 1, pp. 1–10, Jan. 2023, doi: 10.1007/s12553-023-00732-8.

[2] Reddel, H. K, Leonard, B. B, Batman, D. et al. “Global Initiative for Asthma Strategy 2021: Executive Summary and Rationale for Key changes,” American Journal of Respiratory and Critical Care Medicine, vol. 205, no. 1, pp. 17–35, Oct. 2021, doi: 10.1164/rccm.202109-2205pp.

[3] “The Global Asthma Report,” Global Asthma Network, 2022, [Online]. Available: http://www.globalasthmareport.org/

[4] Akinso, O.,Adhikari, A., Yin, J., Chopak-Foss J. and Shah G.“Childhood Asthma-Management Practices in Rural Nigeria: Exploring the knowledge, attitude, and practice of caregivers in Oyo State,” Children, vol. 10, no. 6, p. 1043, Jun. 2023, doi: 10.3390/children10061043.

[5] Onyedum, C. C., Ukwaja, K. N., Desalu O. O. and Ezeudo C. “Challenges in the management of bronchial asthma among adults in Nigeria: a Systematic review,” Annals of Medical and Health Sciences Research, 3(3), 324-329., 2013.

[6] Patel, D., Hall, G. L., Broadhurst, D., Smith, A., Schultz, A.and Foong, R. E. “Does machine learning have a role in the prediction of asthma in children?,” Paediatric Respiratory Reviews, vol. 41, pp. 51–60, Jun. 2021, doi: 10.1016/j.prrv.2021.06.002

[7] Razavi-Termeh, S. V., Sadeghi-Niaraki, A. and Choi, S. M. “Asthma-prone areas modeling using a machine learning model,” Scientific Reports, vol. 11, no. 1, Jan. 2021, doi: 10.1038/s41598-021-81147-1.

[8] De Jesus Romero-Tapia, S., Becerril-Negrete,J. R., Castro-Rodriguez,J . A and Del-Río-Navarro, B. E. “Early prediction of asthma,” Journal of Clinical Medicine, vol. 12, no. 16, p. 5404, Aug. 2023, doi: 10.3390/jcm12165404

[9] Sills, M. R., Ozkaynak, M. and Jang, H. “Predicting hospitalization of pediatric asthma patients in emergency departments using machine learning,” International Journal of Medical Informatics.

[10] Cilluffo, G., Fasola, S., Ferrante, G., Licari, A., Marseglia, G.R., Albarelli, A., Marseglia, G.L. and La Grutta, S. “Machine learning: A modern approach to pediatric asthma,” Pediatric Allergy and Immunology, vol. 33, no. S27, pp. 34–37, Jan. 2022, doi: 10.1111/pai.13624

[11] Zein, J.G., Wu, C.P., Attaway, A.H., Zhang, P. and Nazha, A. “Novel machine learning can predict acute asthma exacerbation,” CHEST Journal, vol. 159, no. 5, pp. 1747–1757, Jan. 2021, doi: 10.1016/j.chest.2020.12.051.

[12] Filipow, N., Main, E., Sebire, N.J., Booth, J., Taylor, A.M., Davies, G. and Stanojevic, S

“Implementation of prognostic machine learning algorithms in paediatric chronic respiratory conditions: a scoping review,” BMJ Open Respiratory Research, vol. 9, no. 1, p. e001165, Mar. 2022, doi: 10.1136/bmjresp-2021-001165.

[13] Jeddi, Z., Gryech, I., Ghogho, M., El Hammoumi, M. and Mahraoui, C. .“Machine learning for predicting the risk for childhood asthma using prenatal, perinatal, postnatal and environmental factors,” Healthcare, vol. 9, no. 11, p. 1464, Oct. 2021, doi: 10.3390/healthcare9111464.

[14] Spyroglou, I.I., Spöck, G., Chatzimichail, E.A., Rigas, A.G. and Paraskakis, E.N.

“A Bayesian Logistic Regression approach in Asthma Persistence Prediction,” Epidemiology Biostatistics and Public Health, vol. 15, no. 1, Feb. 2022, doi: 10.2427/12777.

[15] Hogan, A.H., Brimacombe, M., Mosha, M. and Flores, G.“Comparing artificial intelligence and traditional methods to identify factors associated with pediatric asthma readmission,” Academic Pediatrics, vol. 22, no. 1, pp. 55–61, Jul. 2021, doi: 10.1016/j.acap.2021.07.015

[16] Bose, S., Kenyon, C.C.and Masino, A.J. “Personalized prediction of early childhood asthma persistence: A machine learning approach,” PLoS ONE, vol. 16, no. 3, p. e0247784, Mar. 2021, doi: 10.1371/journal.pone.0247784

[17] Wang, X., Wang, Z., Pengetnze, Y.M., Lachman, B.S. and Chowdhry, V. “Deep learning models to predict pediatric asthma emergency department visits,” arXiv (Cornell University), Jan. 2019, doi: 10.48550/arxiv.1907.11195.

[18] Kim, D., Cho, S., Tamil, L., Song, D.J. and Seo, S. “Predicting Asthma attacks: Effects of indoor PM concentrations on peak expiratory flow rates of asthmatic children,” IEEE Access, vol. 8, pp. 8791–8797, Dec. 2019, doi: 10.1109/access.2019.2960551.

[19] Goto, T., Camargo, C.A., Faridi, M.K., Freishtat, R.J. and Hasegawa, K. “Machine learning–based prediction of clinical outcomes for children during emergency department triage.,” JAMA Network Open, doi: 10.1001/jamanetworkopen.2018

[20] Lovrić, M., Banić, I., Lacić, E., Pavlović, K., Kern, R. and Turkalj, M. .“Predicting Treatment Outcomes Using Explainable Machine Learning in Children with Asthma,” Children, vol. 8, no. 5, p. 376, May 2021, doi: 10.3390/children8050376

[21] Urbanowicz, R.J., Meeker, M., La Cava, W., Olson, R.S. and Moore, J.H. “Relief-based feature selection: Introduction and review,” Journal of Biomedical Informatics, vol. 85, pp. 189–203, Jul. 2018, doi: 10.1016/j.jbi.2018.07.014.

[22] Noroozi, Z., Orooji, A. and Erfannia, L. “Analyzing the impact of feature selection methods on machine learning algorithms for heart disease prediction,” Scientific Reports, vol. 13, no. 1, Dec. 2023, doi: 10.1038/s41598-023-49962-w.

[23] Belyadi, H. and Haghighat, A. “Machine learning guide for oil and gas using Python: A step-by-step breakdown with data, algorithms, codes, and applications. Supervised Learning Gulf Professional Publishing. https://doi.org/10.1016/B978-0-12-821929-4.00004-4.

[24] Emanet, N., Öz, H.R., Bayram, N. and Delen, D. , “A comparative analysis of machine learning methods for classification type decision problems in healthcare,” Decision Analytics, vol. 1, no. 1, Feb. 2014, doi: 10.1186/2193-8636-1-6.

[25] Nandom, S.S., Abe, G.T. and Gambo, I. P. “Application of random forest and hierarchical clustering models for crop and fertilizer recommendation to farmers,” Nigerian Journal of Technology, vol. 44, no. 1, pp. 114–122, May 2025, doi: https://doi.org/10.4314/njt.v44i1.13.

[26] Yao, D., Yang, J. and Zhan, X. “A novel method for disease prediction: hybrid of random forest and multivariate adaptive regression SPlines,” Journal of Computers, vol. 8, no. 1, Jan. 2013, doi: 10.4304/jcp.8.1.170-177.

[27] Chaudhary, A., Kolhe, S. and Kamal, R. “An improved random forest classifier for multi-class classification,” Information Processing in Agriculture, vol. 3, no. 4, pp. 215–222, Sep. 2016, doi: 10.1016/j.inpa.2016.08.002

[28] Ma, L. and Fan, S. .“CURE-SMOTE algorithm and hybrid algorithm for feature selection and parameter optimization based on random forests,” BMC Bioinformatics, vol. 18, no. 1, Mar. 2017, doi: 10.1186/s12859-017-1578-z.

[29] Simbolon, I.N. and Naibaho, R. “Influence of relief feature selection on random forest and support vector machine classification algorithm,” International Workshop on Big Data and Information Security (IWBIS, pp. 27–32, Oct. 2022, doi: 10.1109/iwbis56557.2022.9924782.