Comparative predictive modeling of pediatric spirometry reference equations in Jordanian children: Complex versus simple models
5 affiliations
- 1Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, Amman, Jordan
- 2Department of Clinical Pharmacy, Faculty of Pharmacy, Jordan University of Science and Technology, Irbid, Jordan
- 3Department of Psychology, School of Social Sciences, Humanities and Law, Teesside University, Middlesbrough, United Kingdom
- 4Department of Health Sciences, Faculty of Graduated Studies, Arab American University, Jenin, Palestine
- 5Department of Pharmacy, Faculty of Pharmacy, Al-Quds University, Jerusalem, Palestine
Abstract
Spirometric interpretation relies on reference equations, yet equations developed in one population or age range may not transport. Reference equations use distributional models to account for nonlinear growth, their calibration may differ across populations, it remains uncertain whether machine-learning algorithms improve prediction beyond simpler transformed regression models. This two-phase cross-sectional study compared sex-specific predictive models. Phase 1 used the same 1,576-child derivation dataset used to develop the original Jordanian GAMLSS equation (Al-Qerem equation), allowing comparison with predictive modeling strategies. Phase 2 evaluated equations in a validation sample of 1,007 healthy children aged 6–18 years. Candidate models were evaluated on the scale after back-transformation of log-outcome predictions. Models included GBM for FEV1 in both sexes, GLM for FVC in both sexes, GLM for FEV1/FVC in girls, and GBM for FEV1/FVC in boys.FEV1 and FVC were predicted more accurately than FEV1/FVC, whose explained variance from age and height remained low across model classes and established equations. In external validation, the study model had the lowest mean squared error for female FEV1 and FVC, but did not consistently outperform GLI 2012, GLI 2022, or Al-Qerem equations in boys or for FEV1/FVC. Age-stratified analyses showed elevated FEV1 and FVC below-LLN rates in boys younger than 10 years across the study, Al-Qerem, GLI 2012, and GLI 2022 equations, whereas FEV1/FVC below-LLN proportions were generally closer to nominal values. These findings support comparative predictive modeling as a useful development framework, but do not show superiority of complex machine-learning methods or readiness for clinical deployment without further calibration and external validation. Carefully chosen transformations and calibration were more important than model complexity, and the best models differed by outcome and sex. Author summary: Breathing tests are interpreted by comparing a child’s measured lung function with expected values for children of similar age, sex, and height. Many clinics use international equations, but these equations may not fit every population equally well. We compared simple statistical prediction models and more flexible machine-learning algorithms for Jordanian children, using the same dataset that produced a previous Jordanian reference equation and then testing the equations in a separate group of children. The main finding was practical: more complex algorithms were not consistently better. Carefully chosen transformations and calibration were more important than model complexity, and the best models differed by outcome and sex. Lung volumes were predicted more reliably than the FEV1/FVC ratio, the relationship between the air blown out in the first second and the total forced breath. These results support local validation before adopting reference equations and show that future spirometry software should combine prediction with calibration checks rather than relying only on algorithmic complexity.
Related
- A Hilbert Module Approach to Classical and Quantum Reference Frames
- Event-Triggered Funnel Control for Output Reference Tracking of Unknown Nonlinear Systems
- Oblique Projection Networks (OPN) Reference guide - variants, code, tests, complexity, and the application scope of oblique projections
- Assessing Temporal Dispersion of Time-Varying Channel at 38 GHz for Different Reference Signals
- Mutual Information Optimal Density Control of Linear Systems and Generalized Schrödinger Bridges with Reference Refinement
BibTeX
@article{alqerem2026comparative,
title = {{Comparative predictive modeling of pediatric spirometry reference equations in Jordanian children: Complex versus simple models}},
author = {Walid Al-Qerem and Anan Jarab and Judith Eberhardt and Khalda Smairan and Yousef Mimi and Maher Khdour},
journal = {PLOS Digital Health},
year = {2026},
month = sep,
doi = {10.1371/journal.pdig.0001746},
url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001746},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Comparative predictive modeling of pediatric spirometry reference equations in Jordanian children: Complex versus simple models
AU - Walid Al-Qerem
AU - Anan Jarab
AU - Judith Eberhardt
AU - Khalda Smairan
AU - Yousef Mimi
AU - Maher Khdour
PY - 2026
DA - 2026/09/25
JO - PLOS Digital Health
DO - 10.1371/journal.pdig.0001746
UR - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001746
AB - Spirometric interpretation relies on reference equations, yet equations developed in one population or age range may not transport. Reference equations use distributional models to account for nonlinear growth, their calibration may differ across populations, it remains uncertain whether machine-learning algorithms improve prediction beyond simpler transformed regression models. This two-phase cross-sectional study compared sex-specific predictive models. Phase 1 used the same 1,576-child derivation dataset used to develop the original Jordanian GAMLSS equation (Al-Qerem equation), allowing comparison with predictive modeling strategies. Phase 2 evaluated equations in a validation sample of 1,007 healthy children aged 6–18 years. Candidate models were evaluated on the scale after back-transformation of log-outcome predictions. Models included GBM for FEV1 in both sexes, GLM for FVC in both sexes, GLM for FEV1/FVC in girls, and GBM for FEV1/FVC in boys.FEV1 and FVC were predicted more accurately than FEV1/FVC, whose explained variance from age and height remained low across model classes and established equations. In external validation, the study model had the lowest mean squared error for female FEV1 and FVC, but did not consistently outperform GLI 2012, GLI 2022, or Al-Qerem equations in boys or for FEV1/FVC. Age-stratified analyses showed elevated FEV1 and FVC below-LLN rates in boys younger than 10 years across the study, Al-Qerem, GLI 2012, and GLI 2022 equations, whereas FEV1/FVC below-LLN proportions were generally closer to nominal values. These findings support comparative predictive modeling as a useful development framework, but do not show superiority of complex machine-learning methods or readiness for clinical deployment without further calibration and external validation. Carefully chosen transformations and calibration were more important than model complexity, and the best models differed by outcome and sex. Author summary: Breathing tests are interpreted by comparing a child’s measured lung function with expected values for children of similar age, sex, and height. Many clinics use international equations, but these equations may not fit every population equally well. We compared simple statistical prediction models and more flexible machine-learning algorithms for Jordanian children, using the same dataset that produced a previous Jordanian reference equation and then testing the equations in a separate group of children. The main finding was practical: more complex algorithms were not consistently better. Carefully chosen transformations and calibration were more important than model complexity, and the best models differed by outcome and sex. Lung volumes were predicted more reliably than the FEV1/FVC ratio, the relationship between the air blown out in the first second and the total forced breath. These results support local validation before adopting reference equations and show that future spirometry software should combine prediction with calibration checks rather than relying only on algorithmic complexity.
SN - 2767-3170
ER -