Interpretable machine learning identifies predictors of IGF-1 during growth hormone therapy in boys
4 affiliations
- 1Department of Pediatrics, Göteborg Pediatric Growth Research Center (GP-GRC), Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg
- 2Department of Pediatric Endocrinology, Sahlgrenska University Hospital, Queen Silvia Children’s Hospital
- 3AI Competence Center, Sahlgrenska University Hospital
- 4Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital
Abstract
Objectives: Insulin-like growth factor-1 (IGF-1) is widely used to guide growth hormone (GH) therapy, yet its predictors during the maintenance phase and puberty remain incompletely understood. We aimed to predict IGF-1 standard deviation scores (SDS) at 3 and 12 months in GH-treated boys and to identify key predictors of IGF-1 dynamics using interpretable modeling approaches.
Methods: Data from 72 boys with growth hormone deficiency or idiopathic short stature from a previous Swedish clinical trial were analyzed using early-life characteristics, GH treatment variables, and puberty-related measures. Linear regression, Elastic Net regression, and explainable boosting machine (EBM) models were evaluated with nested five-fold patient-grouped cross-validation. Performance estimates were patient-balanced, with 95% confidence intervals based on 2,000 patient-cluster bootstrap resamples.
Results: Elastic Net had the highest point estimates at 3 months, but confidence intervals did not establish a difference between the primary models. No clear differences between models were found at 12 months. Current IGF-1 SDS was the most prominent predictive feature, while additional treatment- and puberty-related variables were also selected across cross-validation models.
Conclusion: Interpretable modeling approaches provided moderate predictive performance for future IGF-1 SDS during the maintenance phase and puberty. The findings indicate that prediction is informed by current IGF-1 SDS together with additional clinical variables, but further validation in independent cohorts is required before clinical application.
Related
- Explainable machine learning identifies predictors for postural instability and cognitive impairment in early Parkinsons Disease
- Systemic immune dysregulation and local barrier failure as predictors of septic shock in acute appendicitis: a large-scale multicenter interpretable machine learning study
- Sex-specific predictors of lower-limb strength: an interpretable machine learning analysis of anthropometric and body composition measures
- Cross-System Meta-Analysis of Machine Learning Predictors Identifies Value-Specific Risk Drivers and Interactions Underlying Acute Kidney Injury
- Scalable Causal-Interpretable Machine Learning for Cancer Prescreening Using Electronic Health Records
BibTeX
@article{ly2026interpretable,
title = {{Interpretable machine learning identifies predictors of IGF-1 during growth hormone therapy in boys}},
author = {Helena-Jamin Ly and Juulia T. Suvilehto and Beatrice Skyman and Carina Ankarberg-Lindgren and Hans Fors and Jesper Havsol and Jovanna Dahlgren},
journal = {Frontiers in Endocrinology},
year = {2026},
month = oct,
doi = {10.3389/fendo.2026.1873245},
url = {https://www.frontiersin.org/articles/10.3389/fendo.2026.1873245/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Interpretable machine learning identifies predictors of IGF-1 during growth hormone therapy in boys
AU - Helena-Jamin Ly
AU - Juulia T. Suvilehto
AU - Beatrice Skyman
AU - Carina Ankarberg-Lindgren
AU - Hans Fors
AU - Jesper Havsol
AU - Jovanna Dahlgren
PY - 2026
DA - 2026/10/16
JO - Frontiers in Endocrinology
DO - 10.3389/fendo.2026.1873245
UR - https://www.frontiersin.org/articles/10.3389/fendo.2026.1873245/full
AB - Objectives: Insulin-like growth factor-1 (IGF-1) is widely used to guide growth hormone (GH) therapy, yet its predictors during the maintenance phase and puberty remain incompletely understood. We aimed to predict IGF-1 standard deviation scores (SDS) at 3 and 12 months in GH-treated boys and to identify key predictors of IGF-1 dynamics using interpretable modeling approaches. Methods: Data from 72 boys with growth hormone deficiency or idiopathic short stature from a previous Swedish clinical trial were analyzed using early-life characteristics, GH treatment variables, and puberty-related measures. Linear regression, Elastic Net regression, and explainable boosting machine (EBM) models were evaluated with nested five-fold patient-grouped cross-validation. Performance estimates were patient-balanced, with 95% confidence intervals based on 2,000 patient-cluster bootstrap resamples. Results: Elastic Net had the highest point estimates at 3 months, but confidence intervals did not establish a difference between the primary models. No clear differences between models were found at 12 months. Current IGF-1 SDS was the most prominent predictive feature, while additional treatment- and puberty-related variables were also selected across cross-validation models. Conclusion: Interpretable modeling approaches provided moderate predictive performance for future IGF-1 SDS during the maintenance phase and puberty. The findings indicate that prediction is informed by current IGF-1 SDS together with additional clinical variables, but further validation in independent cohorts is required before clinical application.
SN - 1664-2392
ER -