Interpretable Machine Learning for Predicting Suboptimal 12-Month Growth Response to Recombinant Human…

AI / informaticsDiagnostics (Basel, Switzerland)· Jul 2026

Interpretable Machine Learning for Predicting Suboptimal 12-Month Growth Response to Recombinant Human Growth Hormone in Children with Idiopathic Short Stature: A Dual-Center External Validation Study.

Chuanyu Yang, Yifeng Shao, Chengyang Jiang … Lin Wang

Pediatric Endocrinology & GrowthAI / informaticsPrognosisQ2IF 4.4

Ensemble machine-learning model predicted suboptimal growth hormone response in external validation

Interpretable Machine Learning for Predicting Suboptimal 12-Month Growth Response to Recombinant Human Growth Hormone in Children with Idiopathic Short Stature: A Dual-Center External Validation Study.

Chuanyu Yang … Lin Wang

Diagnostics (Basel, Switzerland) · Jul 2026 · Q2 in General Medicine

Background

Individual responses to recombinant human growth hormone (rhGH) therapy in children with idiopathic short stature (idiopathic short stature) vary substantially, limiting pretreatment decision-making.

Purpose

This study aimed to develop and externally validate an interpretable machine learning model for predicting suboptimal 12-month growth response to rhGH therapy.

Methods

In this retrospective dual-center study, 901 children from Center 1 were used for model development and internal testing, and 51 children from Center 2 formed an independent external validation cohort.

n = 901 children

Results

correctly ranks growth response even in a new hospital's patients

Internal test set

0.927AUC

External validation

0.897AUC

More results

SHAP analysis identified luteinizing hormone, body mass index, TW3 RUS bone age, and insulin-like growth factor 1 as the leading contributors to predicted suboptimal-response risk.

“

Conclusion · 1 of 2

An interpretable ensemble machine learning model based on routinely available pretreatment data can predict suboptimal short-term rhGH response in children with idiopathic short stature and may support individualized risk stratification in pediatric endocrine practice.

Conclusion · 2 of 2

Clinical trial registration was not required because this was a retrospective analysis.

Interpretable Machine Learning for Predicting Suboptimal 12-Month Growth Response to Recombinant Human Growth Hormone in Children with Idiopathic Short Stature: A Dual-Center External Validation Study.

Interpretable Machine Learning for Predicting Suboptimal 12-Month Growth Response to Recombinant Human Growth Hormone in Children with Idiopathic Short Stature: A Dual-Center External Validation Study.

Related papers