Interpretable Machine Learning for Predicting Suboptimal 12-Month Growth Response to Recombinant Human Growth Hormone
Chuanyu Yang1,2, Yifeng Shao1,3, Chengyang Jiang1,3
1Capital Institute of Pediatrics, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100020, China.
Insights
A new machine learning model accurately predicts poor response to recombinant human growth hormone (rhGH) therapy in children with idiopathic short stature (ISS). This tool uses routine data to identify patients needing alternative treatments, improving growth hormone therapy outcomes.
Area of Science:
- Pediatric Endocrinology
- Machine Learning in Medicine
- Growth Hormone Therapy
Background:
- Individual responses to recombinant human growth hormone (rhGH) therapy for idiopathic short stature (ISS) are highly variable.
- This variability hinders effective pretreatment decision-making for children with ISS.
- Predicting treatment response is crucial for optimizing pediatric endocrine care.
Purpose of the Study:
- To develop and externally validate an interpretable machine learning model.
- The model aims to predict suboptimal 12-month growth response to rhGH therapy in children with ISS.
- To enhance individualized risk stratification in clinical practice.
Main Methods:
- Retrospective dual-center study using 901 children for development and 51 for external validation.
- A soft-voting ensemble classifier was built using baseline demographic, laboratory, hormonal, radiographic, and family history data.
- SHapley Additive exPlanations (SHAP) were used for model interpretability.
Main Results:
- The ensemble model achieved an AUC of 0.927 in internal testing and 0.897 in external validation.
- Key predictors for suboptimal response included luteinizing hormone, body mass index, TW3 RUS bone age, and insulin-like growth factor 1.
- The model demonstrated strong discrimination and robust performance.
Conclusions:
- An interpretable machine learning model using pretreatment data can predict suboptimal rhGH response in children with ISS.
- This predictive model supports individualized risk stratification in pediatric endocrine practice.
- Routine data can be leveraged for better treatment outcome prediction.
Abstract:
Background/Objectives: Individual responses to recombinant human growth hormone (rhGH) therapy in children with idiopathic short stature (ISS) vary substantially, limiting pretreatment decision-making. 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. Routinely collected baseline demographic, laboratory, hormonal, radiographic, and family-history variables were used to develop multiple machine learning models. A soft-voting ensemble classifier was constructed and interpreted using SHapley Additive exPlanations (SHAP). The primary outcome was suboptimal growth response, defined as failure to achieve a height gain of at least 0.5 standard deviation score after 12 months of treatment. Results: The optimized ensemble model showed strong discrimination in the internal test set, with an area under the receiver operating characteristic curve of 0.927, and maintained robust performance in the external validation cohort, with an AUC of 0.897. 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. Conclusions: An interpretable ensemble machine learning model based on routinely available pretreatment data can predict suboptimal short-term rhGH response in children with ISS and may support individualized risk stratification in pediatric endocrine practice. Clinical trial registration was not required because this was a retrospective analysis.
