Growth Hormone Treatment Response and Machine Learning-Based Prediction in Idiopathic GHD and ISS: Analysis of the Korean LG Growth Study.

What Was Tested

This observational study looks at Exogenous HGH, sermorelin & older GHRPs (why they're passed over).

Individual responses to recombinant human growth hormone (rhGH) therapy vary widely among children with idiopathic growth hormone deficiency (iGHD) and idiopathic short stature (ISS), making accurate prediction of treatment outcomes clinically important.

This study aimed to develop and compare machine learning (ML)-based and conventional statistical models to predict short-term growth response and mid-parental height (MPH) attainment following rhGH therapy in iGHD and ISS patients.

Who Took Part

The study group was 2215 children.

The age groups tagged for this paper are children and teenagers, both men and women.

A total of 2215 children (1877 with iGHD and 338 with ISS) treated with rhGH were identified from the Korean LG Growth Study database.

All included patients had at least 1 year of follow-up with available clinical data.

How the Study Was Run

Retrospective observational cohort study using a nationwide, real-world registry.

Primary outcomes were 1- and 2-year changes in height SDS (ΔHSDS) and achievement of MPH SDS.

Predictive models included multiple linear regression, logistic regression, Random Forest, eXtreme Gradient Boosting, and Elastic Net.

Model performance was evaluated using R², error metrics and area under the receiver operating characteristic curve.

Model interpretability was assessed using SHAP values.

What Was Measured

PubMed files the paper under topics including Body Height, Boosting Machine Learning Algorithms, Classification Algorithms, Dwarfism, Pituitary, Growth Disorders, Human Growth Hormone and Predictive Learning Models.

What This Means in Plain Language

This is an observational study of Exogenous HGH, sermorelin & older GHRPs (why they're passed over) in 2215 children.

With several hundred people or more, it is a fairly large study for this kind of research.

The abstract goes on to report its results in about 5 sentences; this page does not restate them, so read the paper for the findings and their limits.

The publication is from 2026 (Clinical endocrinology), a journal based in England.

More context: the Exogenous HGH, sermorelin & older GHRPs (why they're passed over) compound page, all human trials.