Growth Hormone Treatment Response and Machine Learning‐Based Prediction in Idiopathic GHD and Idiopathic Short Stature (ISS): Analysis of the Korean LG Growth Study
An erratum to this article was published (Clin Endocrinol (Oxf), Nov 2026 ↗)
Authors' conclusion
ML approaches provided limited but clinically meaningful improvements in predicting short-term growth response in iGHD, while offering no clear benefit in ISS.
Study context
- Population
- Children with idiopathic growth hormone deficiency (iGHD) or ISS treated with recombinant human growth hormone (rhGH), ≥1 year of follow-up, Korean LG Growth Study database
- Participants
- 2,215 children
- Exposure
- Machine learning (ML) models vs conventional regression
- iGHDn = 1,877
- ISSn = 338
- Outcome
- 1- and 2-year changes in height SDS (ΔHSDS) and achievement of MPH SDS
- Follow-up
- 1 and 2 years
Methodological detailsnationwide, real-world registry, machine learning prediction models
- Nationwide
- Real-world registry
- Machine learning prediction models
Main finding
As reported in the abstract
iGHD: ensemble ML models modestly outperformed linear regression for predicting 1-year ΔHSDS (R² ≈ 0.19 vs 0.16)
R² ≈ 0.19 vs. 0.16
Observational data: associations, not effects.
Original publication
Growth Hormone Treatment Response and Machine Learning‐Based Prediction in Idiopathic GHD and ISS: Analysis of the Korean LG Growth Study. Clin Endocrinol (Oxf). Published 17 May 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →