Academic Journal
Growth Hormone Treatment Response and Machine Learning-Based Prediction in Idiopathic GHD and ISS: Analysis of the Korean LG Growth Study.
| Τίτλος: | Growth Hormone Treatment Response and Machine Learning-Based Prediction in Idiopathic GHD and ISS: Analysis of the Korean LG Growth Study. |
|---|---|
| Συγγραφείς: | Park J; Department of Pediatrics, Inha University Hospital, Inha University College of Medicine, Incheon, South Korea., Joo EY; Department of Pediatrics, Inha University Hospital, Inha University College of Medicine, Incheon, South Korea., Kim SJ; Department of Pediatrics, Inha University Hospital, Inha University College of Medicine, Incheon, South Korea., Yoo MJ; Department of Pediatrics, Inha University Hospital, Inha University College of Medicine, Incheon, South Korea., Lee JE; Department of Pediatrics, Inha University Hospital, Inha University College of Medicine, Incheon, South Korea. |
| Πηγή: | Clinical endocrinology [Clin Endocrinol (Oxf)] 2026 Sep; Vol. 105 (3), pp. 322-330. Date of Electronic Publication: 2026 May 17. |
| Τύπος έκδοσης: | Journal Article; Observational Study |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Blackwell Publishing Country of Publication: England NLM ID: 0346653 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1365-2265 (Electronic) Linking ISSN: 03000664 NLM ISO Abbreviation: Clin Endocrinol (Oxf) Subsets: MEDLINE |
| Imprint Name(s): | Publication: <2003->: Oxford : Blackwell Publishing Original Publication: Oxford, Blackwell Scientific Publications. |
| Ιατρικοί όροι (MeSH): | Dwarfism, Pituitary*/drug therapy , Growth Disorders*/drug therapy , Human Growth Hormone*/therapeutic use , Human Growth Hormone*/deficiency , Boosting Machine Learning Algorithms*, Body Height/drug effects ; Adolescent ; Child ; Female ; Humans ; Male ; Classification Algorithms ; Predictive Learning Models ; Republic of Korea ; Retrospective Studies ; Treatment Outcome |
| Περίληψη: | Objective: 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. Design: Retrospective observational cohort study using a nationwide, real-world registry. Patients: 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. Measurements: 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. Results: In the iGHD group, ensemble ML models modestly outperformed linear regression for predicting 1-year ΔHSDS (R² ≈ 0.19 vs. 0.16), but predictive performance declined at 2 years across all models. Prediction of MPH attainment showed high specificity but very low sensitivity at 1 year, with no clear advantage of ML over logistic regression. In ISS patients, all models demonstrated poor predictive performance for both ΔHSDS and MPH attainment, reflecting substantial clinical heterogeneity. Conclusions: ML approaches provided limited but clinically meaningful improvements in predicting short-term growth response in iGHD, while offering no clear benefit in ISS. These findings highlight both the potential and limitations of ML models based solely on routine clinical variables and underscore the need for integrating multimodal data to improve growth prediction, particularly in heterogeneous ISS populations. (© 2026 The Author(s). Clinical Endocrinology published by John Wiley & Sons Ltd.) |
| Σχόλια: | Erratum in: Clin Endocrinol (Oxf). 2026 Sep 6. doi: 10.1111/cen.70204.. (PMID: 42702854) |
| References: | J Clin Res Pediatr Endocrinol. 2020 Oct 2;13(2):124-135. (PMID: 33006554) Endocrine. 2019 Dec;66(3):614-621. (PMID: 31423546) Front Med (Lausanne). 2025 Aug 06;12:1577396. (PMID: 40842547) J Korean Med Sci. 2020 May 18;35(19):e151. (PMID: 32419399) Ann Pediatr Endocrinol Metab. 2018 Mar;23(1):43-50. (PMID: 29609449) Ann Pediatr Endocrinol Metab. 2024 Apr;29(2):95-101. (PMID: 37946439) PLoS One. 2019 May 16;14(5):e0216927. (PMID: 31095622) Horm Res Paediatr. 2018;90(3):190-195. (PMID: 30269125) J Clin Epidemiol. 2022 Feb;142:218-229. (PMID: 34798287) Front Endocrinol (Lausanne). 2022 Oct 05;13:999077. (PMID: 36277722) BMC Med Res Methodol. 2024 Aug 28;24(1):188. (PMID: 39198744) Horm Res Paediatr. 2026;99(3):448-460. (PMID: 39571543) BMC Endocr Disord. 2025 May 12;25(1):129. (PMID: 40355909) J Pediatr Endocrinol Metab. 2020 Jan 28;33(1):71-78. (PMID: 31811805) Curr Opin Pediatr. 2000 Aug;12(4):400-4. (PMID: 10943824) Front Endocrinol (Lausanne). 2021 Dec 10;12:781044. (PMID: 34956092) Front Endocrinol (Lausanne). 2025 Oct 15;16:1628072. (PMID: 41169468) Exp Clin Endocrinol Diabetes. 2025 Jan;133(1):34-39. (PMID: 39821899) Front Endocrinol (Lausanne). 2021 Sep 24;12:737947. (PMID: 34630332) J Endocr Soc. 2023 Feb 16;7(5):bvad026. (PMID: 36936713) Endocr Connect. 2022 Sep 02;11(10):. (PMID: 35968864) Front Endocrinol (Lausanne). 2021 Jun 01;12:678094. (PMID: 34140931) J Clin Endocrinol Metab. 2024 Apr 19;109(5):1214-1221. (PMID: 38066644) Diagnostics (Basel). 2023 Nov 16;13(22):. (PMID: 37998589) J Med Internet Res. 2024 Nov 27;26:e54641. (PMID: 39602803) Inf Fusion. 2022 Jun;82:99-122. (PMID: 35664012) Horm Res Paediatr. 2015;84(2):79-87. (PMID: 25966824) J Endocrinol Invest. 2022 Apr;45(4):887-897. (PMID: 34791604) Clin Endocrinol (Oxf). 2025 Mar;102(3):281-287. (PMID: 39676465) Inf Fusion. 2019 Oct;50:71-91. (PMID: 30467459) Health Qual Life Outcomes. 2019 Jun 20;17(1):106. (PMID: 31221151) Ann Pediatr Endocrinol Metab. 2024 Feb;29(1):3-11. (PMID: 38461800) touchREV Endocrinol. 2022 Jun;18(1):49-57. (PMID: 35949366) Korean J Pediatr. 2018 May;61(5):135-149. (PMID: 29853938) |
| Substance Nomenclature: | 12629-01-5 (Human Growth Hormone) |
| Entry Date(s): | Date Created: 20260518 Date Completed: 20260803 Latest Revision: 20260907 |
| Update Code: | 20260907 |
| PubMed Central ID: | PMC13432686 |
| DOI: | 10.1111/cen.70163 |
| PMID: | 42144818 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!