Mathematical models for predicting final achieved height and its standard deviation rate in children with growth hormone deficiency in the Russian population

Background. Predicting the efficacy of rGH therapy in patients with GH deficiency, based on the final achieved height (FAH) criterion, is an important tool for the clinician. It enables a personalized approach to the treatment of patients with GH deficiency: to recommend careful adherence to the regimen and dosage of the drug, evaluate the efficacy of therapy in different groups of patients, and clearly demonstrate the factors affecting the FAH indicator.

Aim — to develop mathematical models for predicting FAH and its standard deviation score (SDS) in patients with GH deficiency in the Russian population.

Material and methods. For simulation, we used the data of 121 patients diagnosed with GH deficiency who received rGH since the time of diagnosis to the time of final height and were followed-up at the Institute of Pediatric Endocrinology of the Endocrinology Research Centre in the period between 1978 and 2016. As model predictors, we used 11 indicators: the gender, chronological age at the time of GH deficiency diagnosis, puberty status, disease form, regularity of rGH therapy, height SDS at birth, height SDS at the time of GH deficiency diagnosis, bone age at the time of GH deficiency diagnosis, bone age/chronological index, SDS of a genetically predicted height, and maximum stimulated GH level in a clonidine test. To generate models, we used multiple linear regression, artificial neural networks (ANNs), and the Statistica 13 software.

Results. The developed ANNs demonstrated a high accuracy of predicting FAH (the root-mean-square error was 4.4 cm, and the explained variance fraction was 76%) and a lower accuracy of predicting the FAH SDS (the root-mean-square error was 0.601 SDS, and the explained variance fraction was 42%). Linear regression models that were based on quantitative predictors only had a substantially worse quality. Free software implementation was developed for the best produced ANN.

Conclusion. An ANN-based software-implemented model for predicting FAH uses indicators available for any clinician as predictors and can be used for individual prediction of FAH. In the future, the use of larger databases for simulation will improve the quality of predicting the efficacy of rGH therapy.

artificial neural network, multiple regression, predicting, GH deficiency, insulin-like growth factor 1, growth hormone therapy, final achieved height

1. Darendeliler F, Lindberg A, Wilton P. Response to growth hormone treatment in isolated growth hormone deficiency versus multiple pituitary hormone deficiency. Horm Res Paediatr. 2011;76 Suppl 1:42-46. doi: 10.1159/000329161

2. Blethen SL, Baptista J, Kuntze J, et al. Adult height in growth hormone (GH)-deficient children treated with biosynthetic GH. The Genentech Growth Study Group. J Clin Endocrinol Metab. 1997;82(2):418-420. doi: 10.1210/jcem.82.2.3734

3. Rachmiel M, Rota V, Atenafu E, et al. Final height in children with idiopathic growth hormone deficiency treated with a fixed dose of recombinant growth hormone. Horm Res. 2007;68(5):236-243. doi: 10.1159/000101427

4. Thomas M, Massa G, Bourguignon JP, et al. Final height in children with idiopathic growth hormone deficiency treated with recombinant human growth hormone: the Belgian experience. Horm Res Paediatr. 2001;55(2):88-94. doi: 10.1159/000049976

5. Mortensen HB, Main K, Michaelsen KF, et al. Predicting and monitoring of growth in children with short stature during the first year of growth hormone treatment. Acta Paediatr. 1991;80(12):1150-1157. doi: 10.1111/j.1651-2227.1991.tb11803.x

6. Wikland KA, Kriström B, Rosberg S, et al. Validated multivariate models predicting the growth response to GH treatment in individual short children with a broad range in GH Secretion Capacities. Pediatr Res. 2000;48(4):475-484. doi: 10.1203/00006450-200010000-00010

7. Schonau E, Westermann F, Rauch F, et al. A new and accurate prediction model for growth response to growth hormone treatment in children with growth hormone deficiency. Eur J Endocrinol. 2001;144(1):13-20. doi: 10.1530/eje.0.1440013

8. Ranke MB, Martin DD, Lindberg A, on behalf of the Kigs International Board o. prediction model of total pubertal growth in idiopathic growth hormone deficiency: analysis of data from KIGS. Horm Res Paediatr. 2004;60(1):58-59. doi: 10.1159/000071227

9. de Ridder MAJ, Stijnen T, Hokken-Koelega ACS. Prediction of adult height in growth-hormone-treated children with growth hormone deficiency. J Clin Endocr Metab. 2007;92(3):925-931. doi: 10.1210/jc.2006-1259

10. Smyczynska J, Hilczer M, Smyczynska U, et al. Neural network models — a novel tool for predicting the efficacy of growth hormone (GH) therapy in children with short stature. Neuro Endocrinol Lett. 2015;36(4):348-353.

11. Реброва О.Ю. Применение методов интеллектуального анализа данных для решения задачи медицинской диагностики. // Новости искусственного интеллекта. — 2004. — №3. — С. 76-80. [Rebrova OYu. Primenenie metodov intellektual’nogo analiza dannykh dlya resheniya zadachi meditsinskoy diagnostiki. Novosti iskusstvennogo intellekta. 2004;(3):76-80.(In Russ.)].

12. Нагаева Е.В. Федеральные клинические рекомендации по диагностике и лечению гипопитуитаризма у детей и подростков // Проблемы Эндокринологии. — 2013. — Т. 59. — №6. — C. 27—43. [Nagaeva EV. Russian association of endocrinologists national practice guidelines(clinical signs, diagnosis, differential diagnosis, treatment). Hypopituitarism in children and adolescents. Problems of Endocrinology. 2013;59(6):27-43. (In Russ.)].doi: 10.14341/probl201359627-43

13. Blethen SL, Baptista J, Kuntze J, et al. Adult height in growth hormone (GH)-deficient children treated with biosynthetic GH. The Genentech Growth Study Group. J Clin Endocrinol Metab. 1997;82(2):418-420. doi: 10.1210/jcem.82.2.3734

14. Rohayem J, Drechsel H, Tittel B, et al. Long-term outcomes, genetics, and pituitary morphology in patients with isolated growth hormone deficiency and multiple pituitary hormone deficiencies: a single-centre experience of four decades of growth hormone replacement. Horm Res Paediatr. 2016;86(2):106-116. doi: 10.1159/000448098

15. WHO Child Growth Standards. Acta Paediatrica. 2006;95(suppl 1):5-101. Available from: http://www.who.int/childgrowth/standards/ru

16. Greulich WW, Pyle SI. Radiographic atlas of skeletal development of the hand and wrist. The American Journal of the Medical Sciences. 1959;238(3):393.

17. Kromeyer-Hauschild K, Jaeger U. Growth studies in Jena, Germany: changes in body size and subcutaneous fat distribution between 1975 and 1995. Am J Hum Biol. 1998;10(5):579-587. doi: 10.1002/(sici)1520-6300(1998)10:5<579::aid-ajhb4>3.0.co;2-9