English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Introduction. Prediction of recombinant human growth hormone (rhGH) therapy effectiveness seems an important issue, especially in situations when diagnosis is problematic. Until now the problem was solved by multiple regression analysis, while here we propose application of artificial neural networks (ANN), particularly multilayer perceptron (MLP), as a novel tool. Material and methods. The analysis was performed on data of 289 patients, treated for at least 2 years due to GH deficiency. First, we automatically classified patients to one of two groups depending on attainment of final height (FH) over or below 10th centile (2-stage classification). Secondly, we introduced third group for FH below 3rd centile (3-stage classification). Finally, we predicted attained FH standard deviation score (SDS) in ANN regression model. Results. In 2-stage version MLP networks classified more than 80% of patients correctly. In 3-stage classification, the ratio of right answers was close to 70%. ANN regression model predicted FH SDS with average error of 0.7 SD (4.2 cm), explaining about 45% of its variability. Conclusion. The results of the study are promising and the topic definitely worth further consideration. Due to their characteristics, ANN seem to be parSłowa kluczowe Sztuczne sieci neuronowe, hormon wzrostu, modelowanie skuteczności leczenia

Artificial neural networks – a novel tool in modelling the effectiveness of growth hormone (GH) therapy in children with GH deficiency