Key result
Artificial neural network models identified pre-treatment IGF-I concentration and earlier growth as the most important predictors of response to growth hormone therapy, explaining 45% of the variability.
Why the study?
Do artificial neural networks accurately predict growth during the 1st year of treatment and final height in children receiving growth hormone therapy?
Population
272 children treated with growth hormone for at least 1 year, 133 of whom have attained final height
Follow-up
at least 1 year
Authors
Loading...
May guide individualized growth hormone dosing; leaves open prospective validation of neural network predictions.
Observational (n=272)
Do artificial neural networks accurately predict growth during the 1st year of treatment and final height in children receiving growth hormone therapy?
Artificial neural networks identified IGF-I concentration and earlier growth as key non-linear predictors of growth hormone therapy effectiveness.
Smyczyńska et al. (2017) conducted an observational in Growth hormone deficiency (n=272). Growth hormone therapy was evaluated on Prediction of 1st-year growth response and final height using artificial neural networks. Artificial neural network models identified pre-treatment IGF-I concentration and earlier growth as the most important predictors of response to growth hormone therapy, explaining 45% of the variability.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: