Methodology of algorithm development

Responses to growth hormone (GH) treatment vary widely. There is a broad range of sensitivity — and responsiveness — to GH, so a ‘one size fits all’ approach to GH treatment is no longer appropriate1-2.
iGRO™ applies evidence-based, validated and peer-reviewed growth prediction algorithms to provide realistic and personalised growth targets, to help improve growth outcomes and optimise treatment3.

These algorithms have been developed using the wealth of real-world clinical data from separate cohorts of patients in KIGS (the Pfizer International Growth Database3.

This international database contains growth data collected over a 25-year period from over 83,000 children who have received growth hormone treatment from 52 countries. These algorithms enable you to make a more accurate prediction, based on the gender, age and condition of a child; and monitor their response to treatment. Using this information you can identify any issues, confirm diagnoses and guide further treatment — offering personalised growth hormone treatment that is based on your patient’s needs3.



1 - Wit JM, Ranke MB, Albertsson-Wikland K et al. Personalized approach to growth hormone treatment: clinical use of growth prediction models. Hormone research in paediatrics (2013);79:257–70.

2 - Kaspers S, Ranke MB, Han D et al. Implications of a datadriven approach to treatment with growth hormone in children with growth hormone deficiency and Turner syndrome. Appl Health Econ Health Policy (2013);11: 237–49.

3 - Loftus J, Lindberg A, Aydin F, et al. Journal of Pediatric Endocrinology and Metabolism (2017);30:1019–1026.