Curve matching: a big data technique to predict growth in patients receiving growth hormone therapy: abstract

Curve matching may be used to predict growth outcomes. To apply this method a longitudinal database is needed with a large amount of patients’ longitudinal growth data that forms the basis of developing growth curves. This database can be used to identify growth curves (e.g. height) of patients that are similar to the growth curve of a new patient up until their current visit. The growth curves of these ‘matched’ patients can then be added to the growth chart of the new patient to visualize how this patient is expected to grow in the future. We aimed to investigate the validity of curve matching to predict growth in patients with growth hormone deficiency (GHD) and those born small for gestational age (SGA) receiving recombinant human growth hormone (r-hGH). Height data collected between 0–48 months of treatment were extracted from the easypod™ connect ecosystem and the easypod™ connect observational study. Selected patients with height standard deviation scores (HSDS) [-4, <-1] and age [3, <16y] at start were included. The ‘Matching Database’ consisted of patients’ monthly HSDS obtained by the broken stick method and imputation. Standard deviation (SD) was obtained from the observed minus the predicted HSDS (error) based on matched patients within the ‘Matching Database’. Data were available for 3,213 patients in the ‘Matching Database’, and 2,472 patients with 16,624 HSDS measurements in the observed database. When ≥2 HSDS measurements were available, the error SD for a one-year prediction was approximately 0.2, which corresponds to 1.1 cm, 1.3 cm, and 1.5 cm at 7, 11, and 15 years of age, respectively. We conclude that curve matching is a simple and valid technique for predicting growth in patients with GHD and those born SGA. The results are interpretable and explainable without adding significant workload to the clinical pathway.