PediTools Electronic Growth Chart Calculators: Applications in Clinical Care, Research, and Quality Improvement

Abstract

Background: Parameterization of pediatric growth charts allows precise quantitation of growth metrics that would be difficult or impossible with traditional paper charts. However, limited availability of growth chart calculators for use by clinicians and clinical researchers currently restricts broader application.

Objective: The aim of this study was to assess the deployment of electronic calculators for growth charts using the lambda-mu-sigma (LMS) parameterization method, with examples of their utilization for patient care delivery, clinical research, and quality improvement projects.

Methods: The publicly accessible PediTools website of clinical calculators was developed to allow LMS-based calculations on anthropometric measurements of individual patients. Similar calculations were applied in a retrospective study of a population of patients from 7 Massachusetts neonatal intensive care units (NICUs) to compare interhospital growth outcomes (change in weight Z-score from birth to discharge [∆Z weight]) and their association with gestational age at birth. At 1 hospital, a bundle of quality improvement interventions targeting improved growth was implemented, and the outcomes were assessed prospectively via monitoring of ∆Z weight pre- and postintervention.

Results: The PediTools website was launched in January 2012, and as of June 2019, it received over 500,000 page views per month, with users from over 21 countries. A retrospective analysis of 7975 patients at 7 Massachusetts NICUs, born between 2006 and 2011, at 23 to 34 completed weeks gestation identified an overall ∆Z weight from birth to discharge of -0.81 (P<.001). However, the degree of ∆Z weight differed significantly by hospital, ranging from -0.56 to -1.05 (P<.001). Also identified was the association between inferior growth outcomes and lower gestational age at birth, as well as that the degree of association between ∆Z weight and gestation at birth also differed by hospital. At 1 hospital, implementing a bundle of interventions targeting growth resulted in a significant and sustained reduction in loss of weight Z-score from birth to discharge.

Conclusions: LMS-based anthropometric measurement calculation tools on a public website have been widely utilized. Application in a retrospective clinical study on a large dataset demonstrated inferior growth at lower gestational age and interhospital variation in growth outcomes. Change in weight Z-score has potential utility as an outcome measure for monitoring clinical quality improvement. We also announce the release of open-source computer code written in R to allow other clinicians and clinical researchers to easily perform similar analyses.

Keywords: failure to thrive; growth charts; infant, newborn; infant, premature; internet; pediatrics; software.

Figure 1

Equations for LMS-based growth metric calculations for Z score (a and b) and for an anthropometric measurement X (c and d).

Figure 2

Screenshot of a representative PediTools web-based growth calculator (Fenton 2013 for preterm infants). The upper section demonstrates flexible support for multiple methods of input data entry. Data entry can include age as either gestational age or specific dates; measurements can be entered in metric or imperial units (grams or pounds and ounces; centimeters or inches); and even if no measurement is entered, the expected median (50th percentile) values will be displayed. The lower section displays the results of the LMS-based calculations, including the anthropometric measures in both metric and imperial units, percentile, Z-score, expected median measurement for age, and weekly growth required to maintain the current percentile.

Figure 3

PediTools (https://peditools.org/) website overall monthly pageviews over time from public launch in January 2012 through June 2019.

Figure 4

Electronic Fenton 2013 preterm growth chart. De-identified demographic and anthropometric data is copied into a webpage form from a specifically designed Microsoft Excel™ spreadsheet. The upper panel shows each anthropometric measurement plotted automatically onto the traditional paper-based chart. The lower panel displays calculated percentiles, Z-scores, and weekly weight change, both the actual observed change as well as the expected weekly change needed to maintain the previous percentile. Clinical decision support is provided by color-coding based on the weekly weight Z-score change.

Figure 5

Change in weight Z-score from birth to discharge versus gestational age at birth, demonstrating inferior growth with increasing prematurity for all seven NICUs combined. The dark blue line is for all years 2006 - 2011 combined with the gray band representing the 95% confidence interval; the thin lines show the grouped birth years 2006 - 2008 versus 2009 - 2011.

Figure 6

Inter-hospital variation in change in weight Z-score from birth to discharge, as related to gestational age at birth, (A) separately for each of seven different hospital NICUs in Massachusetts, and (B) for hospitals C and F overlaid on the same plot to better demonstrate inter-hospital differences.

Figure 7

Improvement of growth outcomes (∆Z weight) at hospital C, by birth gestation and birth year epoch. Epoch 2006 – 2008 is pre-intervention; 2009 - 2011 covers the beginning of implementation of interventions; 2012 - 2014 is the immediate post-intervention epoch; 2015 - 2017 demonstrates sustained improvement, but less extreme at lower gestational ages, after targeting a goal ∆Z weight of -0.6. The largest improvements are seen at the lowest gestational ages at birth.