Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Imputing Longitudinal Growth Data in International Pediatric Studies : Does CDC Reference Suffice?

Li, Zhiguo ; Toppari, Jorma ; Lundgren, Markus LU ; Frohnert, Brigitte I. ; Achenbach, Peter ; Veijola, Riitta LU and Anand, Vibha (2021) In AMIA ... Annual Symposium proceedings. AMIA Symposium 2021. p.754-762
Abstract

This study investigates a missing value imputation approach for longitudinal growth data in pediatric studies from multiple countries. We analyzed a combined cohort from five natural history studies of type 1 diabetes (T1D) in the US and EU with longitudinal growth measurements for 23,201 subjects. We developed a multiple imputation methodology using LMS parameters of CDC reference data. We measured imputation errors on both combined and individual cohorts using mean absolute percentage error (MAPE) and normalized root-mean-square error (NRMSE). Our results show low imputation errors using CDC reference. Overall height imputation errors were lower than for weight. The largest MAPE for weight and height among all age groups was 4.8% and... (More)

This study investigates a missing value imputation approach for longitudinal growth data in pediatric studies from multiple countries. We analyzed a combined cohort from five natural history studies of type 1 diabetes (T1D) in the US and EU with longitudinal growth measurements for 23,201 subjects. We developed a multiple imputation methodology using LMS parameters of CDC reference data. We measured imputation errors on both combined and individual cohorts using mean absolute percentage error (MAPE) and normalized root-mean-square error (NRMSE). Our results show low imputation errors using CDC reference. Overall height imputation errors were lower than for weight. The largest MAPE for weight and height among all age groups was 4.8% and 1.7%, respectively. When comparing performance between CDC reference and country-specific growth charts, we found no significant differences for height (CDC vs. German: p =0.993, CDC vs. Swedish: p=0.368) and for weight (CDC vs. Swedish: p=0.513) for all ages.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
author collaboration
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
AMIA ... Annual Symposium proceedings. AMIA Symposium
volume
2021
pages
9 pages
publisher
American Medical Informatics Association
external identifiers
  • pmid:35308906
  • scopus:85126851432
ISSN
1942-597X
language
English
LU publication?
yes
id
32dd3a0e-9275-4d8e-97c9-eb14cd53de37
date added to LUP
2022-05-03 13:48:02
date last changed
2024-05-02 08:16:40
@article{32dd3a0e-9275-4d8e-97c9-eb14cd53de37,
  abstract     = {{<p>This study investigates a missing value imputation approach for longitudinal growth data in pediatric studies from multiple countries. We analyzed a combined cohort from five natural history studies of type 1 diabetes (T1D) in the US and EU with longitudinal growth measurements for 23,201 subjects. We developed a multiple imputation methodology using LMS parameters of CDC reference data. We measured imputation errors on both combined and individual cohorts using mean absolute percentage error (MAPE) and normalized root-mean-square error (NRMSE). Our results show low imputation errors using CDC reference. Overall height imputation errors were lower than for weight. The largest MAPE for weight and height among all age groups was 4.8% and 1.7%, respectively. When comparing performance between CDC reference and country-specific growth charts, we found no significant differences for height (CDC vs. German: p =0.993, CDC vs. Swedish: p=0.368) and for weight (CDC vs. Swedish: p=0.513) for all ages.</p>}},
  author       = {{Li, Zhiguo and Toppari, Jorma and Lundgren, Markus and Frohnert, Brigitte I. and Achenbach, Peter and Veijola, Riitta and Anand, Vibha}},
  issn         = {{1942-597X}},
  language     = {{eng}},
  pages        = {{754--762}},
  publisher    = {{American Medical Informatics Association}},
  series       = {{AMIA ... Annual Symposium proceedings. AMIA Symposium}},
  title        = {{Imputing Longitudinal Growth Data in International Pediatric Studies : Does CDC Reference Suffice?}},
  volume       = {{2021}},
  year         = {{2021}},
}