Advanced

Imputing missing data of function and disease activity in rheumatoid arthritis registers : What is the best technique?

Mongin, Denis ; Lauper, Kim ; Turesson, Carl LU ; Hetland, Merete Lund ; Klami Kristianslund, Eirik ; Kvien, Tore K. ; Santos, Maria Jose ; Pavelka, Karel ; Iannone, Florenzo and Finckh, Axel , et al. (2019) In RMD Open 5(2).
Abstract

Objective To compare several methods of missing data imputation for function (Health Assessment Questionnaire) and for disease activity (Disease Activity Score-28 and Clinical Disease Activity Index) in rheumatoid arthritis (RA) patients. Methods One thousand RA patients from observational cohort studies with complete data for function and disease activity at baseline, 6, 12 and 24 months were selected to conduct a simulation study. Values were deleted at random or following a predicted attrition bias. Three types of imputation were performed: (1) methods imputing forward in time (last observation carried forward; linear forward extrapolation); (2) methods considering data both forward and backward in time (nearest available observation... (More)

Objective To compare several methods of missing data imputation for function (Health Assessment Questionnaire) and for disease activity (Disease Activity Score-28 and Clinical Disease Activity Index) in rheumatoid arthritis (RA) patients. Methods One thousand RA patients from observational cohort studies with complete data for function and disease activity at baseline, 6, 12 and 24 months were selected to conduct a simulation study. Values were deleted at random or following a predicted attrition bias. Three types of imputation were performed: (1) methods imputing forward in time (last observation carried forward; linear forward extrapolation); (2) methods considering data both forward and backward in time (nearest available observation - NAO; linear extrapolation; polynomial extrapolation); and (3) methods using multi-individual models (linear mixed effects cubic regression - LME3; multiple imputation by chained equation - MICE). The performance of each estimation method was assessed using the difference between the mean outcome value, the remission and low disease activity rates after imputation of the missing values and the true value. Results When imputing missing baseline values, all methods underestimated equally the true value, but LME3 and MICE correctly estimated remission and low disease activity rates. When imputing missing follow-up values at 6, 12, or 24 months, NAO provided the least biassed estimate of the mean disease activity and corresponding remission rate. These results were not affected by the presence of attrition bias. Conclusion When imputing function and disease activity in large registers of active RA patients, researchers can consider the use of a simple method such as NAO for missing follow-up data, and the use of mixed-effects regression or multiple imputation for baseline data.

(Less)
Please use this url to cite or link to this publication:
author
, et al. (More)
(Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
DAS28, disease activity, epidemiology, outcomes research, rheumatoid arthritis
in
RMD Open
volume
5
issue
2
article number
000994
publisher
BMJ Publishing Group
external identifiers
  • scopus:85073717875
ISSN
2056-5933
DOI
10.1136/rmdopen-2019-000994
language
English
LU publication?
yes
id
601ab624-39b7-4d95-9264-3eccbb470723
date added to LUP
2019-11-05 08:45:13
date last changed
2019-12-08 05:50:18
@article{601ab624-39b7-4d95-9264-3eccbb470723,
  abstract     = {<p>Objective To compare several methods of missing data imputation for function (Health Assessment Questionnaire) and for disease activity (Disease Activity Score-28 and Clinical Disease Activity Index) in rheumatoid arthritis (RA) patients. Methods One thousand RA patients from observational cohort studies with complete data for function and disease activity at baseline, 6, 12 and 24 months were selected to conduct a simulation study. Values were deleted at random or following a predicted attrition bias. Three types of imputation were performed: (1) methods imputing forward in time (last observation carried forward; linear forward extrapolation); (2) methods considering data both forward and backward in time (nearest available observation - NAO; linear extrapolation; polynomial extrapolation); and (3) methods using multi-individual models (linear mixed effects cubic regression - LME3; multiple imputation by chained equation - MICE). The performance of each estimation method was assessed using the difference between the mean outcome value, the remission and low disease activity rates after imputation of the missing values and the true value. Results When imputing missing baseline values, all methods underestimated equally the true value, but LME3 and MICE correctly estimated remission and low disease activity rates. When imputing missing follow-up values at 6, 12, or 24 months, NAO provided the least biassed estimate of the mean disease activity and corresponding remission rate. These results were not affected by the presence of attrition bias. Conclusion When imputing function and disease activity in large registers of active RA patients, researchers can consider the use of a simple method such as NAO for missing follow-up data, and the use of mixed-effects regression or multiple imputation for baseline data.</p>},
  author       = {Mongin, Denis and Lauper, Kim and Turesson, Carl and Hetland, Merete Lund and Klami Kristianslund, Eirik and Kvien, Tore K. and Santos, Maria Jose and Pavelka, Karel and Iannone, Florenzo and Finckh, Axel and Courvoisier, Delphine Sophie},
  issn         = {2056-5933},
  language     = {eng},
  number       = {2},
  publisher    = {BMJ Publishing Group},
  series       = {RMD Open},
  title        = {Imputing missing data of function and disease activity in rheumatoid arthritis registers : What is the best technique?},
  url          = {http://dx.doi.org/10.1136/rmdopen-2019-000994},
  doi          = {10.1136/rmdopen-2019-000994},
  volume       = {5},
  year         = {2019},
}