Controlling for selective dropout in longitudinal dementia data: Application to the SveDem registry

Ron Handels; Linus Jönsson; Sara Garcia-Ptacek; Maria Eriksdotter; Anders Wimo

doi:10.1002/alz.12050

Controlling for selective dropout in longitudinal dementia data: Application to the SveDem registry

Ron Handels^*, Linus Jönsson, Sara Garcia-Ptacek, Maria Eriksdotter, Anders Wimo

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

INTRODUCTION: Loss to follow-up in dementia studies is common and related to cognition, which worsens over time. We aimed to (1) describe dropout and missing cognitive data in the Swedish dementia registry, SveDem; (2) identify factors associated with dropout; and (3) estimate propensity scores and use them to adjust for dropout.

METHODS: Longitudinal cognitive data were obtained from 53,880 persons from the SveDem national quality dementia registry. Inverse probability of censoring weights (IPCWs) were estimated using a logistic regression model on dropout.

RESULTS: The mean annualized rate of change in Mini-Mental State Examination (MMSE) in those with a low MMSE (0 to 10) was likely underestimated in the complete case analysis (+1.5 points/year) versus the IPCW analysis (-0.3 points/year).

DISCUSSION: Handling dropout by IPCWs resulted in plausible estimates of cognitive decline. This method is likely of value to adjust for biased dropout in longitudinal cohorts of dementia.

Original language	English
Pages (from-to)	789-796
Number of pages	8
Journal	Alzheimer's & Dementia
Volume	16
Issue number	5
DOIs	https://doi.org/10.1002/alz.12050
Publication status	Published - May 2020

Keywords

attrition
cognition
dementia
dropout
inverse probability of censoring weighting
loss to follow-up
registry
ATTRITION
MORTALITY
COHORT

Access to Document

10.1002/alz.12050Licence: CC BY-NC

Cite this

@article{b058696de0834933a62fdc06f206a8aa,

title = "Controlling for selective dropout in longitudinal dementia data: Application to the SveDem registry",

abstract = "INTRODUCTION: Loss to follow-up in dementia studies is common and related to cognition, which worsens over time. We aimed to (1) describe dropout and missing cognitive data in the Swedish dementia registry, SveDem; (2) identify factors associated with dropout; and (3) estimate propensity scores and use them to adjust for dropout.METHODS: Longitudinal cognitive data were obtained from 53,880 persons from the SveDem national quality dementia registry. Inverse probability of censoring weights (IPCWs) were estimated using a logistic regression model on dropout.RESULTS: The mean annualized rate of change in Mini-Mental State Examination (MMSE) in those with a low MMSE (0 to 10) was likely underestimated in the complete case analysis (+1.5 points/year) versus the IPCW analysis (-0.3 points/year).DISCUSSION: Handling dropout by IPCWs resulted in plausible estimates of cognitive decline. This method is likely of value to adjust for biased dropout in longitudinal cohorts of dementia.",

keywords = "attrition, cognition, dementia, dropout, inverse probability of censoring weighting, loss to follow-up, registry, ATTRITION, MORTALITY, COHORT",

author = "Ron Handels and Linus J{\"o}nsson and Sara Garcia-Ptacek and Maria Eriksdotter and Anders Wimo",

note = "{\textcopyright} 2019 The Authors. Alzheimer's & Dementia published by Wiley Periodicals, Inc. on behalf of Alzheimer's Association.",

year = "2020",

month = may,

doi = "10.1002/alz.12050",

language = "English",

volume = "16",

pages = "789--796",

journal = "Alzheimer's & Dementia",

issn = "1552-5260",

publisher = "Elsevier Science",

number = "5",

}

TY - JOUR

T1 - Controlling for selective dropout in longitudinal dementia data

T2 - Application to the SveDem registry

AU - Handels, Ron

AU - Jönsson, Linus

AU - Garcia-Ptacek, Sara

AU - Eriksdotter, Maria

AU - Wimo, Anders

PY - 2020/5

Y1 - 2020/5

N2 - INTRODUCTION: Loss to follow-up in dementia studies is common and related to cognition, which worsens over time. We aimed to (1) describe dropout and missing cognitive data in the Swedish dementia registry, SveDem; (2) identify factors associated with dropout; and (3) estimate propensity scores and use them to adjust for dropout.METHODS: Longitudinal cognitive data were obtained from 53,880 persons from the SveDem national quality dementia registry. Inverse probability of censoring weights (IPCWs) were estimated using a logistic regression model on dropout.RESULTS: The mean annualized rate of change in Mini-Mental State Examination (MMSE) in those with a low MMSE (0 to 10) was likely underestimated in the complete case analysis (+1.5 points/year) versus the IPCW analysis (-0.3 points/year).DISCUSSION: Handling dropout by IPCWs resulted in plausible estimates of cognitive decline. This method is likely of value to adjust for biased dropout in longitudinal cohorts of dementia.

AB - INTRODUCTION: Loss to follow-up in dementia studies is common and related to cognition, which worsens over time. We aimed to (1) describe dropout and missing cognitive data in the Swedish dementia registry, SveDem; (2) identify factors associated with dropout; and (3) estimate propensity scores and use them to adjust for dropout.METHODS: Longitudinal cognitive data were obtained from 53,880 persons from the SveDem national quality dementia registry. Inverse probability of censoring weights (IPCWs) were estimated using a logistic regression model on dropout.RESULTS: The mean annualized rate of change in Mini-Mental State Examination (MMSE) in those with a low MMSE (0 to 10) was likely underestimated in the complete case analysis (+1.5 points/year) versus the IPCW analysis (-0.3 points/year).DISCUSSION: Handling dropout by IPCWs resulted in plausible estimates of cognitive decline. This method is likely of value to adjust for biased dropout in longitudinal cohorts of dementia.

KW - attrition

KW - cognition

KW - dementia

KW - dropout

KW - inverse probability of censoring weighting

KW - loss to follow-up

KW - registry

KW - ATTRITION

KW - MORTALITY

KW - COHORT

U2 - 10.1002/alz.12050

DO - 10.1002/alz.12050

M3 - Article

C2 - 32202077

SN - 1552-5260

VL - 16

SP - 789

EP - 796

JO - Alzheimer's & Dementia

JF - Alzheimer's & Dementia

IS - 5

ER -