Evaluating the use of existing data sources, probabilistic linkage, and multiple imputation to build population-based injury databases across phases of trauma care

Craig Newgard, Susan Malveau, Kristan Staudenmayer, N. Ewen Wang, Renee Y. Hsia, N. Clay Mann, James F. Holmes, Nathan Kuppermann, Jason S. Haukoos, Eileen M. Bulger, Mengtao Dai, Lawrence J. Cook

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

Objectives: The objective was to evaluate the process of using existing data sources, probabilistic linkage, and multiple imputation to create large population-based injury databases matched to outcomes. Methods: This was a retrospective cohort study of injured children and adults transported by 94 emergency medical systems (EMS) agencies to 122 hospitals in seven regions of the western United States over a 36-month period (2006 to 2008). All injured patients evaluated by EMS personnel within specific geographic catchment areas were included, regardless of field disposition or outcome. The authors performed probabilistic linkage of EMS records to four hospital and postdischarge data sources (emergency department [ED] data, patient discharge data, trauma registries, and vital statistics files) and then handled missing values using multiple imputation. The authors compare and evaluate matched records, match rates (proportion of matches among eligible patients), and injury outcomes within and across sites. Results: There were 381,719 injured patients evaluated by EMS personnel in the seven regions. Among transported patients, match rates ranged from 14.9% to 87.5% and were directly affected by the availability of hospital data sources and proportion of missing values for key linkage variables. For vital statistics records (1-year mortality), estimated match rates ranged from 88.0% to 98.7%. Use of multiple imputation (compared to complete case analysis) reduced bias for injury outcomes, although sample size, percentage missing, type of variable, and combined-site versus single-site imputation models all affected the resulting estimates and variance. Conclusions: This project demonstrates the feasibility and describes the process of constructing population-based injury databases across multiple phases of care using existing data sources and commonly available analytic methods. Attention to key linkage variables and decisions for handling missing values can be used to increase match rates between data sources, minimize bias, and preserve sampling design.

Original languageEnglish (US)
Pages (from-to)469-480
Number of pages12
JournalAcademic Emergency Medicine
Volume19
Issue number4
DOIs
StatePublished - Apr 2012

Fingerprint

Information Storage and Retrieval
Databases
Emergencies
Wounds and Injuries
Vital Statistics
Population
Selection Bias
Patient Discharge
Sample Size
Medical Records
Registries
Hospital Emergency Service
Cohort Studies
Retrospective Studies
Mortality

ASJC Scopus subject areas

  • Emergency Medicine

Cite this

Evaluating the use of existing data sources, probabilistic linkage, and multiple imputation to build population-based injury databases across phases of trauma care. / Newgard, Craig; Malveau, Susan; Staudenmayer, Kristan; Wang, N. Ewen; Hsia, Renee Y.; Mann, N. Clay; Holmes, James F.; Kuppermann, Nathan; Haukoos, Jason S.; Bulger, Eileen M.; Dai, Mengtao; Cook, Lawrence J.

In: Academic Emergency Medicine, Vol. 19, No. 4, 04.2012, p. 469-480.

Research output: Contribution to journalArticle

Newgard, C, Malveau, S, Staudenmayer, K, Wang, NE, Hsia, RY, Mann, NC, Holmes, JF, Kuppermann, N, Haukoos, JS, Bulger, EM, Dai, M & Cook, LJ 2012, 'Evaluating the use of existing data sources, probabilistic linkage, and multiple imputation to build population-based injury databases across phases of trauma care', Academic Emergency Medicine, vol. 19, no. 4, pp. 469-480. https://doi.org/10.1111/j.1553-2712.2012.01324.x
Newgard, Craig ; Malveau, Susan ; Staudenmayer, Kristan ; Wang, N. Ewen ; Hsia, Renee Y. ; Mann, N. Clay ; Holmes, James F. ; Kuppermann, Nathan ; Haukoos, Jason S. ; Bulger, Eileen M. ; Dai, Mengtao ; Cook, Lawrence J. / Evaluating the use of existing data sources, probabilistic linkage, and multiple imputation to build population-based injury databases across phases of trauma care. In: Academic Emergency Medicine. 2012 ; Vol. 19, No. 4. pp. 469-480.
@article{e607a7886bbd47afa950fa3795f4f050,
title = "Evaluating the use of existing data sources, probabilistic linkage, and multiple imputation to build population-based injury databases across phases of trauma care",
abstract = "Objectives: The objective was to evaluate the process of using existing data sources, probabilistic linkage, and multiple imputation to create large population-based injury databases matched to outcomes. Methods: This was a retrospective cohort study of injured children and adults transported by 94 emergency medical systems (EMS) agencies to 122 hospitals in seven regions of the western United States over a 36-month period (2006 to 2008). All injured patients evaluated by EMS personnel within specific geographic catchment areas were included, regardless of field disposition or outcome. The authors performed probabilistic linkage of EMS records to four hospital and postdischarge data sources (emergency department [ED] data, patient discharge data, trauma registries, and vital statistics files) and then handled missing values using multiple imputation. The authors compare and evaluate matched records, match rates (proportion of matches among eligible patients), and injury outcomes within and across sites. Results: There were 381,719 injured patients evaluated by EMS personnel in the seven regions. Among transported patients, match rates ranged from 14.9{\%} to 87.5{\%} and were directly affected by the availability of hospital data sources and proportion of missing values for key linkage variables. For vital statistics records (1-year mortality), estimated match rates ranged from 88.0{\%} to 98.7{\%}. Use of multiple imputation (compared to complete case analysis) reduced bias for injury outcomes, although sample size, percentage missing, type of variable, and combined-site versus single-site imputation models all affected the resulting estimates and variance. Conclusions: This project demonstrates the feasibility and describes the process of constructing population-based injury databases across multiple phases of care using existing data sources and commonly available analytic methods. Attention to key linkage variables and decisions for handling missing values can be used to increase match rates between data sources, minimize bias, and preserve sampling design.",
author = "Craig Newgard and Susan Malveau and Kristan Staudenmayer and Wang, {N. Ewen} and Hsia, {Renee Y.} and Mann, {N. Clay} and Holmes, {James F.} and Nathan Kuppermann and Haukoos, {Jason S.} and Bulger, {Eileen M.} and Mengtao Dai and Cook, {Lawrence J.}",
year = "2012",
month = "4",
doi = "10.1111/j.1553-2712.2012.01324.x",
language = "English (US)",
volume = "19",
pages = "469--480",
journal = "Academic Emergency Medicine",
issn = "1069-6563",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - Evaluating the use of existing data sources, probabilistic linkage, and multiple imputation to build population-based injury databases across phases of trauma care

AU - Newgard, Craig

AU - Malveau, Susan

AU - Staudenmayer, Kristan

AU - Wang, N. Ewen

AU - Hsia, Renee Y.

AU - Mann, N. Clay

AU - Holmes, James F.

AU - Kuppermann, Nathan

AU - Haukoos, Jason S.

AU - Bulger, Eileen M.

AU - Dai, Mengtao

AU - Cook, Lawrence J.

PY - 2012/4

Y1 - 2012/4

N2 - Objectives: The objective was to evaluate the process of using existing data sources, probabilistic linkage, and multiple imputation to create large population-based injury databases matched to outcomes. Methods: This was a retrospective cohort study of injured children and adults transported by 94 emergency medical systems (EMS) agencies to 122 hospitals in seven regions of the western United States over a 36-month period (2006 to 2008). All injured patients evaluated by EMS personnel within specific geographic catchment areas were included, regardless of field disposition or outcome. The authors performed probabilistic linkage of EMS records to four hospital and postdischarge data sources (emergency department [ED] data, patient discharge data, trauma registries, and vital statistics files) and then handled missing values using multiple imputation. The authors compare and evaluate matched records, match rates (proportion of matches among eligible patients), and injury outcomes within and across sites. Results: There were 381,719 injured patients evaluated by EMS personnel in the seven regions. Among transported patients, match rates ranged from 14.9% to 87.5% and were directly affected by the availability of hospital data sources and proportion of missing values for key linkage variables. For vital statistics records (1-year mortality), estimated match rates ranged from 88.0% to 98.7%. Use of multiple imputation (compared to complete case analysis) reduced bias for injury outcomes, although sample size, percentage missing, type of variable, and combined-site versus single-site imputation models all affected the resulting estimates and variance. Conclusions: This project demonstrates the feasibility and describes the process of constructing population-based injury databases across multiple phases of care using existing data sources and commonly available analytic methods. Attention to key linkage variables and decisions for handling missing values can be used to increase match rates between data sources, minimize bias, and preserve sampling design.

AB - Objectives: The objective was to evaluate the process of using existing data sources, probabilistic linkage, and multiple imputation to create large population-based injury databases matched to outcomes. Methods: This was a retrospective cohort study of injured children and adults transported by 94 emergency medical systems (EMS) agencies to 122 hospitals in seven regions of the western United States over a 36-month period (2006 to 2008). All injured patients evaluated by EMS personnel within specific geographic catchment areas were included, regardless of field disposition or outcome. The authors performed probabilistic linkage of EMS records to four hospital and postdischarge data sources (emergency department [ED] data, patient discharge data, trauma registries, and vital statistics files) and then handled missing values using multiple imputation. The authors compare and evaluate matched records, match rates (proportion of matches among eligible patients), and injury outcomes within and across sites. Results: There were 381,719 injured patients evaluated by EMS personnel in the seven regions. Among transported patients, match rates ranged from 14.9% to 87.5% and were directly affected by the availability of hospital data sources and proportion of missing values for key linkage variables. For vital statistics records (1-year mortality), estimated match rates ranged from 88.0% to 98.7%. Use of multiple imputation (compared to complete case analysis) reduced bias for injury outcomes, although sample size, percentage missing, type of variable, and combined-site versus single-site imputation models all affected the resulting estimates and variance. Conclusions: This project demonstrates the feasibility and describes the process of constructing population-based injury databases across multiple phases of care using existing data sources and commonly available analytic methods. Attention to key linkage variables and decisions for handling missing values can be used to increase match rates between data sources, minimize bias, and preserve sampling design.

UR - http://www.scopus.com/inward/record.url?scp=84859881529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859881529&partnerID=8YFLogxK

U2 - 10.1111/j.1553-2712.2012.01324.x

DO - 10.1111/j.1553-2712.2012.01324.x

M3 - Article

C2 - 22506952

AN - SCOPUS:84859881529

VL - 19

SP - 469

EP - 480

JO - Academic Emergency Medicine

JF - Academic Emergency Medicine

SN - 1069-6563

IS - 4

ER -