Automated data extraction

merging clinical care with real-time cohort-specific research and quality improvement data

Ferdynand Hebal*, Elizabeth Nanney, Christine Stake, M. L. Miller, George Lales, Katherine A. Barsness

*Corresponding author for this work

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Background/Purpose Although prohibitively labor intensive, manual data extraction (MDE) is the prevailing method used to obtain clinical research and quality improvement (QI) data. Automated data extraction (ADE) offers a powerful alternative. The purposes of this study were to 1) assess the feasibility of ADE from provider-authored outpatient documentation, and 2) evaluate the effectiveness of ADE compared to MDE. Methods A prospective collection of data was performed on 90 ADE-templated notes (N = 71 patients) evaluated in our bowel management clinic. ADE captured data were compared to 59 MDE notes (N = 51) collected under an IRB-exempt review. Sixteen variables were directly comparable between ADE and MDE. Results MDE for 59 clinic notes (27 unique variables) took 6 months to complete. ADE-templated notes for 90 clinic notes (154 unique variables) took 5 min to run a research/QI report. Implementation of ADE included eight weeks of development and testing. Pre-implementation clinical documentation was similar to post-implementation documentation (5–10 min). Conclusions ADE-templated notes allow for a 5-fold increase in clinically relevant data that can be captured with each encounter. ADE also results in real-time data extraction to a research/QI database that is easily queried. The immediate availability of these data, in a research-formatted spreadsheet, allows for rapid collection, analyses, and interpretation of the data. Level of evidence IV. Type of study Retrospective Study.

Original languageEnglish (US)
Pages (from-to)149-152
Number of pages4
JournalJournal of pediatric surgery
Volume52
Issue number1
DOIs
StatePublished - Jan 1 2017

Fingerprint

Quality Improvement
Documentation
Research
Research Ethics Committees
Outpatients
Retrospective Studies
Databases

Keywords

  • Automated data extraction
  • Clinical documentation
  • Electronic data capture
  • Electronic documentation
  • Templated notes

ASJC Scopus subject areas

  • Surgery
  • Pediatrics, Perinatology, and Child Health

Cite this

@article{6db62fccef0e4e8e93c7a80144437417,
title = "Automated data extraction: merging clinical care with real-time cohort-specific research and quality improvement data",
abstract = "Background/Purpose Although prohibitively labor intensive, manual data extraction (MDE) is the prevailing method used to obtain clinical research and quality improvement (QI) data. Automated data extraction (ADE) offers a powerful alternative. The purposes of this study were to 1) assess the feasibility of ADE from provider-authored outpatient documentation, and 2) evaluate the effectiveness of ADE compared to MDE. Methods A prospective collection of data was performed on 90 ADE-templated notes (N = 71 patients) evaluated in our bowel management clinic. ADE captured data were compared to 59 MDE notes (N = 51) collected under an IRB-exempt review. Sixteen variables were directly comparable between ADE and MDE. Results MDE for 59 clinic notes (27 unique variables) took 6 months to complete. ADE-templated notes for 90 clinic notes (154 unique variables) took 5 min to run a research/QI report. Implementation of ADE included eight weeks of development and testing. Pre-implementation clinical documentation was similar to post-implementation documentation (5–10 min). Conclusions ADE-templated notes allow for a 5-fold increase in clinically relevant data that can be captured with each encounter. ADE also results in real-time data extraction to a research/QI database that is easily queried. The immediate availability of these data, in a research-formatted spreadsheet, allows for rapid collection, analyses, and interpretation of the data. Level of evidence IV. Type of study Retrospective Study.",
keywords = "Automated data extraction, Clinical documentation, Electronic data capture, Electronic documentation, Templated notes",
author = "Ferdynand Hebal and Elizabeth Nanney and Christine Stake and Miller, {M. L.} and George Lales and Barsness, {Katherine A.}",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.jpedsurg.2016.10.040",
language = "English (US)",
volume = "52",
pages = "149--152",
journal = "Journal of Pediatric Surgery",
issn = "0022-3468",
publisher = "W.B. Saunders Ltd",
number = "1",

}

Automated data extraction : merging clinical care with real-time cohort-specific research and quality improvement data. / Hebal, Ferdynand; Nanney, Elizabeth; Stake, Christine; Miller, M. L.; Lales, George; Barsness, Katherine A.

In: Journal of pediatric surgery, Vol. 52, No. 1, 01.01.2017, p. 149-152.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated data extraction

T2 - merging clinical care with real-time cohort-specific research and quality improvement data

AU - Hebal, Ferdynand

AU - Nanney, Elizabeth

AU - Stake, Christine

AU - Miller, M. L.

AU - Lales, George

AU - Barsness, Katherine A.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Background/Purpose Although prohibitively labor intensive, manual data extraction (MDE) is the prevailing method used to obtain clinical research and quality improvement (QI) data. Automated data extraction (ADE) offers a powerful alternative. The purposes of this study were to 1) assess the feasibility of ADE from provider-authored outpatient documentation, and 2) evaluate the effectiveness of ADE compared to MDE. Methods A prospective collection of data was performed on 90 ADE-templated notes (N = 71 patients) evaluated in our bowel management clinic. ADE captured data were compared to 59 MDE notes (N = 51) collected under an IRB-exempt review. Sixteen variables were directly comparable between ADE and MDE. Results MDE for 59 clinic notes (27 unique variables) took 6 months to complete. ADE-templated notes for 90 clinic notes (154 unique variables) took 5 min to run a research/QI report. Implementation of ADE included eight weeks of development and testing. Pre-implementation clinical documentation was similar to post-implementation documentation (5–10 min). Conclusions ADE-templated notes allow for a 5-fold increase in clinically relevant data that can be captured with each encounter. ADE also results in real-time data extraction to a research/QI database that is easily queried. The immediate availability of these data, in a research-formatted spreadsheet, allows for rapid collection, analyses, and interpretation of the data. Level of evidence IV. Type of study Retrospective Study.

AB - Background/Purpose Although prohibitively labor intensive, manual data extraction (MDE) is the prevailing method used to obtain clinical research and quality improvement (QI) data. Automated data extraction (ADE) offers a powerful alternative. The purposes of this study were to 1) assess the feasibility of ADE from provider-authored outpatient documentation, and 2) evaluate the effectiveness of ADE compared to MDE. Methods A prospective collection of data was performed on 90 ADE-templated notes (N = 71 patients) evaluated in our bowel management clinic. ADE captured data were compared to 59 MDE notes (N = 51) collected under an IRB-exempt review. Sixteen variables were directly comparable between ADE and MDE. Results MDE for 59 clinic notes (27 unique variables) took 6 months to complete. ADE-templated notes for 90 clinic notes (154 unique variables) took 5 min to run a research/QI report. Implementation of ADE included eight weeks of development and testing. Pre-implementation clinical documentation was similar to post-implementation documentation (5–10 min). Conclusions ADE-templated notes allow for a 5-fold increase in clinically relevant data that can be captured with each encounter. ADE also results in real-time data extraction to a research/QI database that is easily queried. The immediate availability of these data, in a research-formatted spreadsheet, allows for rapid collection, analyses, and interpretation of the data. Level of evidence IV. Type of study Retrospective Study.

KW - Automated data extraction

KW - Clinical documentation

KW - Electronic data capture

KW - Electronic documentation

KW - Templated notes

UR - http://www.scopus.com/inward/record.url?scp=85006809838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006809838&partnerID=8YFLogxK

U2 - 10.1016/j.jpedsurg.2016.10.040

DO - 10.1016/j.jpedsurg.2016.10.040

M3 - Article

VL - 52

SP - 149

EP - 152

JO - Journal of Pediatric Surgery

JF - Journal of Pediatric Surgery

SN - 0022-3468

IS - 1

ER -