Going Beyond Administrative Data: Retrospective Evaluation of an Algorithm Using the Electronic Health Record to Help Identify Bleeding Events Among Hospitalized Medical Patients on Warfarin

James P. Moriarty, Paul R. Daniels, Dennis M. Manning, John G. O’Meara, Narith N. Ou, Tamara M. Berg, Jordan D. Haag, Daniel L. Roellinger, James M Naessens

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

To reliably assess quality, a standardized electronic approach is needed to identify bleeding events. The study aims were the following: (1) clinically validate an electronic health record–based algorithm for bleeding and (2) assess interrater results to determine validity and reliability. Data were analyzed before and after implementation of a pharmacist-managed warfarin protocol. Bleeding was based on ≥2 of 3 criteria: (1) diagnosis indicating bleeding, (2) lab value decrease suggesting bleeding, and (3) blood product use. All suspected bleeds (234) and a sample (58) not meeting criteria were compared with clinical review. There were 234 bleeding cases identified electronically. Reviewer agreement was 78.2% (κ = 0.565). Algorithm sensitivity was 93.9% and positive predictive value 46.2%. Algorithm identification was least accurate for those with only 2 criteria but good for those with all criteria. This study supports using multiple electronic criteria to identify bleeding events. However, cases having exactly 2 criteria may require manual review for validation.

Original languageEnglish (US)
Pages (from-to)391-396
Number of pages6
JournalAmerican Journal of Medical Quality
Volume32
Issue number4
DOIs
StatePublished - Jul 1 2017

Fingerprint

Electronic Health Records
Warfarin
Hemorrhage
Pharmacists
Reproducibility of Results
Health

Keywords

  • algorithms
  • electronic health records
  • hemorrhage
  • warfarin

ASJC Scopus subject areas

  • Health Policy

Cite this

Going Beyond Administrative Data : Retrospective Evaluation of an Algorithm Using the Electronic Health Record to Help Identify Bleeding Events Among Hospitalized Medical Patients on Warfarin. / Moriarty, James P.; Daniels, Paul R.; Manning, Dennis M.; O’Meara, John G.; Ou, Narith N.; Berg, Tamara M.; Haag, Jordan D.; Roellinger, Daniel L.; Naessens, James M.

In: American Journal of Medical Quality, Vol. 32, No. 4, 01.07.2017, p. 391-396.

Research output: Contribution to journalArticle

Moriarty, James P. ; Daniels, Paul R. ; Manning, Dennis M. ; O’Meara, John G. ; Ou, Narith N. ; Berg, Tamara M. ; Haag, Jordan D. ; Roellinger, Daniel L. ; Naessens, James M. / Going Beyond Administrative Data : Retrospective Evaluation of an Algorithm Using the Electronic Health Record to Help Identify Bleeding Events Among Hospitalized Medical Patients on Warfarin. In: American Journal of Medical Quality. 2017 ; Vol. 32, No. 4. pp. 391-396.
@article{ecaef1b18b5e40a3a21aa49bf62c517e,
title = "Going Beyond Administrative Data: Retrospective Evaluation of an Algorithm Using the Electronic Health Record to Help Identify Bleeding Events Among Hospitalized Medical Patients on Warfarin",
abstract = "To reliably assess quality, a standardized electronic approach is needed to identify bleeding events. The study aims were the following: (1) clinically validate an electronic health record–based algorithm for bleeding and (2) assess interrater results to determine validity and reliability. Data were analyzed before and after implementation of a pharmacist-managed warfarin protocol. Bleeding was based on ≥2 of 3 criteria: (1) diagnosis indicating bleeding, (2) lab value decrease suggesting bleeding, and (3) blood product use. All suspected bleeds (234) and a sample (58) not meeting criteria were compared with clinical review. There were 234 bleeding cases identified electronically. Reviewer agreement was 78.2{\%} (κ = 0.565). Algorithm sensitivity was 93.9{\%} and positive predictive value 46.2{\%}. Algorithm identification was least accurate for those with only 2 criteria but good for those with all criteria. This study supports using multiple electronic criteria to identify bleeding events. However, cases having exactly 2 criteria may require manual review for validation.",
keywords = "algorithms, electronic health records, hemorrhage, warfarin",
author = "Moriarty, {James P.} and Daniels, {Paul R.} and Manning, {Dennis M.} and O’Meara, {John G.} and Ou, {Narith N.} and Berg, {Tamara M.} and Haag, {Jordan D.} and Roellinger, {Daniel L.} and Naessens, {James M}",
year = "2017",
month = "7",
day = "1",
doi = "10.1177/1062860616660757",
language = "English (US)",
volume = "32",
pages = "391--396",
journal = "American Journal of Medical Quality",
issn = "1062-8606",
publisher = "SAGE Publications Inc.",
number = "4",

}

TY - JOUR

T1 - Going Beyond Administrative Data

T2 - Retrospective Evaluation of an Algorithm Using the Electronic Health Record to Help Identify Bleeding Events Among Hospitalized Medical Patients on Warfarin

AU - Moriarty, James P.

AU - Daniels, Paul R.

AU - Manning, Dennis M.

AU - O’Meara, John G.

AU - Ou, Narith N.

AU - Berg, Tamara M.

AU - Haag, Jordan D.

AU - Roellinger, Daniel L.

AU - Naessens, James M

PY - 2017/7/1

Y1 - 2017/7/1

N2 - To reliably assess quality, a standardized electronic approach is needed to identify bleeding events. The study aims were the following: (1) clinically validate an electronic health record–based algorithm for bleeding and (2) assess interrater results to determine validity and reliability. Data were analyzed before and after implementation of a pharmacist-managed warfarin protocol. Bleeding was based on ≥2 of 3 criteria: (1) diagnosis indicating bleeding, (2) lab value decrease suggesting bleeding, and (3) blood product use. All suspected bleeds (234) and a sample (58) not meeting criteria were compared with clinical review. There were 234 bleeding cases identified electronically. Reviewer agreement was 78.2% (κ = 0.565). Algorithm sensitivity was 93.9% and positive predictive value 46.2%. Algorithm identification was least accurate for those with only 2 criteria but good for those with all criteria. This study supports using multiple electronic criteria to identify bleeding events. However, cases having exactly 2 criteria may require manual review for validation.

AB - To reliably assess quality, a standardized electronic approach is needed to identify bleeding events. The study aims were the following: (1) clinically validate an electronic health record–based algorithm for bleeding and (2) assess interrater results to determine validity and reliability. Data were analyzed before and after implementation of a pharmacist-managed warfarin protocol. Bleeding was based on ≥2 of 3 criteria: (1) diagnosis indicating bleeding, (2) lab value decrease suggesting bleeding, and (3) blood product use. All suspected bleeds (234) and a sample (58) not meeting criteria were compared with clinical review. There were 234 bleeding cases identified electronically. Reviewer agreement was 78.2% (κ = 0.565). Algorithm sensitivity was 93.9% and positive predictive value 46.2%. Algorithm identification was least accurate for those with only 2 criteria but good for those with all criteria. This study supports using multiple electronic criteria to identify bleeding events. However, cases having exactly 2 criteria may require manual review for validation.

KW - algorithms

KW - electronic health records

KW - hemorrhage

KW - warfarin

UR - http://www.scopus.com/inward/record.url?scp=85021745068&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021745068&partnerID=8YFLogxK

U2 - 10.1177/1062860616660757

DO - 10.1177/1062860616660757

M3 - Article

C2 - 27455999

AN - SCOPUS:85021745068

VL - 32

SP - 391

EP - 396

JO - American Journal of Medical Quality

JF - American Journal of Medical Quality

SN - 1062-8606

IS - 4

ER -