Classification of acute decompensated heart failure an automated algorithm compared with a physician reviewer panel: The atherosclerosis risk in communities study

Laura R. Loehr, Sunil K. Agarwal, Chris Baggett, Lisa M. Wruck, Patricia P. Chang, Scott D. Solomon, Eyal Shahar, Hanyu Ni, Wayne D. Rosamond, Gerardo Heiss

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Background-An algorithm to classify heart failure (HF) end points inclusive of contemporary measures of biomarkers and echocardiography was recently proposed by an international expert panel. Our objective was to assess agreement of HF classification by this contemporaneous algorithm with that by a standardized physician reviewer panel, when applied to data abstracted from community-based hospital records. Methods and Results-During 2005-2007, all hospitalizations were identified from 4 US communities under surveillance as part of the Atherosclerosis Risk in Communities (ARIC) study. Potential HF hospitalizations were sampled by International Classification of Diseases discharge codes and demographics from men and women aged ≥55 years. The HF classification algorithm was automated and applied to 2729 (n=13 854 weighted hospitalizations) hospitalizations in which either brain natriuretic peptide measures or ejection fraction were documented (mean age, 75 years). There were 1403 (54%; n=7534 weighted) events classified as acute decompensated HF by the automated algorithm, and 1748 (68%; n=9276 weighted) such events by the ARIC reviewer panel. The chance-corrected agreement between acute decompensated HF by physician reviewer panel and the automated algorithm was moderate (κ=0.39). Sensitivity and specificity of the automated algorithm with ARIC reviewer panel as the referent standard were 0.68 (95% confidence interval, 0.67-0.69) and 0.75 (95% confidence interval, 0.74-0.76), respectively. Conclusions-Although the automated classification improved efficiency and decreased costs, its accuracy in classifying HF hospitalizations was modest compared with a standardized physician reviewer panel.

Original languageEnglish (US)
Pages (from-to)719-726
Number of pages8
JournalCirculation: Heart Failure
Volume6
Issue number4
DOIs
StatePublished - Jul 2013

Fingerprint

Atherosclerosis
Heart Failure
Physicians
Hospitalization
Confidence Intervals
Hospital Records
Brain Natriuretic Peptide
Community Hospital
International Classification of Diseases
Echocardiography
Biomarkers
Demography
Costs and Cost Analysis
Sensitivity and Specificity

Keywords

  • ARIC
  • BNP
  • Classification
  • Ejection fraction
  • Heart failure

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine
  • Medicine(all)

Cite this

Classification of acute decompensated heart failure an automated algorithm compared with a physician reviewer panel : The atherosclerosis risk in communities study. / Loehr, Laura R.; Agarwal, Sunil K.; Baggett, Chris; Wruck, Lisa M.; Chang, Patricia P.; Solomon, Scott D.; Shahar, Eyal; Ni, Hanyu; Rosamond, Wayne D.; Heiss, Gerardo.

In: Circulation: Heart Failure, Vol. 6, No. 4, 07.2013, p. 719-726.

Research output: Contribution to journalArticle

Loehr, Laura R. ; Agarwal, Sunil K. ; Baggett, Chris ; Wruck, Lisa M. ; Chang, Patricia P. ; Solomon, Scott D. ; Shahar, Eyal ; Ni, Hanyu ; Rosamond, Wayne D. ; Heiss, Gerardo. / Classification of acute decompensated heart failure an automated algorithm compared with a physician reviewer panel : The atherosclerosis risk in communities study. In: Circulation: Heart Failure. 2013 ; Vol. 6, No. 4. pp. 719-726.
@article{43038e3b8ba748fd822e2dcfd0230660,
title = "Classification of acute decompensated heart failure an automated algorithm compared with a physician reviewer panel: The atherosclerosis risk in communities study",
abstract = "Background-An algorithm to classify heart failure (HF) end points inclusive of contemporary measures of biomarkers and echocardiography was recently proposed by an international expert panel. Our objective was to assess agreement of HF classification by this contemporaneous algorithm with that by a standardized physician reviewer panel, when applied to data abstracted from community-based hospital records. Methods and Results-During 2005-2007, all hospitalizations were identified from 4 US communities under surveillance as part of the Atherosclerosis Risk in Communities (ARIC) study. Potential HF hospitalizations were sampled by International Classification of Diseases discharge codes and demographics from men and women aged ≥55 years. The HF classification algorithm was automated and applied to 2729 (n=13 854 weighted hospitalizations) hospitalizations in which either brain natriuretic peptide measures or ejection fraction were documented (mean age, 75 years). There were 1403 (54{\%}; n=7534 weighted) events classified as acute decompensated HF by the automated algorithm, and 1748 (68{\%}; n=9276 weighted) such events by the ARIC reviewer panel. The chance-corrected agreement between acute decompensated HF by physician reviewer panel and the automated algorithm was moderate (κ=0.39). Sensitivity and specificity of the automated algorithm with ARIC reviewer panel as the referent standard were 0.68 (95{\%} confidence interval, 0.67-0.69) and 0.75 (95{\%} confidence interval, 0.74-0.76), respectively. Conclusions-Although the automated classification improved efficiency and decreased costs, its accuracy in classifying HF hospitalizations was modest compared with a standardized physician reviewer panel.",
keywords = "ARIC, BNP, Classification, Ejection fraction, Heart failure",
author = "Loehr, {Laura R.} and Agarwal, {Sunil K.} and Chris Baggett and Wruck, {Lisa M.} and Chang, {Patricia P.} and Solomon, {Scott D.} and Eyal Shahar and Hanyu Ni and Rosamond, {Wayne D.} and Gerardo Heiss",
year = "2013",
month = "7",
doi = "10.1161/CIRCHEARTFAILURE.112.000195",
language = "English (US)",
volume = "6",
pages = "719--726",
journal = "Circulation: Heart Failure",
issn = "1941-3297",
publisher = "Lippincott Williams and Wilkins",
number = "4",

}

TY - JOUR

T1 - Classification of acute decompensated heart failure an automated algorithm compared with a physician reviewer panel

T2 - The atherosclerosis risk in communities study

AU - Loehr, Laura R.

AU - Agarwal, Sunil K.

AU - Baggett, Chris

AU - Wruck, Lisa M.

AU - Chang, Patricia P.

AU - Solomon, Scott D.

AU - Shahar, Eyal

AU - Ni, Hanyu

AU - Rosamond, Wayne D.

AU - Heiss, Gerardo

PY - 2013/7

Y1 - 2013/7

N2 - Background-An algorithm to classify heart failure (HF) end points inclusive of contemporary measures of biomarkers and echocardiography was recently proposed by an international expert panel. Our objective was to assess agreement of HF classification by this contemporaneous algorithm with that by a standardized physician reviewer panel, when applied to data abstracted from community-based hospital records. Methods and Results-During 2005-2007, all hospitalizations were identified from 4 US communities under surveillance as part of the Atherosclerosis Risk in Communities (ARIC) study. Potential HF hospitalizations were sampled by International Classification of Diseases discharge codes and demographics from men and women aged ≥55 years. The HF classification algorithm was automated and applied to 2729 (n=13 854 weighted hospitalizations) hospitalizations in which either brain natriuretic peptide measures or ejection fraction were documented (mean age, 75 years). There were 1403 (54%; n=7534 weighted) events classified as acute decompensated HF by the automated algorithm, and 1748 (68%; n=9276 weighted) such events by the ARIC reviewer panel. The chance-corrected agreement between acute decompensated HF by physician reviewer panel and the automated algorithm was moderate (κ=0.39). Sensitivity and specificity of the automated algorithm with ARIC reviewer panel as the referent standard were 0.68 (95% confidence interval, 0.67-0.69) and 0.75 (95% confidence interval, 0.74-0.76), respectively. Conclusions-Although the automated classification improved efficiency and decreased costs, its accuracy in classifying HF hospitalizations was modest compared with a standardized physician reviewer panel.

AB - Background-An algorithm to classify heart failure (HF) end points inclusive of contemporary measures of biomarkers and echocardiography was recently proposed by an international expert panel. Our objective was to assess agreement of HF classification by this contemporaneous algorithm with that by a standardized physician reviewer panel, when applied to data abstracted from community-based hospital records. Methods and Results-During 2005-2007, all hospitalizations were identified from 4 US communities under surveillance as part of the Atherosclerosis Risk in Communities (ARIC) study. Potential HF hospitalizations were sampled by International Classification of Diseases discharge codes and demographics from men and women aged ≥55 years. The HF classification algorithm was automated and applied to 2729 (n=13 854 weighted hospitalizations) hospitalizations in which either brain natriuretic peptide measures or ejection fraction were documented (mean age, 75 years). There were 1403 (54%; n=7534 weighted) events classified as acute decompensated HF by the automated algorithm, and 1748 (68%; n=9276 weighted) such events by the ARIC reviewer panel. The chance-corrected agreement between acute decompensated HF by physician reviewer panel and the automated algorithm was moderate (κ=0.39). Sensitivity and specificity of the automated algorithm with ARIC reviewer panel as the referent standard were 0.68 (95% confidence interval, 0.67-0.69) and 0.75 (95% confidence interval, 0.74-0.76), respectively. Conclusions-Although the automated classification improved efficiency and decreased costs, its accuracy in classifying HF hospitalizations was modest compared with a standardized physician reviewer panel.

KW - ARIC

KW - BNP

KW - Classification

KW - Ejection fraction

KW - Heart failure

UR - http://www.scopus.com/inward/record.url?scp=84883570707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883570707&partnerID=8YFLogxK

U2 - 10.1161/CIRCHEARTFAILURE.112.000195

DO - 10.1161/CIRCHEARTFAILURE.112.000195

M3 - Article

C2 - 23650310

AN - SCOPUS:84883570707

VL - 6

SP - 719

EP - 726

JO - Circulation: Heart Failure

JF - Circulation: Heart Failure

SN - 1941-3297

IS - 4

ER -