Towards prevention of acute syndromes

Electronic identification of at-risk patients during hospital admission

A. Ahmed, C. Thongprayoon, Brian W Pickering, A. Akhoundi, G. Wilson, D. Pieczkiewicz, Vitaly D Herasevich

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Background: Identifying patients at risk for acute respiratory distress syndrome (ARDS) before their admission to intensive care is crucial to prevention and treatment. The objective of this study is to determine the performance of an automated algorithm for identifying selected ARDS predisposing conditions at the time of hospital admission. Methods: This secondary analysis of a prospective cohort study included 3,005 patients admitted to hospital between January 1 and December 31, 2010. The automated algorithm for five ARDS predisposing conditions (sepsis, pneumonia, aspiration, acute pancreatitis, and shock) was developed through a series of queries applied to institutional electronic medical record databases. The automated algorithm was derived and refined in a derivation cohort of 1,562 patients and subsequently validated in an independent cohort of 1,443 patients. The sensitivity, specificity, and positive and negative predictive values of an automated algorithm to identify ARDS risk factors were compared with another two independent data extraction strategies, including manual data extraction and ICD-9 code search. The reference standard was defined as the agreement between the ICD-9 code, automated and manual data extraction. Results: Compared to the reference standard, the automated algorithm had higher sensitivity than manual data extraction for identifying a case of sepsis (95% vs. 56%), aspiration (63% vs. 42%), acute pancreatitis (100% vs. 70%), pneumonia (93% vs. 62%) and shock (77% vs. 41%) with similar specificity except for sepsis and pneumonia (90% vs. 98% for sepsis and 95% vs. 99% for pneumonia). The PPV for identifying these five acute conditions using the automated algorithm ranged from 65% for pneumonia to 91 % for acute pancreatitis, whereas the NPV for the automated algorithm ranged from 99% to 100%. Conclusion: A rule-based electronic data extraction can reliably and accurately identify patients at risk of ARDS at the time of hospital admission.

Original languageEnglish (US)
Pages (from-to)58-72
Number of pages15
JournalApplied Clinical Informatics
Volume5
Issue number1
DOIs
StatePublished - 2014

Fingerprint

Adult Respiratory Distress Syndrome
International Classification of Diseases
Sepsis
Pneumonia
Pancreatitis
Shock
Electronic medical equipment
Aspiration Pneumonia
Electronic Health Records
Critical Care
Cohort Studies
Databases
Prospective Studies
Sensitivity and Specificity

Keywords

  • ARDS
  • Electronic search
  • EMR
  • Risk factor

ASJC Scopus subject areas

  • Health Informatics
  • Computer Science Applications
  • Health Information Management

Cite this

Towards prevention of acute syndromes : Electronic identification of at-risk patients during hospital admission. / Ahmed, A.; Thongprayoon, C.; Pickering, Brian W; Akhoundi, A.; Wilson, G.; Pieczkiewicz, D.; Herasevich, Vitaly D.

In: Applied Clinical Informatics, Vol. 5, No. 1, 2014, p. 58-72.

Research output: Contribution to journalArticle

@article{1aa1c72232ae4af18441052cdeb27342,
title = "Towards prevention of acute syndromes: Electronic identification of at-risk patients during hospital admission",
abstract = "Background: Identifying patients at risk for acute respiratory distress syndrome (ARDS) before their admission to intensive care is crucial to prevention and treatment. The objective of this study is to determine the performance of an automated algorithm for identifying selected ARDS predisposing conditions at the time of hospital admission. Methods: This secondary analysis of a prospective cohort study included 3,005 patients admitted to hospital between January 1 and December 31, 2010. The automated algorithm for five ARDS predisposing conditions (sepsis, pneumonia, aspiration, acute pancreatitis, and shock) was developed through a series of queries applied to institutional electronic medical record databases. The automated algorithm was derived and refined in a derivation cohort of 1,562 patients and subsequently validated in an independent cohort of 1,443 patients. The sensitivity, specificity, and positive and negative predictive values of an automated algorithm to identify ARDS risk factors were compared with another two independent data extraction strategies, including manual data extraction and ICD-9 code search. The reference standard was defined as the agreement between the ICD-9 code, automated and manual data extraction. Results: Compared to the reference standard, the automated algorithm had higher sensitivity than manual data extraction for identifying a case of sepsis (95{\%} vs. 56{\%}), aspiration (63{\%} vs. 42{\%}), acute pancreatitis (100{\%} vs. 70{\%}), pneumonia (93{\%} vs. 62{\%}) and shock (77{\%} vs. 41{\%}) with similar specificity except for sepsis and pneumonia (90{\%} vs. 98{\%} for sepsis and 95{\%} vs. 99{\%} for pneumonia). The PPV for identifying these five acute conditions using the automated algorithm ranged from 65{\%} for pneumonia to 91 {\%} for acute pancreatitis, whereas the NPV for the automated algorithm ranged from 99{\%} to 100{\%}. Conclusion: A rule-based electronic data extraction can reliably and accurately identify patients at risk of ARDS at the time of hospital admission.",
keywords = "ARDS, Electronic search, EMR, Risk factor",
author = "A. Ahmed and C. Thongprayoon and Pickering, {Brian W} and A. Akhoundi and G. Wilson and D. Pieczkiewicz and Herasevich, {Vitaly D}",
year = "2014",
doi = "10.4338/ACI-2013-07-RA-0045",
language = "English (US)",
volume = "5",
pages = "58--72",
journal = "Applied Clinical Informatics",
issn = "1869-0327",
publisher = "Schattauer GmbH",
number = "1",

}

TY - JOUR

T1 - Towards prevention of acute syndromes

T2 - Electronic identification of at-risk patients during hospital admission

AU - Ahmed, A.

AU - Thongprayoon, C.

AU - Pickering, Brian W

AU - Akhoundi, A.

AU - Wilson, G.

AU - Pieczkiewicz, D.

AU - Herasevich, Vitaly D

PY - 2014

Y1 - 2014

N2 - Background: Identifying patients at risk for acute respiratory distress syndrome (ARDS) before their admission to intensive care is crucial to prevention and treatment. The objective of this study is to determine the performance of an automated algorithm for identifying selected ARDS predisposing conditions at the time of hospital admission. Methods: This secondary analysis of a prospective cohort study included 3,005 patients admitted to hospital between January 1 and December 31, 2010. The automated algorithm for five ARDS predisposing conditions (sepsis, pneumonia, aspiration, acute pancreatitis, and shock) was developed through a series of queries applied to institutional electronic medical record databases. The automated algorithm was derived and refined in a derivation cohort of 1,562 patients and subsequently validated in an independent cohort of 1,443 patients. The sensitivity, specificity, and positive and negative predictive values of an automated algorithm to identify ARDS risk factors were compared with another two independent data extraction strategies, including manual data extraction and ICD-9 code search. The reference standard was defined as the agreement between the ICD-9 code, automated and manual data extraction. Results: Compared to the reference standard, the automated algorithm had higher sensitivity than manual data extraction for identifying a case of sepsis (95% vs. 56%), aspiration (63% vs. 42%), acute pancreatitis (100% vs. 70%), pneumonia (93% vs. 62%) and shock (77% vs. 41%) with similar specificity except for sepsis and pneumonia (90% vs. 98% for sepsis and 95% vs. 99% for pneumonia). The PPV for identifying these five acute conditions using the automated algorithm ranged from 65% for pneumonia to 91 % for acute pancreatitis, whereas the NPV for the automated algorithm ranged from 99% to 100%. Conclusion: A rule-based electronic data extraction can reliably and accurately identify patients at risk of ARDS at the time of hospital admission.

AB - Background: Identifying patients at risk for acute respiratory distress syndrome (ARDS) before their admission to intensive care is crucial to prevention and treatment. The objective of this study is to determine the performance of an automated algorithm for identifying selected ARDS predisposing conditions at the time of hospital admission. Methods: This secondary analysis of a prospective cohort study included 3,005 patients admitted to hospital between January 1 and December 31, 2010. The automated algorithm for five ARDS predisposing conditions (sepsis, pneumonia, aspiration, acute pancreatitis, and shock) was developed through a series of queries applied to institutional electronic medical record databases. The automated algorithm was derived and refined in a derivation cohort of 1,562 patients and subsequently validated in an independent cohort of 1,443 patients. The sensitivity, specificity, and positive and negative predictive values of an automated algorithm to identify ARDS risk factors were compared with another two independent data extraction strategies, including manual data extraction and ICD-9 code search. The reference standard was defined as the agreement between the ICD-9 code, automated and manual data extraction. Results: Compared to the reference standard, the automated algorithm had higher sensitivity than manual data extraction for identifying a case of sepsis (95% vs. 56%), aspiration (63% vs. 42%), acute pancreatitis (100% vs. 70%), pneumonia (93% vs. 62%) and shock (77% vs. 41%) with similar specificity except for sepsis and pneumonia (90% vs. 98% for sepsis and 95% vs. 99% for pneumonia). The PPV for identifying these five acute conditions using the automated algorithm ranged from 65% for pneumonia to 91 % for acute pancreatitis, whereas the NPV for the automated algorithm ranged from 99% to 100%. Conclusion: A rule-based electronic data extraction can reliably and accurately identify patients at risk of ARDS at the time of hospital admission.

KW - ARDS

KW - Electronic search

KW - EMR

KW - Risk factor

UR - http://www.scopus.com/inward/record.url?scp=84893066723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893066723&partnerID=8YFLogxK

U2 - 10.4338/ACI-2013-07-RA-0045

DO - 10.4338/ACI-2013-07-RA-0045

M3 - Article

VL - 5

SP - 58

EP - 72

JO - Applied Clinical Informatics

JF - Applied Clinical Informatics

SN - 1869-0327

IS - 1

ER -