Derivation and validation of the automated search algorithms to identify cognitive impairment and dementia in electronic health records

Sakusic Amra, John C. O'Horo, Tarun D. Singh, Gregory A. Wilson, Rahul Kashyap, Ronald Carl Petersen, Rosebud O Roberts, John D. Fryer, Alejandro Rabinstein, Ognjen Gajic

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Purpose Long-term cognitive impairment is a common and important problem in survivors of critical illness. We developed electronic search algorithms to identify cognitive impairment and dementia from the electronic medical records (EMRs) that provide opportunity for big data analysis. Materials and methods Eligible patients met 2 criteria. First, they had a formal cognitive evaluation by The Mayo Clinic Study of Aging. Second, they were hospitalized in intensive care unit at our institution between 2006 and 2014. The “criterion standard” for diagnosis was formal cognitive evaluation supplemented by input from an expert neurologist. Using all available EMR data, we developed and improved our algorithms in the derivation cohort and validated them in the independent validation cohort. Results Of 993 participants who underwent formal cognitive testing and were hospitalized in intensive care unit, we selected 151 participants at random to form the derivation and validation cohorts. The automated electronic search algorithm for cognitive impairment was 94.3% sensitive and 93.0% specific. The search algorithms for dementia achieved respective sensitivity and specificity of 97% and 99%. EMR search algorithms significantly outperformed International Classification of Diseases codes. Conclusions Automated EMR data extractions for cognitive impairment and dementia are reliable and accurate and can serve as acceptable and efficient alternatives to time-consuming manual data review.

Original languageEnglish (US)
Pages (from-to)202-205
Number of pages4
JournalJournal of Critical Care
Volume37
DOIs
StatePublished - Feb 1 2017

Fingerprint

Electronic Health Records
Dementia
Intensive Care Units
International Classification of Diseases
Critical Illness
Survivors
Cognitive Dysfunction
Sensitivity and Specificity

Keywords

  • Cognitive decline
  • Cognitive impairment
  • Critical illness
  • Dementia
  • Electronic medical records
  • Electronic search strategy

ASJC Scopus subject areas

  • Critical Care and Intensive Care Medicine

Cite this

Derivation and validation of the automated search algorithms to identify cognitive impairment and dementia in electronic health records. / Amra, Sakusic; O'Horo, John C.; Singh, Tarun D.; Wilson, Gregory A.; Kashyap, Rahul; Petersen, Ronald Carl; Roberts, Rosebud O; Fryer, John D.; Rabinstein, Alejandro; Gajic, Ognjen.

In: Journal of Critical Care, Vol. 37, 01.02.2017, p. 202-205.

Research output: Contribution to journalArticle

@article{db767abe502f48babff7530fe03ef6a7,
title = "Derivation and validation of the automated search algorithms to identify cognitive impairment and dementia in electronic health records",
abstract = "Purpose Long-term cognitive impairment is a common and important problem in survivors of critical illness. We developed electronic search algorithms to identify cognitive impairment and dementia from the electronic medical records (EMRs) that provide opportunity for big data analysis. Materials and methods Eligible patients met 2 criteria. First, they had a formal cognitive evaluation by The Mayo Clinic Study of Aging. Second, they were hospitalized in intensive care unit at our institution between 2006 and 2014. The “criterion standard” for diagnosis was formal cognitive evaluation supplemented by input from an expert neurologist. Using all available EMR data, we developed and improved our algorithms in the derivation cohort and validated them in the independent validation cohort. Results Of 993 participants who underwent formal cognitive testing and were hospitalized in intensive care unit, we selected 151 participants at random to form the derivation and validation cohorts. The automated electronic search algorithm for cognitive impairment was 94.3{\%} sensitive and 93.0{\%} specific. The search algorithms for dementia achieved respective sensitivity and specificity of 97{\%} and 99{\%}. EMR search algorithms significantly outperformed International Classification of Diseases codes. Conclusions Automated EMR data extractions for cognitive impairment and dementia are reliable and accurate and can serve as acceptable and efficient alternatives to time-consuming manual data review.",
keywords = "Cognitive decline, Cognitive impairment, Critical illness, Dementia, Electronic medical records, Electronic search strategy",
author = "Sakusic Amra and O'Horo, {John C.} and Singh, {Tarun D.} and Wilson, {Gregory A.} and Rahul Kashyap and Petersen, {Ronald Carl} and Roberts, {Rosebud O} and Fryer, {John D.} and Alejandro Rabinstein and Ognjen Gajic",
year = "2017",
month = "2",
day = "1",
doi = "10.1016/j.jcrc.2016.09.026",
language = "English (US)",
volume = "37",
pages = "202--205",
journal = "Journal of Critical Care",
issn = "0883-9441",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Derivation and validation of the automated search algorithms to identify cognitive impairment and dementia in electronic health records

AU - Amra, Sakusic

AU - O'Horo, John C.

AU - Singh, Tarun D.

AU - Wilson, Gregory A.

AU - Kashyap, Rahul

AU - Petersen, Ronald Carl

AU - Roberts, Rosebud O

AU - Fryer, John D.

AU - Rabinstein, Alejandro

AU - Gajic, Ognjen

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Purpose Long-term cognitive impairment is a common and important problem in survivors of critical illness. We developed electronic search algorithms to identify cognitive impairment and dementia from the electronic medical records (EMRs) that provide opportunity for big data analysis. Materials and methods Eligible patients met 2 criteria. First, they had a formal cognitive evaluation by The Mayo Clinic Study of Aging. Second, they were hospitalized in intensive care unit at our institution between 2006 and 2014. The “criterion standard” for diagnosis was formal cognitive evaluation supplemented by input from an expert neurologist. Using all available EMR data, we developed and improved our algorithms in the derivation cohort and validated them in the independent validation cohort. Results Of 993 participants who underwent formal cognitive testing and were hospitalized in intensive care unit, we selected 151 participants at random to form the derivation and validation cohorts. The automated electronic search algorithm for cognitive impairment was 94.3% sensitive and 93.0% specific. The search algorithms for dementia achieved respective sensitivity and specificity of 97% and 99%. EMR search algorithms significantly outperformed International Classification of Diseases codes. Conclusions Automated EMR data extractions for cognitive impairment and dementia are reliable and accurate and can serve as acceptable and efficient alternatives to time-consuming manual data review.

AB - Purpose Long-term cognitive impairment is a common and important problem in survivors of critical illness. We developed electronic search algorithms to identify cognitive impairment and dementia from the electronic medical records (EMRs) that provide opportunity for big data analysis. Materials and methods Eligible patients met 2 criteria. First, they had a formal cognitive evaluation by The Mayo Clinic Study of Aging. Second, they were hospitalized in intensive care unit at our institution between 2006 and 2014. The “criterion standard” for diagnosis was formal cognitive evaluation supplemented by input from an expert neurologist. Using all available EMR data, we developed and improved our algorithms in the derivation cohort and validated them in the independent validation cohort. Results Of 993 participants who underwent formal cognitive testing and were hospitalized in intensive care unit, we selected 151 participants at random to form the derivation and validation cohorts. The automated electronic search algorithm for cognitive impairment was 94.3% sensitive and 93.0% specific. The search algorithms for dementia achieved respective sensitivity and specificity of 97% and 99%. EMR search algorithms significantly outperformed International Classification of Diseases codes. Conclusions Automated EMR data extractions for cognitive impairment and dementia are reliable and accurate and can serve as acceptable and efficient alternatives to time-consuming manual data review.

KW - Cognitive decline

KW - Cognitive impairment

KW - Critical illness

KW - Dementia

KW - Electronic medical records

KW - Electronic search strategy

UR - http://www.scopus.com/inward/record.url?scp=85006312755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006312755&partnerID=8YFLogxK

U2 - 10.1016/j.jcrc.2016.09.026

DO - 10.1016/j.jcrc.2016.09.026

M3 - Article

C2 - 27969571

AN - SCOPUS:85006312755

VL - 37

SP - 202

EP - 205

JO - Journal of Critical Care

JF - Journal of Critical Care

SN - 0883-9441

ER -