Fall Ascertainment and Development of a Risk Prediction Model Using Electronic Medical Records

Caryn E.S. Oshiro, Timothy B. Frankland, A. Gabriela Rosales, Nancy A Perrin, Christina L. Bell, Serena H.Y. Lo, Connie M. Trinacty

Research output: Contribution to journalArticle

Abstract

OBJECTIVES: To examine the use of electronic medical record (EMR) data to ascertain falls and develop a fall risk prediction model in an older population. DESIGN: Retrospective longitudinal study using 10 years of EMR data (2004-2014). A series of 3-year cohorts included members continuously enrolled for a minimum of 3 years, requiring 2 years pre-fall (no previous record of a fall) and a 1-year fall risk period. SETTING: Kaiser Permanente Hawaii, an ambulatory setting. PARTICIPANTS: A total of 57 678 adults, age 60 years and older. MEASUREMENTS: Initial EMR searches were guided by current literature and geriatricians to understand coding sources of falls as our outcome. Falls were captured by two coding sources: International Classification of Diseases, Ninth Revision (ICD-9) codes (E880-889) and/or a fall listed as a “primary reason for visit.” A comprehensive list of EMR predictors of falls were included into prediction models enabling statistical subset selection from many variables and modeling by logistic regression. RESULTS: Although 72% of falls in the training data set were coded as “primary reason for visit,” 22% of falls were coded as ICD-9 and 6% coded as both. About 80% were reported in face-to-face encounters (eg, emergency department). A total of 2164 individuals had a fall in the risk period. Using the 13 key predictors (age, comorbidities, female sex, other mental disorder, walking issues, Parkinson's disease, urinary incontinence, depression, polypharmacy, psychotropic and anticonvulsant medications, osteoarthritis, osteoporosis) identified through LASSO regression, the final model had a sensitivity of 67%, specificity of 69%, positive predictive value of 8%, negative predictive value of 98%, and area under the curve of.74. CONCLUSION: This study demonstrated how the EMR can be used to ascertain falls and develop a fall risk prediction model with moderate sensitivity/specificity. Concurrent work with clinical providers to enhance fall documentation will improve the ability of the EMR to capture falls and consequently may improve the model to predict fall risk.

Original languageEnglish (US)
JournalJournal of the American Geriatrics Society
DOIs
StatePublished - Jan 1 2019

Fingerprint

Electronic Health Records
International Classification of Diseases
Polypharmacy
Sensitivity and Specificity
Aptitude
Urinary Incontinence
Statistical Models
Mental Disorders
Osteoarthritis
Documentation
Anticonvulsants
Osteoporosis
Walking
Area Under Curve
Parkinson Disease
Longitudinal Studies
Hospital Emergency Service
Comorbidity
Retrospective Studies
Logistic Models

Keywords

  • adults
  • EMR
  • falls
  • risk

ASJC Scopus subject areas

  • Geriatrics and Gerontology

Cite this

Fall Ascertainment and Development of a Risk Prediction Model Using Electronic Medical Records. / Oshiro, Caryn E.S.; Frankland, Timothy B.; Rosales, A. Gabriela; Perrin, Nancy A; Bell, Christina L.; Lo, Serena H.Y.; Trinacty, Connie M.

In: Journal of the American Geriatrics Society, 01.01.2019.

Research output: Contribution to journalArticle

Oshiro, Caryn E.S. ; Frankland, Timothy B. ; Rosales, A. Gabriela ; Perrin, Nancy A ; Bell, Christina L. ; Lo, Serena H.Y. ; Trinacty, Connie M. / Fall Ascertainment and Development of a Risk Prediction Model Using Electronic Medical Records. In: Journal of the American Geriatrics Society. 2019.
@article{eaee6dba731c4c30adb909e0efbeef1a,
title = "Fall Ascertainment and Development of a Risk Prediction Model Using Electronic Medical Records",
abstract = "OBJECTIVES: To examine the use of electronic medical record (EMR) data to ascertain falls and develop a fall risk prediction model in an older population. DESIGN: Retrospective longitudinal study using 10 years of EMR data (2004-2014). A series of 3-year cohorts included members continuously enrolled for a minimum of 3 years, requiring 2 years pre-fall (no previous record of a fall) and a 1-year fall risk period. SETTING: Kaiser Permanente Hawaii, an ambulatory setting. PARTICIPANTS: A total of 57 678 adults, age 60 years and older. MEASUREMENTS: Initial EMR searches were guided by current literature and geriatricians to understand coding sources of falls as our outcome. Falls were captured by two coding sources: International Classification of Diseases, Ninth Revision (ICD-9) codes (E880-889) and/or a fall listed as a “primary reason for visit.” A comprehensive list of EMR predictors of falls were included into prediction models enabling statistical subset selection from many variables and modeling by logistic regression. RESULTS: Although 72{\%} of falls in the training data set were coded as “primary reason for visit,” 22{\%} of falls were coded as ICD-9 and 6{\%} coded as both. About 80{\%} were reported in face-to-face encounters (eg, emergency department). A total of 2164 individuals had a fall in the risk period. Using the 13 key predictors (age, comorbidities, female sex, other mental disorder, walking issues, Parkinson's disease, urinary incontinence, depression, polypharmacy, psychotropic and anticonvulsant medications, osteoarthritis, osteoporosis) identified through LASSO regression, the final model had a sensitivity of 67{\%}, specificity of 69{\%}, positive predictive value of 8{\%}, negative predictive value of 98{\%}, and area under the curve of.74. CONCLUSION: This study demonstrated how the EMR can be used to ascertain falls and develop a fall risk prediction model with moderate sensitivity/specificity. Concurrent work with clinical providers to enhance fall documentation will improve the ability of the EMR to capture falls and consequently may improve the model to predict fall risk.",
keywords = "adults, EMR, falls, risk",
author = "Oshiro, {Caryn E.S.} and Frankland, {Timothy B.} and Rosales, {A. Gabriela} and Perrin, {Nancy A} and Bell, {Christina L.} and Lo, {Serena H.Y.} and Trinacty, {Connie M.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1111/jgs.15872",
language = "English (US)",
journal = "Journal of the American Geriatrics Society",
issn = "0002-8614",
publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - Fall Ascertainment and Development of a Risk Prediction Model Using Electronic Medical Records

AU - Oshiro, Caryn E.S.

AU - Frankland, Timothy B.

AU - Rosales, A. Gabriela

AU - Perrin, Nancy A

AU - Bell, Christina L.

AU - Lo, Serena H.Y.

AU - Trinacty, Connie M.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - OBJECTIVES: To examine the use of electronic medical record (EMR) data to ascertain falls and develop a fall risk prediction model in an older population. DESIGN: Retrospective longitudinal study using 10 years of EMR data (2004-2014). A series of 3-year cohorts included members continuously enrolled for a minimum of 3 years, requiring 2 years pre-fall (no previous record of a fall) and a 1-year fall risk period. SETTING: Kaiser Permanente Hawaii, an ambulatory setting. PARTICIPANTS: A total of 57 678 adults, age 60 years and older. MEASUREMENTS: Initial EMR searches were guided by current literature and geriatricians to understand coding sources of falls as our outcome. Falls were captured by two coding sources: International Classification of Diseases, Ninth Revision (ICD-9) codes (E880-889) and/or a fall listed as a “primary reason for visit.” A comprehensive list of EMR predictors of falls were included into prediction models enabling statistical subset selection from many variables and modeling by logistic regression. RESULTS: Although 72% of falls in the training data set were coded as “primary reason for visit,” 22% of falls were coded as ICD-9 and 6% coded as both. About 80% were reported in face-to-face encounters (eg, emergency department). A total of 2164 individuals had a fall in the risk period. Using the 13 key predictors (age, comorbidities, female sex, other mental disorder, walking issues, Parkinson's disease, urinary incontinence, depression, polypharmacy, psychotropic and anticonvulsant medications, osteoarthritis, osteoporosis) identified through LASSO regression, the final model had a sensitivity of 67%, specificity of 69%, positive predictive value of 8%, negative predictive value of 98%, and area under the curve of.74. CONCLUSION: This study demonstrated how the EMR can be used to ascertain falls and develop a fall risk prediction model with moderate sensitivity/specificity. Concurrent work with clinical providers to enhance fall documentation will improve the ability of the EMR to capture falls and consequently may improve the model to predict fall risk.

AB - OBJECTIVES: To examine the use of electronic medical record (EMR) data to ascertain falls and develop a fall risk prediction model in an older population. DESIGN: Retrospective longitudinal study using 10 years of EMR data (2004-2014). A series of 3-year cohorts included members continuously enrolled for a minimum of 3 years, requiring 2 years pre-fall (no previous record of a fall) and a 1-year fall risk period. SETTING: Kaiser Permanente Hawaii, an ambulatory setting. PARTICIPANTS: A total of 57 678 adults, age 60 years and older. MEASUREMENTS: Initial EMR searches were guided by current literature and geriatricians to understand coding sources of falls as our outcome. Falls were captured by two coding sources: International Classification of Diseases, Ninth Revision (ICD-9) codes (E880-889) and/or a fall listed as a “primary reason for visit.” A comprehensive list of EMR predictors of falls were included into prediction models enabling statistical subset selection from many variables and modeling by logistic regression. RESULTS: Although 72% of falls in the training data set were coded as “primary reason for visit,” 22% of falls were coded as ICD-9 and 6% coded as both. About 80% were reported in face-to-face encounters (eg, emergency department). A total of 2164 individuals had a fall in the risk period. Using the 13 key predictors (age, comorbidities, female sex, other mental disorder, walking issues, Parkinson's disease, urinary incontinence, depression, polypharmacy, psychotropic and anticonvulsant medications, osteoarthritis, osteoporosis) identified through LASSO regression, the final model had a sensitivity of 67%, specificity of 69%, positive predictive value of 8%, negative predictive value of 98%, and area under the curve of.74. CONCLUSION: This study demonstrated how the EMR can be used to ascertain falls and develop a fall risk prediction model with moderate sensitivity/specificity. Concurrent work with clinical providers to enhance fall documentation will improve the ability of the EMR to capture falls and consequently may improve the model to predict fall risk.

KW - adults

KW - EMR

KW - falls

KW - risk

UR - http://www.scopus.com/inward/record.url?scp=85062937594&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062937594&partnerID=8YFLogxK

U2 - 10.1111/jgs.15872

DO - 10.1111/jgs.15872

M3 - Article

C2 - 30875089

AN - SCOPUS:85062937594

JO - Journal of the American Geriatrics Society

JF - Journal of the American Geriatrics Society

SN - 0002-8614

ER -