Automated identification of older adults at risk for cognitive decline

Abstract INTRODUCTION Automated models that predict cognitive risk in older adults can aid decisions about which patients to screen in busy primary care settings. METHODS In this retrospective prediction model development study, we conducted formal cognitive testing on 337 older primary care patient...

Full description

Saved in:
Bibliographic Details
Main Authors: Darlene P. Floden, Olivia Hogue, Saket A. Saxena, Anita D. Misra‐Hebert, Alex Milinovich, Michael B. Rothberg, Elizabeth R. Pfoh, Robyn M. Busch, Kamini Krishnan, Robert J. Fox, Michael W. Kattan
Format: Article
Language:English
Published: Wiley 2025-04-01
Series:Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring
Subjects:
Online Access:https://doi.org/10.1002/dad2.70136
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849683248307765248
author Darlene P. Floden
Olivia Hogue
Saket A. Saxena
Anita D. Misra‐Hebert
Alex Milinovich
Michael B. Rothberg
Elizabeth R. Pfoh
Robyn M. Busch
Kamini Krishnan
Robert J. Fox
Michael W. Kattan
author_facet Darlene P. Floden
Olivia Hogue
Saket A. Saxena
Anita D. Misra‐Hebert
Alex Milinovich
Michael B. Rothberg
Elizabeth R. Pfoh
Robyn M. Busch
Kamini Krishnan
Robert J. Fox
Michael W. Kattan
author_sort Darlene P. Floden
collection DOAJ
description Abstract INTRODUCTION Automated models that predict cognitive risk in older adults can aid decisions about which patients to screen in busy primary care settings. METHODS In this retrospective prediction model development study, we conducted formal cognitive testing on 337 older primary care patients to establish cognitive status. We used up to 5 years of prior discrete‐field electronic health record (EHR) data to develop a multivariable prediction model that differentiates patients with impaired versus intact cognition. RESULTS The final model included seven easily extractable variables with known associations to cognitive decline: age, race, pulse, systolic blood pressure, non‐steroidal anti‐inflammatory use, history of mood disorder, and family history of neurological disease. The model demonstrated good discrimination of cognitive status (concordance statistic = 0.72). DISCUSSION The cognitive risk model may be useful clinically to prompt for objective cognitive screening in high‐risk patients. The use of common, discrete variables ensures relative ease of implementation in EHRs. Highlights 337 older primary care patients completed full neuropsychological assessment. Risk modeling used data available in a typical primary care record. The model successfully differentiated patients with/without cognitive impairment. This EHR model offers a passive workflow to identify patients at cognitive risk.
format Article
id doaj-art-db2c4207bdfa422796eea142461d9d1e
institution DOAJ
issn 2352-8729
language English
publishDate 2025-04-01
publisher Wiley
record_format Article
series Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring
spelling doaj-art-db2c4207bdfa422796eea142461d9d1e2025-08-20T03:23:57ZengWileyAlzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring2352-87292025-04-01172n/an/a10.1002/dad2.70136Automated identification of older adults at risk for cognitive declineDarlene P. Floden0Olivia Hogue1Saket A. Saxena2Anita D. Misra‐Hebert3Alex Milinovich4Michael B. Rothberg5Elizabeth R. Pfoh6Robyn M. Busch7Kamini Krishnan8Robert J. Fox9Michael W. Kattan10Section of Neuropsychology Neurological Institute Cleveland Clinic Cleveland Ohio USAQuantitative Health Sciences Lerner Research Institute Cleveland Clinic Cleveland Ohio USACenter for Geriatric Medicine Primary Care Institute Cleveland Clinic Cleveland Ohio USAQuantitative Health Sciences Lerner Research Institute Cleveland Clinic Cleveland Ohio USAQuantitative Health Sciences Lerner Research Institute Cleveland Clinic Cleveland Ohio USADepartment of Internal Medicine Primary Care Institute Cleveland Clinic Cleveland Ohio USADepartment of Internal Medicine Primary Care Institute Cleveland Clinic Cleveland Ohio USASection of Neuropsychology Neurological Institute Cleveland Clinic Cleveland Ohio USASection of Neuropsychology Neurological Institute Cleveland Clinic Cleveland Ohio USAMellen Center for Multiple Sclerosis Neurological Institute Research Office Neurological Institute Cleveland Clinic Cleveland Ohio USAQuantitative Health Sciences Lerner Research Institute Cleveland Clinic Cleveland Ohio USAAbstract INTRODUCTION Automated models that predict cognitive risk in older adults can aid decisions about which patients to screen in busy primary care settings. METHODS In this retrospective prediction model development study, we conducted formal cognitive testing on 337 older primary care patients to establish cognitive status. We used up to 5 years of prior discrete‐field electronic health record (EHR) data to develop a multivariable prediction model that differentiates patients with impaired versus intact cognition. RESULTS The final model included seven easily extractable variables with known associations to cognitive decline: age, race, pulse, systolic blood pressure, non‐steroidal anti‐inflammatory use, history of mood disorder, and family history of neurological disease. The model demonstrated good discrimination of cognitive status (concordance statistic = 0.72). DISCUSSION The cognitive risk model may be useful clinically to prompt for objective cognitive screening in high‐risk patients. The use of common, discrete variables ensures relative ease of implementation in EHRs. Highlights 337 older primary care patients completed full neuropsychological assessment. Risk modeling used data available in a typical primary care record. The model successfully differentiated patients with/without cognitive impairment. This EHR model offers a passive workflow to identify patients at cognitive risk.https://doi.org/10.1002/dad2.70136decision supportdementiaearly diagnosiselectronic health recordmachine learningmild cognitive impairment
spellingShingle Darlene P. Floden
Olivia Hogue
Saket A. Saxena
Anita D. Misra‐Hebert
Alex Milinovich
Michael B. Rothberg
Elizabeth R. Pfoh
Robyn M. Busch
Kamini Krishnan
Robert J. Fox
Michael W. Kattan
Automated identification of older adults at risk for cognitive decline
Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring
decision support
dementia
early diagnosis
electronic health record
machine learning
mild cognitive impairment
title Automated identification of older adults at risk for cognitive decline
title_full Automated identification of older adults at risk for cognitive decline
title_fullStr Automated identification of older adults at risk for cognitive decline
title_full_unstemmed Automated identification of older adults at risk for cognitive decline
title_short Automated identification of older adults at risk for cognitive decline
title_sort automated identification of older adults at risk for cognitive decline
topic decision support
dementia
early diagnosis
electronic health record
machine learning
mild cognitive impairment
url https://doi.org/10.1002/dad2.70136
work_keys_str_mv AT darlenepfloden automatedidentificationofolderadultsatriskforcognitivedecline
AT oliviahogue automatedidentificationofolderadultsatriskforcognitivedecline
AT saketasaxena automatedidentificationofolderadultsatriskforcognitivedecline
AT anitadmisrahebert automatedidentificationofolderadultsatriskforcognitivedecline
AT alexmilinovich automatedidentificationofolderadultsatriskforcognitivedecline
AT michaelbrothberg automatedidentificationofolderadultsatriskforcognitivedecline
AT elizabethrpfoh automatedidentificationofolderadultsatriskforcognitivedecline
AT robynmbusch automatedidentificationofolderadultsatriskforcognitivedecline
AT kaminikrishnan automatedidentificationofolderadultsatriskforcognitivedecline
AT robertjfox automatedidentificationofolderadultsatriskforcognitivedecline
AT michaelwkattan automatedidentificationofolderadultsatriskforcognitivedecline