Development and Validation of eRADAR: A Tool Using EHR Data to Detect Unrecognized Dementia

Abstract

OBJECTIVES Early recognition of dementia would allow patients and their families to receive care earlier in the disease process, potentially improving care management and patient outcomes, yet nearly half of patients with dementia are undiagnosed. Our aim was to develop and validate an electronic health record (EHR)‐based tool to help detect patients with unrecognized dementia (EHR Risk of Alzheimer's and Dementia Assessment Rule [eRADAR]). DESIGN Retrospective cohort study. SETTING Kaiser Permanente Washington (KPWA), an integrated healthcare delivery system. PARTICIPANTS A total of 16 665 visits among 4330 participants in the Adult Changes in Thought (ACT) study, who undergo a comprehensive process to detect and diagnose dementia every 2 years and have linked KPWA EHR data, divided into development (70%) and validation (30%) samples. MEASUREMENTS EHR predictors included demographics, medical diagnoses, vital signs, healthcare utilization, and medications within the previous 2 years. Unrecognized dementia was defined as detection in ACT before documentation in the KPWA EHR (ie, lack of dementia or memory loss diagnosis codes or dementia medication fills). RESULTS Overall, 1015 ACT visits resulted in a diagnosis of incident dementia, of which 498 (49%) were unrecognized in the KPWA EHR. The final 31‐predictor model included markers of dementia‐related symptoms (eg, psychosis diagnoses, antidepressant fills), healthcare utilization pattern (eg, emergency department visits), and dementia risk factors (eg, cerebrovascular disease, diabetes). Discrimination was good in the development (C statistic = .78; 95% confidence interval [CI] = .76‐.81) and validation (C statistic = .81; 95% CI = .78‐.84) samples, and calibration was good based on plots of predicted vs observed risk. If patients with scores in the top 5% were flagged for additional evaluation, we estimate that 1 in 6 would have dementia. CONCLUSION The eRADAR tool uses existing EHR data to detect patients with good accuracy who may have unrecognized dementia. J Am Geriatr Soc 68:103–111, 2019

Patient and caregiver perspectives on a tool to identify undiagnosed dementia: A qualitative study

“…(2,3,18) Our team has developed a tool called the electronic health record Risk of Alzheimer's and Dementia Assessment Rule (eRADAR) that uses electronic health record (EHR) data (such as dementia-related symptoms, healthcare utilization patterns, and dementia risk factors) to identify patients who may have undiagnosed dementia, which could address some barriers to diagnosis. (19) Use of this tool could provide an alternative to routine screening for dementia by supporting further evaluation of those patients identified as being at particularly high risk for undiagnosed dementia.…”

“…(14,15) Clinicians may have difficulty recognizing symptoms during brief clinical encounters, particularly early in the disease process, or may focus on physical symptoms more than cognitive problems and concerns. (3,(16)(17)(18)(19) System-level barriers also exist such as competing priorities during clinical encounters. (3) To overcome these barriers, several studies have called for standardized tools and information technology resources to support earlier recognition of dementia in primary care.…”

Cognitive measures lacking in EHR prior to dementia or Alzheimer's disease diagnosis

“…Missing cognitive data, particularly when heightened among demographic subsets, affects not only quality of patient care, but also quality of EHR databases increasingly used for research and clinical decision‐making algorithms. Researchers have developed models to identify patients with high risk of AD using various EHR data including the presence of cognitive symptoms in EHR 19–21,37 . Suboptimal data inputs reduce the accuracy and generalizability of EHR‐based models.…”

“…Researchers have developed models to identify patients with high risk of AD using various EHR data including the presence of cognitive symptoms in EHR. 19 , 20 , 21 , 37 Suboptimal data inputs reduce the accuracy and generalizability of EHR‐based models. Large‐scale initiatives to facilitate EHR embedded pragmatic clinical trials face challenges in obtaining valid dementia outcome measures.…”

A Deep Neural Network-Based Method for Prediction of Dementia Using Big Data

“…The first screening was accurate, but the second achieved relatively low performance. Barnes et al [ 36 ] developed an electronic health record (EHR)-based tool to detect patients with unrecognized dementia. Among 16,655 records, 15,640 indicated no dementia, 498 indicated unrecognized dementia, and 517 indicated recognized dementia.…”