Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Development of Both a Risk Prediction Model for Conversion to Alzheimer’s Disease and Prototype Clinical Dashboard: A Prototype CDS Tool for PCPs to Monitor Cognitive Impairment
ABSTRACT
Background:
: Primary care physicians (PCPs) have substantial obstacles to detecting Alzheimer’s Disease (AD) including lack of time and ability to properly screen those with cognitive impairment. The solution for this project involves designing an algorithm based on known risk factors, such as depression ((as measured by a screening tool called Patient Health Questionnaire-9 (PHQ-9)), level of exercise, education and Montreal Cognitive Assessment (MoCA. Using a Tableau dashboard embedded in a clinic electronic medical record (EMR), the solution will visually display critical indicators to the clinician and flag changes in health status.
Objective:
The purpose of this report is to describe a risk prediction model for cognitive impairment and potential conversion to AD and display the model in a prototype clinical dashboard (Nair-dashboard) for use as a clinical decision support (CDS) tool. Implementation strategies will also be discussed.
Methods:
This model was developed using data from a retrospective cohort of 960 patients with varying degrees of cognitive impairment who were seen in a primary outpatient clinic between 2000 and 2012 in Chicago (IL). All eligible patients were identified by a PCP. The clinic uses Cerbo EMR.
Results:
The model had good discrimination, indicating good ability to separate those who convert to AD from those who do not. The Nair-dashboard produced visual displays for individual and overall risk factors of conversion to AD as a percentage. Additionally, patients with highest overall risk of conversion based on pre-set thresholds were also displayed. Errors were found with MoCA score trend lines and further troubleshooting was inconclusive.
Conclusions:
Cognitive impairment is a complex scenario, and the algorithm and dashboard can be the first steps to addressing some of these issues. The inherent limitations must be recognized, and future work would entail improving the performance.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.