Integrating the Electronic Self-administered Gerocognitive Examination (eSAGE) With Electronic Health Records (EHR) Data Using Machine Learning (ML) for the Early Detection and Monitoring of Cognitive Impairment in Individuals
Integrating the Electronic Self-administered Gerocognitive Examination (eSAGE) With Electronic Health Records (EHR) Data Using Machine Learning (ML) for the Early Detection and Monitoring of Cognitive Impairment in Individuals
The goal of this observational trial is to leverage the electronic Self-Administered Gerocognitive Examination (eSAGE), a variety of metadata (a set of data that describes and gives information about other data) collected during eSAGE testing, electronic health records (EHR) information, and advanced machine learning (ML) techniques to develop a new tool that can aid in early-stage prediction of individuals with cognitive impairments.
This is a retrospective and prospective record review trial for patients who are followed at the Center for Cognitive and Memory Disorders.
eSAGE assessment data (including cognitive data, behavioral data, timing data and other metadata) as well as varying amount of electronic health records (EHR) data will be collected on all eligible subjects. Machine learning techniques with feature selection will identify important EHR variables to determine what may be useful for the prediction of cognitive impairment.
Based on the EHR analysis additional questions will be added to the eSAGE to make an enhanced eSAGE version (eSAGE+). The goal of the eSAGE+ is to facilitate the identification of cognition impairment, and ultimately have a translational impact on Alzheimer's disease (AD) identification and management.
Inclusion Criteria:
Exclusion Criteria: