Regency EF
Classifying Symptom Trajectories in Patients with Mild Cognitive Impairment (304068)
*Sudeshna Paul, Emory UniversityWhitney Wharton, Emory University
Keywords: cognitive, multivariate, symptoms, mixed effects, clustering
Dementia due to Alzheimer’s disease (AD) is an irreversible, progressive brain disorder that destroys cognitive skills, and, eventually, the ability to carry out the simplest tasks of everyday life. The disease course may include a conversion from normal to impaired cognition state to mild cognitive impairment (MCI) and finally, AD. Different stages of AD are characterized by unique cognitive, behavior and motor symptoms. Motivated by the National Alzheimer's Coordinating Center’s uniform database, we seek to model the alterations in symptoms trajectories in relation to disease progression on a sample of 2,127 adult participants (age >= 40 years) diagnosed with MCI at visit 1, with = 5 years followup. We characterized their multivariate symptom trajectories using mixed effects modeling and used a model-based clustering approach for classification, after accounting for covariates (fixed and time-varying) and shifts in disease stage. Preliminary results identified distinct clusters based on symptom severity and time trends. This research has important clinical implications in symptom management strategies and designing early interventions to slow down progression of AD.