Machine learning models identify predictive features of patient mortality across dementia types

Cohort characteristics and patient mortality across dementia types

Data for this study was obtained from the National Alzheimer’s Coordinating Center (NACC) database13, which spans 39 past and present Alzheimer’s Disease Centers (ADCs) across the United States. The NACC collects, audits, and distributes ADC-derived data across the U.S. The NACC data release used for this study included 45,275 unique participants and 163,782 visit records between 2005 and 2021.

Data were extracted for various dementia severity levels (Table 1 and Supplementary Table 3). The mean age at visit increased from 73 years for those who had normal cognition (n = 16,379), to 76 years for those with dementia (n = 19,186). The percentage of females was 64.9% among normal cognition patients, compared to 52.0% among demented patients. For impaired-not-MCI (n = 1840), MCI (n = 7870), and…

Read more…