The National Alzheimer’s Coordinating Center (NACC) is responsible for maintaining a database of clinical information collected from the 29 NIA-funded Alzheimer’s Disease Centers (ADCs)​​. Each center collects and manages patient information in a site-specific way, requiring data harmonization on the part of NACC. We created a combined dataset from ADCs 1-7, which included genetic and AD diagnosis information for 5869 subjects (2494 AD cases, 2021 controls, and 1354 missing/unknown) before QC.

For our testing dataset we used the ADRC housed at the University of Pittsburgh, the largest non-NACC ADGC dataset. This input dataset contained 2212 subjects before QC.