A high-generalizability machine learning framework for predicting the progression of Alzheimer’s disease using limited data

Datasets used in the study

The data used for training, cross-validation, and test in our study were obtained from the ADNI1, ADNI-GO, and ADNI2 datasets in the NA-ADNI database (http://adni.loni.usc.edu/ADNI). The NA-ADNI is a cohort study launched in 2003 as a public–private partnership, led by principal investigator Michael W. Weiner M.D., and carried out across 55 research centers in the USA and Canada. The clinical coordination center of NA-ADNI established a network of clinical sites and developed a plan for the recruitment and retention of subjects, and furthermore prepared the final clinical protocol and informed consent, which is distributed to the sites for local institutional review board (IRB) approval⁶, Subjects were willing and able to undergo test procedures, including neuroimaging and follow-up, and written informed consent was obtained from participants¹⁷. Over 2000…