Premium
Predicting sporadic Alzheimer's disease progression via inherited Alzheimer's disease‐informed machine‐learning
Author(s) -
Franzmeier Nicolai,
Koutsouleris Nikolaos,
Benzinger Tammie,
Goate Alison,
Karch Celeste M.,
Fagan Anne M.,
McDade Eric,
Duering Marco,
Dichgans Martin,
Levin Johannes,
Gordon Brian A.,
Lim Yen Ying,
Masters Colin L.,
Rossor Martin,
Fox Nick C.,
O'Connor Antoinette,
Chhatwal Jasmeer,
Salloway Stephen,
Danek Adrian,
Hassenstab Jason,
Schofield Peter R.,
Morris John C.,
Bateman Randall J.,
Ewers Michael
Publication year - 2020
Publication title -
alzheimer's and dementia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.713
H-Index - 118
eISSN - 1552-5279
pISSN - 1552-5260
DOI - 10.1002/alz.12032
Subject(s) - biomarker , cognitive decline , magnetic resonance imaging , disease , positron emission tomography , cognition , alzheimer's disease , neuroimaging , alzheimer's disease neuroimaging initiative , medicine , sample size determination , oncology , psychology , psychiatry , dementia , nuclear medicine , biology , radiology , statistics , biochemistry , mathematics
Developing cross‐validated multi‐biomarker models for the prediction of the rate of cognitive decline in Alzheimer's disease (AD) is a critical yet unmet clinical challenge. Methods We applied support vector regression to AD biomarkers derived from cerebrospinal fluid, structural magnetic resonance imaging (MRI), amyloid‐PET and fluorodeoxyglucose positron‐emission tomography (FDG‐PET) to predict rates of cognitive decline. Prediction models were trained in autosomal‐dominant Alzheimer's disease (ADAD, n = 121) and subsequently cross‐validated in sporadic prodromal AD (n = 216). The sample size needed to detect treatment effects when using model‐based risk enrichment was estimated. Results A model combining all biomarker modalities and established in ADAD predicted the 4‐year rate of decline in global cognition (R 2 = 24%) and memory (R 2 = 25%) in sporadic AD. Model‐based risk‐enrichment reduced the sample size required for detecting simulated intervention effects by 50%–75%. Discussion Our independently validated machine‐learning model predicted cognitive decline in sporadic prodromal AD and may substantially reduce sample size needed in clinical trials in AD.