Premium
F1‐02‐04: GENOMICS AND EPIGENOMICS ANALYSES IN THE EMIF‐AD MULTIMODAL BIOMARKER DISCOVERY STUDY
Author(s) -
Hong Shengjun,
Dobricic Valerija,
Smith Rebecca G.,
Küçükali Fahri,
Kilpert Fabian,
Bos Isabelle,
Vos Stephanie J.B.,
Vandenberghe Rik,
Scheltens Philip,
Engelborghs Sebastiaan,
Frisoni Giovanni B.,
Blin Olivier,
Richardson Jill,
Bordet Régis,
Tsolaki Magda,
Verhey Frans R.J.,
Popp Julius,
Martinez-Lage Pablo,
Lleó Alberto,
Johannsen Peter,
Frölich Lutz,
Baird Alison L.,
Barkhof Frederik,
Quigley Cristina Legido,
Lovestone Simon,
Streffer Johannes,
Visser Pieter Jelle,
Zetterberg Henrik,
Sleegers Kristel,
Van Broeckhoven Christine,
Lun Katie,
Bertram Lars
Publication year - 2018
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 - 10.1016/j.jalz.2018.06.2310
Subject(s) - genome wide association study , epigenomics , epigenetics , dna methylation , biology , epigenome , exome , exome sequencing , genetics , computational biology , genotyping , biomarker discovery , bioinformatics , genotype , single nucleotide polymorphism , proteomics , gene , phenotype , gene expression
These associations were stronger in MCI compared to CN. The multi-variable SVM classifier provided an area under the curve (AUC) of 0.74 6 0.08 in CN (Figure 1) and an AUC of 0.79 6 0.08 in MCI (Figure 2). Conclusions:Amyloid pathology is associated with changes in structural MRI measures in preclinical and prodromal AD. An automated classifier based on clinical and imaging variables can identify the presence of amyloid pathology with a moderate level of accuracy. These results could be used in trial design to pre-screen subjects for enrolment.