Assessing polyomic risk to predict Alzheimer's disease using a machine learning model
We developed a polyomic model to predict AD and age-at-onset using omics and medication use data from EHR. We identified GFAP and CXCL17 proteins to be the strongest predictors of AD, besides APOE alleles. "AD-by-proxy" cases, if used in training, do not improve AD prediction. Proteomics was the most informative modality overall for affection status and AAO prediction.
Authors
- Christoph Lange (ORCID: https://orcid.org/0000-0003-2620-1030)
- Kristina Mullin
- Georg Hahn (ORCID: https://orcid.org/0000-0001-6008-2720)
- Dmitry Prokopenko (ORCID: https://orcid.org/0000-0002-1844-5652)
- Lucas Fishbein
- Julian Willett (ORCID: https://orcid.org/0000-0002-8103-0329)
- Rudolph E. Tanzi (ORCID: https://orcid.org/0000-0002-7032-1454)
- Julian Hecker (ORCID: https://orcid.org/0000-0001-7918-089X)
- Younjung Choi
- Mohammad Waqas (ORCID: https://orcid.org/0000-0002-4633-4167)
- Tiffany Ngai
Institutions
- Brigham and Women's Hospital (US)
- Harvard University (US)
- University of Waterloo (CA)
- Massachusetts General Hospital (US)
- Center for Pain and the Brain (US)
Publication Details
- Journal
- Alzheimer s & Dementia
- Published
- 2024-11-07
- DOI
- https://doi.org/10.1002/alz.14319
- Citations
- 4
- Primary Topic
- Metabolomics and Mass Spectrometry Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.94
Funders
- Cure Alzheimer's Fund
- National Institutes of Health