Blood biomarkers predict conversion from cognitively stable to mild cognitive impairment or Alzheimer's disease in Down syndrome at 16-month follow-up in ABC-DS

Authors

• Fan Zhang, University of North Texas Health Science CenterFollow
• Melissa Petersen, University of North Texas Health Science Center
• Mark Mapstone, University of California Irvine
• James Hall, University of North Texas Health Science Center
• Benjamin Handen, University of Pittsburgh
• Brad Christian, University of Wisconsin-Madison
• Elizabeth Head, University of California Irvine
• Herminia Diana Rosas, Harvard University
• Florence Lai, Harvard University
• Joseph H. Lee, Columbia University Medical Center
• Sharon J. Krinsky-McHale, New York State Office for People with Developmental Disabilities
• Frederick A. Schmitt, University of KentuckyFollow
• Jordan Harp, University of KentuckyFollow
• Christy Hom, University of California Irvine
• Ira T. Lott, University of California Irvine
• Sigan Hartley, University of Wisconsin-Madison
• Shahid Zaman, University of Cambridge
• Beau M. Ances, Washington University School of Medicine in St. Louis
• Lauren Ptomey, University of Kansas
• Jeffrey M. Burns, University of Kansas
• Ann D. Cohen, University of Pittsburgh
• Adam M. Brickman, Columbia University
• Sid E.O’ Bryant, University of North Texas Health Science Center

Abstract

INTRODUCTION: Individuals with Down syndrome (DS) face high risk for Alzheimer's disease (AD), yet presymptomatic detection of cognitive decline is hindered by lifelong intellectual disability. METHODS: Using data from the Alzheimer's Biomarker Consortium–Down Syndrome (ABC-DS), blood samples from 246 participants were analyzed, yielding 404 longitudinal observations (45 Converters, 359 Stable) collected at 0, 16, and 32 months were analyzed. A Support Vector Machine was trained on 25 plasma biomarkers spanning neurodegeneration, inflammation, and vascular health, along with demographic factors (age, sex, ethnicity, karyotype, apolipoprotein E [APOE ε4]). Batch-effect correction and feature selection were applied, resulting in 13 key markers. RESULTS: The refined model achieved 92.4% sensitivity, 59.9% specificity, and an area under the curve (AUC) of 77.9%, accurately identifying individuals at risk of cognitive decline up to 16 months before clinical progression. DISCUSSION: This multi-domain, blood-based machine learning approach demonstrates that plasma biomarkers are valuable non-invasive tools for early detection and risk stratification of cognitive decline in DS.

Document Type

Article

Publication Date

7-14-2026

Notes/Citation Information

Publisher Copyright: © 2026 The Author(s). Alzheimer's & Dementia published by Wiley Periodicals LLC on behalf of Alzheimer's Association.

Digital Object Identifier (DOI)

10.1002/alz.71659

Archival?

Archival

Repository Citation

Zhang, Fan; Petersen, Melissa; Mapstone, Mark; Hall, James; Handen, Benjamin; Christian, Brad; Head, Elizabeth; Rosas, Herminia Diana; Lai, Florence; Lee, Joseph H.; Krinsky-McHale, Sharon J.; Schmitt, Frederick A.; Harp, Jordan; Hom, Christy; Lott, Ira T.; Hartley, Sigan; Zaman, Shahid; Ances, Beau M.; Ptomey, Lauren; Burns, Jeffrey M.; Cohen, Ann D.; Brickman, Adam M.; and Bryant, Sid E.O’, "Blood biomarkers predict conversion from cognitively stable to mild cognitive impairment or Alzheimer's disease in Down syndrome at 16-month follow-up in ABC-DS" (2026). Psychology Faculty Publications. 276.
https://uknowledge.uky.edu/psychology_facpub/276