Virtual Spectral Decomposition of Plasma Biomarkers for Non-Invasive Detection of Cerebral Amyloid Pathology: A Multi-Channel Framework with Disease-Exclusion Logic
Chandra, S.
Show abstract
BackgroundDetection of cerebral amyloid pathology currently requires amyloid PET imaging ($5,000-$8,000) or cerebrospinal fluid analysis via lumbar puncture, procedures that are inaccessible for population-level screening. The FDA-cleared Lumipulse G pTau217/A{beta}1-42 plasma ratio test (May 2025) represents the first approved blood-based alternative; however, single-ratio approaches cannot distinguish Alzheimers disease (AD) from non-AD neurodegeneration or provide multi-dimensional disease characterization. MethodsWe developed Virtual Spectral Decomposition (VSD), a framework that decomposes plasma biomarker profiles into biologically interpretable diagnostic channels. Four plasma biomarkers--phosphorylated tau-217 (pTau217), amyloid-{beta}42/40 ratio, neurofilament light chain (NfL), and glial fibrillary acidic protein (GFAP)--were measured in 1,139 Alzheimers Disease Neuroimaging Initiative (ADNI) participants. Each biomarker was mapped to a VSD channel representing a distinct pathophysiological axis: tau/amyloid phosphorylation, amyloid clearance, neurodegeneration, and astrocytic activation. Channel weights were calibrated via logistic regression, and performance was evaluated against amyloid PET (UC Berkeley) using 10x5-fold repeated cross-validation. ResultsVSD 4-channel fusion achieved AUC = 0.900 ({+/-}0.018), exceeding pTau217 alone (0.888{+/-}0.022). Optimal sensitivity was 89.7% with 78.1% specificity (NPV = 90.8%). The NfL channel received a negative weight ({beta} = -1.1), functioning as a disease-exclusion signal: elevated neurodegeneration without amyloid-tau coupling actively reduces the AD probability, distinguishing AD from non-AD neurodegeneration. Complementary CSF proteomics analysis (7,008 proteins, 533 participants) identified 17 amyloid-specific proteins (0.24% of the proteome), revealing a 49:1 tau-to-amyloid asymmetry that explains why blood-based tau markers outperform amyloid markers. ConclusionsBlood-based VSD provides an interpretable, multi-channel framework for amyloid detection that incorporates explicit disease-exclusion logic unavailable to single-biomarker approaches. The architecture extends to multi-disease screening, where the same blood specimen could be routed through disease-specific modules for AD, Parkinsons disease, and cancer.
Matching journals
The top 1 journal accounts for 50% of the predicted probability mass.
Similar papers in this journal
- Plasma p-tau181/Aβ 1-42 ratio predicts Aβ-PET status and correlates with CSF-p-tau181/Aβ 1-42 and future cognitive decline 95%
- CSF metabolites associate with CSF tau and improve prediction of Alzheimer's disease status 95%
- Plasma p217+tau vs NAV4694 amyloid and MK6240 tau PET across the Alzheimer continuum 95%
Similar papers in this journal
- Early Syndecan-4 Upregulation Predicts Cognitive and Pathological Trajectories in Alzheimer Disease 95%
- Comparison and aggregation of event sequences across ten cohorts to describe the consensus biomarker evolution in Alzheimer’s disease 95%
- Tau-PET and in vivo Braak-staging as a prognostic marker in Alzheimer’s disease 94%
Similar papers in this journal
- A conformational variant of p53 (U-p53 AZ ) as blood-based biomarker for the prediction of the onset of symptomatic Alzheimer’s disease 95%
- Identifying Proteomic Prognostic Markers for Alzheimer’s Disease with Survival Machine Learning: the Framingham Heart Study 94%
- Continuous Associations Between Remote Self-Administered Cognitive Measures and Imaging Biomarkers of Alzheimer’s Disease 93%
Similar papers in this journal
- A scoping review of remote and unsupervised digital cognitive assessments in preclinical Alzheimer’s disease 93%
- Interpretable deep learning approach for extracting cognitive features from hand-drawn images of intersecting pentagons in older adults 92%
- Machine Learning Prediction of Incidence of Alzheimers Disease Using Large-Scale Administrative Health Data 92%