# Bloodwork-free Early Screening for Alzheimer’s Disease via Comorbid Pattern Recognition in Electronic Health Records

**Authors:** Dmytro Onishchenko, James A. Mastrianni, Ishanu Chattopadhyay

PMC · DOI: 10.21203/rs.3.rs-8789582/v1 · Research Square · 2026-02-09

## TL;DR

A new AI tool called ZeBRA can predict Alzheimer’s disease up to 10 years before diagnosis using only routine health records, without needing blood tests or imaging.

## Contribution

ZeBRA introduces a scalable, bloodwork-free early screening method for Alzheimer’s using EHR data with high accuracy and interpretability.

## Key findings

- ZeBRA achieved an AUC of 0.93 for 1-year and 0.83 for 10-year prediction of Alzheimer’s disease.
- Higher ZeBRA scores correlated with lower MoCA scores, indicating greater cognitive impairment.
- The model maintains consistent performance across diverse demographic subgroups and over time.

## Abstract

Early identification of Alzheimer’s disease and related dementias (ADRD) remains limited by the need for specialized tests and late-stage diagnosis. The Zero-burden Risk Assessment (ZeBRA) is a AI-driven score that predicts incident ADRD up to a decade before diagnosis, using only routine electronic health record (EHR) data, without laboratory tests, imaging, or questionnaires. Trained on 487,989 cases and 12,483,718 controls from nationwide U.S. insurance claims and validated on held-back samples, and two independent cohorts, ZeBRA achieved AUC = 0.93 and 0.83 for predicting out to 1-year and 10-year horizons respectively, maintaining positive likelihood ratios (>10) at 95% specificity and stable discrimination over time (AUC drop ≈ 1 to 1.3% per year). Performance was consistent across age, sex, race, and ethnicity subgroups. In a limited prospective pilot, higher ZeBRA scores correlated with lower Montreal Cognitive Assessment (MoCA) scores, indicating a greater degree of cognitive impairment (R=-0.78). Compared with prior EHR-based models, ZeBRA provides superior accuracy, cross-site generalizability, and demonstrates noise-corrected interpretability via our novel Λ-OR attrubution metric. Its scalability, low cost, and independence from specialized testing position ZeBRA as a practical tool for population-level early detection and presymptomatic trial enrichment.

## Linked entities

- **Diseases:** Alzheimer’s disease (MONDO:0004975)

## Full-text entities

- **Genes:** MAPT (microtubule associated protein tau) [NCBI Gene 4137] {aka DDPAC, FTD1, FTDP-17, MAPTL, MSTD, MTBT1}
- **Diseases:** benign uterine and breast neoplasms (MESH:D001943), gynecologic disorders (MESH:D005831), dementia (MESH:D003704), amyloid (MESH:C000718787), nervous system diseases (MESH:D009422), cognitive decline (MESH:D003072), hypertension (MESH:D006973), deaths (MESH:D003643), ADHD (MESH:D001289), cerebrovascular disease (MESH:D002561), obesity (MESH:D009765), cognitive symptoms (MESH:D019954), neurodegeneration (MESH:D019636), ovarian cysts (MESH:D010048), congenital malformations (OMIM:163000), endometriosis (MESH:D004715), diabetes (MESH:D003920), malignant neoplasms (MESH:D009369), AD (MESH:D000544), Us (MESH:D019966), psychiatric (MESH:D001523), cervical polyps and dysplasia (MESH:D002578)
- **Chemicals:** ZeBRA (-), alprazolam (MESH:D000525), lecanemab (MESH:C000612089)
- **Species:** Homo sapiens (human, species) [taxon 9606]

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC12919223/full.md

## Figures

4 figures with captions in the complete paper: https://tomesphere.com/paper/PMC12919223/full.md

## References

79 references — full list in the complete paper: https://tomesphere.com/paper/PMC12919223/full.md

---
Source: https://tomesphere.com/paper/PMC12919223