This page is alzhub.org's plain-English summary of a published study, not the paper itself. It is generated from the record we hold for this study, sourced and linked below — check the original for the full text and methods.

16/100

⚠ Preprint — not yet peer-reviewed alzhub usefulness score 16 out of 100. Brain scans and imaging

Topic: Plasma and spinal-fluid biomarkers

Alzheimer’s disease (AD) pathology develops years in advance prior to its clinical presentation. As a result, there is an urgent need to develop extremely early diagnosis modalities that are both accurate and feasible. Existing diagnosis methods based on CSF testing and/or amyloid and tau PET scans can hardly be implemented on a wide scale due to their invasive nature or high costs. Plasma phosphorylated tau 217, which is one of the most promising biomarkers with extremely high accuracy, does not index functional impairment but rather detects biological pathology. At the same time, digital biomarkers based on acoustic properties of speech and gait kinematics allow one to continuously assess cognitive-motor functioning but are devoid of any relation to biological processes. In our paper, we introduce BioDigi-XNet, a multimodal transformer network that unifies static biological features with digital phenotypes using cross attention mechanism. Biological markers query digital sequences allowing the model to understand which markers are associated with behavioral abnormalities. In simulated studies mimicking both the ADNI and BioFINDER cohorts, BioDigi-XNet demonstrated an AUC-ROC value of 0.94 for differentiating between prodromal AD and healthy individuals, surpassing biomarkers only (AUC = 0.89), speech only (AUC = 0.82), and naive late-fusion models (AUC = 0.90). Cross-attention analysis showed that p-tau217 paid particular attention to speech pause time and gait stride variability, connecting molecular pathophysiology with functional disorganization. The results suggest a clinical approach for explainable ultra-early diagnosis of AD based on the combination of biological markers and functional states.

Cite this study APA, Vancouver, BibTeX · download .bib or .ris

APA 7th

Zerrouki, H., & Azzaz-Rahmani, S. (2026). Multimodal Transformer-Based Fusion of Blood-Based and Digital Biomarkers for Explainable (XAI) Ultra-Early Alzheimer's Disease Detection. Research Square. https://doi.org/10.21203/rs.3.rs-10462750/v1

Vancouver

Zerrouki H, Azzaz-Rahmani S. Multimodal Transformer-Based Fusion of Blood-Based and Digital Biomarkers for Explainable (XAI) Ultra-Early Alzheimer's Disease Detection. Research Square. 2026. doi:10.21203/rs.3.rs-10462750/v1.

BibTeX

@article{zerrouki2026-2417b906,
  author  = {Zerrouki, H. and Azzaz-Rahmani, S.},
  title   = {{Multimodal Transformer-Based Fusion of Blood-Based and Digital Biomarkers for Explainable (XAI) Ultra-Early Alzheimer's Disease Detection}},
  journal = {Research Square},
  year    = {2026},
  doi     = {10.21203/rs.3.rs-10462750/v1},
  url     = {https://doi.org/10.21203/rs.3.rs-10462750/v1}
}

Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. Check the citation against the original before you use it.

Key findings

As a result, there is an urgent need to develop extremely early diagnosis modalities that are both accurate and feasible.
Biological markers query digital sequences allowing the model to understand which markers are associated with behavioral abnormalities.
In simulated studies mimicking both the ADNI and BioFINDER cohorts, BioDigi-XNet demonstrated an AUC-ROC value of 0.94 for differentiating between prodromal AD and healthy individuals, surpassing biomarkers only (AUC = 0.89), speech only (AUC = 0.82), and naive late-fusion models (AUC = 0.90).
Cross-attention analysis showed that p-tau217 paid particular attention to speech pause time and gait stride variability, connecting molecular pathophysiology with functional disorganization.
The results suggest a clinical approach for explainable ultra-early diagnosis of AD based on the combination of biological markers and functional states.

New to this subject? Start with our plain-English guide: Brain scans & tests →

Study details

Effect sizeAUC = 0.89; AUC = 0.82; AUC = 0.90
Evidence strengthLow

How this study scored 16/100

Preprint — not yet peer-reviewed. It scored 26 on the same rubric, but non-peer-reviewed sources are capped at 16, so it shows as 16. Scored zero for study design, sample size, studied in people and randomised / blinded because the record does not state it. We have no data on times cited, citations per year, impact for its field and year, cited by studies here, still being cited, senior author's track record, institution's track record and multi-centre collaboration, so those were left out: it earned 16 of the 62 points we could judge it on, which is 26 out of 100.

Component	Points	Why
Journal tier	2 / 10	Tier 4 — not a peer-reviewed journal (Research Square)
Journal's citation record	0 / 4	Not a journal article, so the journal's record does not count
Study design	0 / 12	No study design recorded — scores zero, not guessed (not stated in the record — scored 0)
Strength of evidence	1 / 5	Rated “low” in our summary
Peer-review validation	4 / 10	Preprint — not yet peer-reviewed. Hosted on a preprint server.
How recent	5 / 5	2026 — within 1 year(s) of the newest study here
Sample size	0 / 4	Participant count not stated — scores zero (not stated in the record — scored 0)
Effect reported	3 / 3	Effect reported with a statistic (interval, p-value, ratio or similar)
Studied in people	0 / 3	Not stated whether this was studied in people — scores zero (not stated in the record — scored 0)
Randomised / blinded	0 / 2	No randomisation or blinding stated — scores zero (not stated in the record — scored 0)
Times cited	— / 7	No citation count (not found in OpenAlex) — left out of this score
Citations per year	— / 5	No citation count or no year — left out of this score
Impact for its field and year	— / 6	No field-weighted citation impact (OpenAlex has none yet) — left out of this score
Cited by studies here	— / 6	Not yet checked against this library's citation graph — left out of this score
Still being cited	— / 4	No yearly citation counts — left out of this score
Senior author's track record	— / 4	Senior author's record not available — left out of this score
Institution's track record	— / 3	No institution listed in OpenAlex — left out of this score
Multi-centre collaboration	— / 3	Institutions not listed — left out of this score
Indexed in PubMed	1 / 2	Not in PubMed, but has a DOI
Free to read	0 / 2	Behind a paywall — scores zero
Points	16 / 62	Scored on 12 of 20 parts. We have no data for the rest, so they are left out: 16 of the 62 points we could judge it on is 26 out of 100.
Total	26 / 100	Capped to 16 because this is not a peer-reviewed article.

What each of these 20 components measures, and what this score is not →

Read the original

Free copy unknown: no free-copy check has an answer for this record yet. That does not mean it is paywalled.

Related studies in Brain scans and imaging

Also tagged “convolutional”

205 studies in the library carry the topic tag “convolutional”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 205 tagged studies.

Similar studies

More on Brain scans and imaging

See all studies in Brain scans and imaging →