Home › Research › Getting a diagnosis
A deep joint-learning proteomics model for diagnosis of six conditions associated with dementia
Lijun An, Alexa Pichet Binette, Ines Hristovska, Gabriele Vilkaite, Yu Xiao, Romina Zendehdel, Zijian Dong, Bart Smets, et al.. Nature medicine, 2026-03-31
Topic: Risk, prevention and care in population studies
Co-pathology is a common feature of neurodegenerative diseases that complicates diagnosis, treatment and clinical management. However, sensitive, specific and scalable biomarkers for in vivo pathological diagnosis are not available for most neurodegenerative neuropathologies. Here we present Proteomics-based Artificial Intelligence for Dementia Diagnosis (ProtAIDe-Dx), a deep joint-learning model on 17,187 patients and controls (age of 70.3 ± 11.5 years, 53.2% female), that uses plasma proteomics to provide simultaneous probabilistic diagnosis across 6 conditions associated with dementia in aging. ProtAIDe-Dx achieves cross-validated balanced classification accuracy of 70-95% and area under the curve of >78% across all conditions. The model's diagnostic probabilities highlighted subgroups of patients with co-pathologies and were associated with pathology-specific biomarkers in an external memory clinic sample, even among individuals without cognitive impairment. Model interpretation revealed a suite of protein networks marking shared and specific biological processes across diseases and identified novel and previously described proteins discriminating each diagnosis. ProtAIDe-Dx significantly improved biomarker-based differential diagnosis in a memory clinic sample, pinpointing proteins leading to diagnostic decisions at an individual level. Together, this work highlights the promise of plasma proteomics to improve patient-level diagnostic workup with a single blood draw.
Key findings
- Here we present Proteomics-based Artificial Intelligence for Dementia Diagnosis (ProtAIDe-Dx), a deep joint-learning model on 17,187 patients and controls (age of 70.3 ± 11.5 years, 53.2% female), that uses plasma proteomics to provide simultaneous probabilistic diagnosis across 6 conditions associated with dementia in aging.
- The model's diagnostic probabilities highlighted subgroups of patients with co-pathologies and were associated with pathology-specific biomarkers in an external memory clinic sample, even among individuals without cognitive impairment.
- Model interpretation revealed a suite of protein networks marking shared and specific biological processes across diseases and identified novel and previously described proteins discriminating each diagnosis.
- ProtAIDe-Dx significantly improved biomarker-based differential diagnosis in a memory clinic sample, pinpointing proteins leading to diagnostic decisions at an individual level.
Why it matters
This study describes a computer model using blood proteins to give a probable diagnosis across six conditions linked to dementia, with accuracy of 70-95% across conditions. The model also flagged patients with mixed pathologies and identified proteins behind its decisions, but it is a diagnostic tool rather than a treatment or cure.
New to this subject? Start with our plain-English guide: Getting a diagnosis →
Study details
- Study designcross-sectional
- Participants17,187
- Effect sizeCross-validated balanced classification accuracy 70-95%; AUC >78% across six conditions
- Evidence strengthEarly
Limitations
Model development and internal cross-validation with one external validation sample; diagnostic labels came from clinical or biomarker criteria rather than autopsy; no prospective clinical-impact data.
How this study scored 62/100
Published in a top-tier journal, and it is a snapshot of people at one point in time. Scored zero for randomised / blinded because the record does not state it. We have no data on free to read, so that was left out: it earned 61 of the 98 points we could judge it on, which is 62 out of 100.
| Component | Points | Why |
|---|---|---|
| Journal tier | 10 / 10 | Tier 1 — top-tier general journal (Nature medicine) |
| Journal's citation record | 4 / 4 | Nature Medicine: journal h-index 763 (OpenAlex, 2026-10-29) |
| Study design | 4 / 12 | A snapshot of people at one point in time |
| Strength of evidence | 2 / 5 | Rated “early” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 5 / 5 | 2026 — within 1 year(s) of the newest study here |
| Sample size | 4 / 4 | 17,187 participants |
| Effect reported | 3 / 3 | Effect reported with a statistic (interval, p-value, ratio or similar) |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 1 / 7 | Cited 4 times (OpenAlex, 2026-10-10) |
| Citations per year | 1 / 5 | 2.0 citations a year over 2 year(s) since 2026 |
| Impact for its field and year | 4 / 6 | Cited 19.0× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 0 / 6 | No other study in this library cites it |
| Still being cited | 1 / 4 | Cited 4 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Jacob W. Vogel: h-index 46 (OpenAlex, whole career) |
| Institution's track record | 2 / 3 | Washington University in St. Louis: institution h-index 1,962 (OpenAlex) |
| Multi-centre collaboration | 3 / 3 | OpenAlex lists 15 institution(s) in 6 countries |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 41917159) |
| Free to read | — / 2 | Access not recorded — left out of this score |
| Points | 61 / 98 | Scored on 19 of 20 parts. We have no data for the rest, so they are left out: 61 of the 98 points we could judge it on is 62 out of 100. |
| Total | 62 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
Full text: free to read — PubMed Central lists this copy as free to read: the link above (checked 10 Oct 2026).
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. The record's author list ends in “et al.”, so not every author is named. Check the citation against the original before you use it.
APA 7th
An, L., Binette, A. P., Hristovska, I., Vilkaite, G., Xiao, Y., Zendehdel, R., et al. (2026). A deep joint-learning proteomics model for diagnosis of six conditions associated with dementia. Nature medicine. https://doi.org/10.1038/s41591-026-04303-y
Vancouver
An L, Binette AP, Hristovska I, Vilkaite G, Xiao Y, Zendehdel R, et al. A deep joint-learning proteomics model for diagnosis of six conditions associated with dementia. Nature medicine. 2026. doi:10.1038/s41591-026-04303-y. PMID: 41917159.
BibTeX
@article{an2026-41917159,
author = {An, Lijun and Binette, Alexa Pichet and Hristovska, Ines and Vilkaite, Gabriele and Xiao, Yu and Zendehdel, Romina and Dong, Zijian and Smets, Bart and others},
title = {{A deep joint-learning proteomics model for diagnosis of six conditions associated with dementia}},
journal = {Nature medicine},
year = {2026},
doi = {10.1038/s41591-026-04303-y},
pmid = {41917159},
url = {https://doi.org/10.1038/s41591-026-04303-y}
}
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here. Showing 12 of 23.
Related studies in Getting a diagnosis
Also tagged “prevalence”
1,224 studies in the library carry the topic tag “prevalence”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 1,224 tagged studies.