Home › Research › Digital health tools
Metabolomic Signatures and Machine Learning Models for Distinguishing Alzheimer's Disease and Dementia with Lewy Bodies
Dany Mukesha, Maité Sarter, Mélitine Dubray, Floris Durand, Seval Kul, Lucas Dinh Pham-Van, Stéphanie Boutillier, Guillaume Sacco et al.. Alzheimer s & Dementia, 2025-12-01
Topic: Amyloid, tau and blood-test diagnosis
AD patients exhibited a significantly higher prevalence of APOE e3/e4 and e4/e4 genotypes compared to DLB and HC (p <0.001). Lipid dysregulations, particularly in phosphatidylcholines, lysophosphatidylcholines, triglycerides, and sphingomyelins, were observed across all groups. Lasso identified 63 metabolites, which, combined with APOE, improved AUC for AD vs. DLB from 0.78 to 0.81. Similarly, the AUC for AD vs. HC increased from 0.78 to 0.83 with APOE, while no improvement was seen for DLB vs. HC (AUC=0.78). This study demonstrates the potential of metabolomic biomarkers in differentiating AD from DLB, with APOE improving classification accuracy for AD. Future efforts will focus on validating findings in larger cohorts and translating these findings into non-invasive, cost-effective tool set to reduce AD and DLB misdiagnosis.
Key findings
- AD patients exhibited a significantly higher prevalence of APOE e3/e4 and e4/e4 genotypes compared to DLB and HC (p <0.001).
- Lipid dysregulations, particularly in phosphatidylcholines, lysophosphatidylcholines, triglycerides, and sphingomyelins, were observed across all groups.
- Lasso identified 63 metabolites, which, combined with APOE, improved AUC for AD vs.
- HC increased from 0.78 to 0.83 with APOE, while no improvement was seen for DLB vs.
- This study demonstrates the potential of metabolomic biomarkers in differentiating AD from DLB, with APOE improving classification accuracy for AD.
Why it matters
This study found that metabolomic biomarkers, combined with APOE, improved classification accuracy for distinguishing Alzheimer's disease from dementia with Lewy bodies. It is a diagnostic study only and does not test any treatment, cure or prevention, and the authors note larger cohorts are needed.
New to this subject? Start with our plain-English guide: Digital health →
Study details
- Effect sizeAUC=0.78
- Evidence strengthLow
How this study scored 37/100
Published in a peer-reviewed journal. Scored zero for study design, sample size, studied in people and randomised / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (Alzheimer s & Dementia) |
| Journal's citation record | 2 / 4 | Alzheimer s & Dementia: journal h-index 228 (OpenAlex, 2026-10-29) |
| 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 | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 4 / 5 | 2025 — within 3 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 | 1 / 7 | Cited 1 times (OpenAlex, 2026-10-10) |
| Citations per year | 0 / 5 | 0.3 citations a year over 3 year(s) since 2025 |
| Impact for its field and year | 1 / 6 | Cited 0.6× 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 | 0 / 4 | Cited 1 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Hüseyin Firat: h-index 29 (OpenAlex, whole career) |
| Institution's track record | 0 / 3 | Université Côte d'Azur: institution h-index 696 (OpenAlex) |
| Multi-centre collaboration | 2 / 3 | OpenAlex lists 4 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 41433352) |
| Free to read | 2 / 2 | Free to read |
| Total | 37 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
- DOI: 10.1002/alz70863_110610
- PubMed: 41433352
- Original source →
- Free full text: Alzheimer s & Dementia →
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
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
Mukesha, D., Sarter, M., Dubray, M., Durand, F., Kul, S., Pham-Van, L. D., et al. (2025). Metabolomic Signatures and Machine Learning Models for Distinguishing Alzheimer's Disease and Dementia with Lewy Bodies. Alzheimer s & Dementia. https://doi.org/10.1002/alz70863_110610
Vancouver
Mukesha D, Sarter M, Dubray M, Durand F, Kul S, Pham-Van LD, et al. Metabolomic Signatures and Machine Learning Models for Distinguishing Alzheimer's Disease and Dementia with Lewy Bodies. Alzheimer s & Dementia. 2025. doi:10.1002/alz70863_110610. PMID: 41433352.
BibTeX
@article{mukesha2025-41433352,
author = {Mukesha, Dany and Sarter, Maité and Dubray, Mélitine and Durand, Floris and Kul, Seval and Pham-Van, Lucas Dinh and Boutillier, Stéphanie and Sacco, Guillaume and others},
title = {{Metabolomic Signatures and Machine Learning Models for Distinguishing Alzheimer's Disease and Dementia with Lewy Bodies}},
journal = {Alzheimer s \& Dementia},
year = {2025},
doi = {10.1002/alz70863_110610},
pmid = {41433352},
url = {https://doi.org/10.1002/alz70863_110610}
}