Home › Research › Brain scans and imaging
Structural MRI–based Computer-aided Diagnosis Models for Alzheimer Disease: Insights into Misclassifications and Diagnostic Limitations
Xiaopeng Kang, Jiaji Lin, Kun Zhao, Shaozhen Yan, Pindong Chen, Dawei Wang, Hongxiang Yao, Bo Zhou et al.. Radiology Artificial Intelligence, 2025-07-30
Topic: Amyloid, tau and blood-test diagnosis
The 3D Nested Hierarchical Transformer model helped to accurately diagnose Alzheimer disease based on structural brain MRI scans. False-negative classifications were consistent across all computer-aided detection models, occurring primarily in patients with atypical Alzheimer disease and preserved cognition.
Key findings
- The 3D Nested Hierarchical Transformer model helped to accurately diagnose Alzheimer disease based on structural brain MRI scans.
- False-negative classifications were consistent across all computer-aided detection models, occurring primarily in patients with atypical Alzheimer disease and preserved cognition.
Why it matters
This study found that a 3D Nested Hierarchical Transformer model accurately diagnosed Alzheimer disease from structural MRI scans, but false negatives occurred consistently across models in patients with atypical disease and preserved cognition. It is a diagnostic study and does not test any treatment, cure, or prevention.
New to this subject? Start with our plain-English guide: Brain scans & tests →
Study details
- Evidence strengthLow
How this study scored 38/100
Published in a peer-reviewed journal. Scored zero for study design, sample size, effect reported, studied in people and randomised / blinded because the record does not state it. We have no data on senior author's track record, so that was left out: it earned 36 of the 96 points we could judge it on, which is 38 out of 100.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (Radiology Artificial Intelligence) |
| Journal's citation record | 0 / 4 | Radiology Artificial Intelligence: journal h-index 68 (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 | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| 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 | 2 / 7 | Cited 7 times (OpenAlex, 2026-10-10) |
| Citations per year | 1 / 5 | 2.3 citations a year over 3 year(s) since 2025 |
| Impact for its field and year | 3 / 6 | Cited 4.4× 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 7 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | — / 4 | Senior author's record not available — left out of this score |
| Institution's track record | 2 / 3 | Chinese Academy of Sciences: institution h-index 1,801 (OpenAlex) |
| Multi-centre collaboration | 3 / 3 | OpenAlex lists 14 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 40736363) |
| Free to read | 0 / 2 | Behind a paywall — scores zero |
| Points | 36 / 96 | Scored on 19 of 20 parts. We have no data for the rest, so they are left out: 36 of the 96 points we could judge it on is 38 out of 100. |
| Total | 38 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
May need a subscription OpenAlex found no free copy of the full text (checked 6 Feb 1020), so the publisher may charge for it. The PubMed abstract is free.
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
Kang, X., Lin, J., Zhao, K., Yan, S., Chen, P., Wang, D., et al. (2025). Structural MRI–based Computer-aided Diagnosis Models for Alzheimer Disease: Insights into Misclassifications and Diagnostic Limitations. Radiology Artificial Intelligence. https://doi.org/10.1148/ryai.240508
Vancouver
Kang X, Lin J, Zhao K, Yan S, Chen P, Wang D, et al. Structural MRI–based Computer-aided Diagnosis Models for Alzheimer Disease: Insights into Misclassifications and Diagnostic Limitations. Radiology Artificial Intelligence. 2025. doi:10.1148/ryai.240508. PMID: 40736363.
BibTeX
@article{kang2025-40736363,
author = {Kang, Xiaopeng and Lin, Jiaji and Zhao, Kun and Yan, Shaozhen and Chen, Pindong and Wang, Dawei and Yao, Hongxiang and Zhou, Bo and others},
title = {{Structural MRI–based Computer-aided Diagnosis Models for Alzheimer Disease: Insights into Misclassifications and Diagnostic Limitations}},
journal = {Radiology Artificial Intelligence},
year = {2025},
doi = {10.1148/ryai.240508},
pmid = {40736363},
url = {https://doi.org/10.1148/ryai.240508}
}
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
Related studies in Brain scans and imaging
Also tagged “classification”
835 studies in the library carry the topic tag “classification”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 835 tagged studies.