Home › Research › Getting a diagnosis
A vision transformer approach for fully automated and scalable dementia screening using clock drawing test images
Michael B. Bone, Morris Freedman, Sandra E. Black, Daniel Felsky, Sanjeev Kumar, Bradley Pugh, Stephen C. Strother, David F. Tang‐Wai et al.. Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring, 2025-07-01
Topic: Risk, prevention and care in population studies
The ViT approach predicted dementia with 76.5% balanced accuracy, outperforming human-scored features (74.3%) and existing deep learning models (MiniVGG = 73.3%, MobileNetV2 = 72.3%, relevance factor variational autoencoder = 69.1%) on the TDRA dataset. This pen-and-paper compatible diagnostic system enables scalable remote cognitive screening through automated CDT image analysis that is competitive with human-scored features, potentially increasing diagnostic accessibility for diverse populations across varied socioeconomic contexts. HIGHLIGHTS: The vision transformer model achieves 76.5% accuracy in dementia detection from clock drawing tests, outperforming human scoring and existing deep learning methods.Novel convolutional neural network-based preprocessing automatically handles challenging image quality issues like shadows, irrelevant markings, and improper cropping.The system requires only a photo of a hand-drawn clock test, enabling scalable remote screening accessible across socioeconomic contexts.A feature-extraction model trained on 54,027 samples demonstrates robust generalization to an independent clinical dataset of 862 patients.This fully automated approach eliminates the need for trained scorers while maintaining diagnostic accuracy above manual methods.
Key findings
- The ViT approach predicted dementia with 76.5% balanced accuracy, outperforming human-scored features (74.3%) and existing deep learning models (MiniVGG = 73.3%, MobileNetV2 = 72.3%, relevance factor variational autoencoder = 69.1%) on the TDRA dataset.
- This pen-and-paper compatible diagnostic system enables scalable remote cognitive screening through automated CDT image analysis that is competitive with human-scored features, potentially increasing diagnostic accessibility for diverse populations across varied socioeconomic contexts.
- HIGHLIGHTS: The vision transformer model achieves 76.5% accuracy in dementia detection from clock drawing tests, outperforming human scoring and existing deep learning methods.Novel convolutional neural network-based preprocessing automatically handles challenging image quality issues like shadows, irrelevant markings, and improper cropping.The system requires only a photo of a hand-drawn clock test, enabling scalable remote screening accessible across socioeconomic contexts.A feature-extraction model trained on 54,027 samples demonstrates robust generalization to an independent clinical dataset of 862 patients.This fully automated approach eliminates the need for trained scorers while maintaining diagnostic accuracy above manual methods.
Why it matters
A vision transformer model predicted dementia from clock drawing test images with 76.5% balanced accuracy, slightly outperforming human scoring and other deep learning models. This automated approach could enable scalable remote screening, but it is a diagnostic tool and does not treat or prevent dementia.
New to this subject? Start with our plain-English guide: Getting a diagnosis →
Study details
- Participants862
- Effect size76.5%; 74.3%; 73.3%
- Evidence strengthLow
How this study scored 45/100
Published in a peer-reviewed journal. Scored zero for study design 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 Diagnosis Assessment & Disease Monitoring) |
| Journal's citation record | 1 / 4 | Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring: journal h-index 86 (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 | 2 / 4 | 862 participants |
| Effect reported | 2 / 3 | Effect reported as a number, without an interval or test |
| 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 3 times (OpenAlex, 2026-10-10) |
| Citations per year | 1 / 5 | 1.0 citations a year over 3 year(s) since 2025 |
| Impact for its field and year | 2 / 6 | Cited 1.9× 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 3 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Bradley R. Buchsbaum: h-index 41 (OpenAlex, whole career) |
| Institution's track record | 2 / 3 | University of Toronto: institution h-index 1,923 (OpenAlex) |
| Multi-centre collaboration | 2 / 3 | OpenAlex lists 8 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 41001422) |
| Free to read | 2 / 2 | Free to read |
| Total | 45 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
- DOI: 10.1002/dad2.70171
- PubMed: 41001422
- Original source →
- Free full text: Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring →
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
Bone, M. B., Freedman, M., Black, S. E., Felsky, D., Kumar, S., Pugh, B., et al. (2025). A vision transformer approach for fully automated and scalable dementia screening using clock drawing test images. Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring. https://doi.org/10.1002/dad2.70171
Vancouver
Bone MB, Freedman M, Black SE, Felsky D, Kumar S, Pugh B, et al. A vision transformer approach for fully automated and scalable dementia screening using clock drawing test images. Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring. 2025. doi:10.1002/dad2.70171. PMID: 41001422.
BibTeX
@article{bone2025-41001422,
author = {Bone, Michael B. and Freedman, Morris and Black, Sandra E. and Felsky, Daniel and Kumar, Sanjeev and Pugh, Bradley and Strother, Stephen C. and Tang‐Wai, David F. and others},
title = {{A vision transformer approach for fully automated and scalable dementia screening using clock drawing test images}},
journal = {Alzheimer s \& Dementia Diagnosis Assessment \& Disease Monitoring},
year = {2025},
doi = {10.1002/dad2.70171},
pmid = {41001422},
url = {https://doi.org/10.1002/dad2.70171}
}
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
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.