Home › Research › Digital health tools
Accuracy of dementia diagnosis: a direct comparison between radiologists and a computerized method
Klöppel S, Stonnington CM, Barnes J, Chen F, Chu C, Good CD, Mader I, Mitchell LA et al.. Brain : a journal of neurology, 2008-10-03
Topic: Risk, prevention and care in population studies
There has been recent interest in the application of machine learning techniques to neuroimaging-based diagnosis. These methods promise fully automated, standard PC-based clinical decisions, unbiased by variable radiological expertise. We recently used support vector machines (SVMs) to separate sporadic Alzheimer's disease from normal ageing and from fronto-temporal lobar degeneration (FTLD). In this study, we compare the results to those obtained by radiologists. A binary diagnostic classification was made by six radiologists with different levels of experience on the same scans and information that had been previously analysed with SVM. SVMs correctly classified 95% (sensitivity/specificity: 95/95) of sporadic Alzheimer's disease and controls into their respective groups. Radiologists correctly classified 65-95% (median 89%; sensitivity/specificity: 88/90) of scans. SVM correctly classified another set of sporadic Alzheimer's disease in 93% (sensitivity/specificity: 100/86) of cases, whereas radiologists ranged between 80% and 90% (median 83%; sensitivity/specificity: 80/85). SVMs were better at separating patients with sporadic Alzheimer's disease from those with FTLD (SVM 89%; sensitivity/specificity: 83/95; compared to radiological range from 63% to 83%; median 71%; sensitivity/specificity: 64/76). Radiologists were always accurate when they reported a high degree of diagnostic confidence. The results show that well-trained neuroradiologists classify typical Alzheimer's disease-associated scans comparable to SVMs. However, SVMs require no expert knowledge and trained SVMs can readily be exchanged between centres for use in diagnostic classification. These results are encouraging and indicate a role for computerized diagnostic methods in clinical practice.
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
APA 7th
Klöppel, S., Stonnington, C. M., Barnes, J., Chen, F., Chu, C., Good, C. D., et al. (2008). Accuracy of dementia diagnosis: a direct comparison between radiologists and a computerized method. Brain : a journal of neurology. https://doi.org/10.1093/brain/awn239
Vancouver
Klöppel S, Stonnington CM, Barnes J, Chen F, Chu C, Good CD, et al. Accuracy of dementia diagnosis: a direct comparison between radiologists and a computerized method. Brain : a journal of neurology. 2008. doi:10.1093/brain/awn239. PMID: 18835868.
BibTeX
@article{kloppel2008-18835868,
author = {Klöppel, S. and Stonnington, C. M. and Barnes, J. and Chen, F. and Chu, C. and Good, C. D. and Mader, I. and Mitchell, L. A. and others},
title = {{Accuracy of dementia diagnosis: a direct comparison between radiologists and a computerized method}},
journal = {Brain : a journal of neurology},
year = {2008},
doi = {10.1093/brain/awn239},
pmid = {18835868},
url = {https://doi.org/10.1093/brain/awn239}
}
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.
Key findings
- In this study, we compare the results to those obtained by radiologists.
- SVMs were better at separating patients with sporadic Alzheimer's disease from those with FTLD (SVM 89%; sensitivity/specificity: 83/95; compared to radiological range from 63% to 83%; median 71%; sensitivity/specificity: 64/76).
- The results show that well-trained neuroradiologists classify typical Alzheimer's disease-associated scans comparable to SVMs.
- These results are encouraging and indicate a role for computerized diagnostic methods in clinical practice.
Why it matters
On the same brain scans, a computer method (support vector machines) and six radiologists both tried to tell Alzheimer's disease apart from normal ageing and from frontotemporal lobar degeneration (FTLD). For Alzheimer's vs healthy ageing, the computer was right 93–95% of the time and the radiologists 65–95%, and the authors judged well-trained neuroradiologists "comparable"; the computer's clearest lead was in separating Alzheimer's from FTLD (89% vs a radiologist median of 71%). This is a diagnostic-accuracy comparison on already-labelled groups. It does not show the tool is ready for routine clinical use, and it says nothing about treatment.
New to this subject? Start with our plain-English guide: Digital health →
Study details
- Evidence strengthLow
How this study scored 55/100
Published in a leading specialty journal. Scored zero for study design, sample size, effect reported, studied in people and randomised / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 9 / 10 | Tier 2 — leading specialty journal (Brain : a journal of neurology) |
| Journal's citation record | 4 / 4 | Brain: journal h-index 503 (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 | 1 / 5 | 2008 — within 20 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 | 5 / 7 | Cited 272 times (OpenAlex, 2026-10-10) |
| Citations per year | 3 / 5 | 13.6 citations a year over 20 year(s) since 2008 |
| Impact for its field and year | 4 / 6 | Cited 10.9× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 3 / 6 | Cited by 11 other studies in this library |
| Still being cited | 2 / 4 | Cited 25 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 4 / 4 | Last-listed author Richard S. J. Frackowiak: h-index 188 (OpenAlex, whole career) |
| Institution's track record | 2 / 3 | University College London: institution h-index 2,029 (OpenAlex) |
| Multi-centre collaboration | 3 / 3 | OpenAlex lists 11 institution(s) in 5 countries |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 18835868) |
| Free to read | 2 / 2 | Free to read |
| Total | 55 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
Later studies that cite this one
11 studies in the alzhub library list this one in their references. Showing the 8 highest-scoring.
Related studies in Digital health tools
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.