Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index; 30 of the 40 sources its claims cite were checked for support.

MRI data-driven algorithm for the diagnosis of behavioural variant frontotemporal dementia

Open access
Manera, Ana L, Dadar, Mahsa, Van Swieten, John Cornelis, Borroni, Barbara, Sanchez-Valle, Raquel, Moreno, Fermin, Laforce Jr, Robert, Graff, Caroline, Synofzik, Matthis, Galimberti, Daniela, Rowe, James Benedict, Masellis, Mario, Tartaglia, Maria Carmela, Finger, Elizabeth, Vandenberghe, Rik, de Mendonca, Alexandre, Tagliavini, Fabrizio, Santana, Isabel, Butler, Christopher R, Gerhard, Alex, Danek, Adrian, Levin, Johannes, Otto, Markus, Frisoni, Giovanni, Ghidoni, Roberta, Sorbi, Sandro, Rohrer, Jonathan Daniel, Ducharme, Simon, Collins, D Louis, FTLDNI investigators · 2021 · Journal of Neurology, Neurosurgery & Psychiatry

Abstract

INTRODUCTION: Structural brain imaging is paramount for the diagnosis of behavioural variant of frontotemporal dementia (bvFTD), but it has low sensitivity leading to erroneous or late diagnosis. METHODS: A total of 515 subjects from two different bvFTD cohorts (training and independent validation cohorts) were used to perform voxel-wise morphometric analysis to identify regions with significant differences between bvFTD and controls. A random forest classifier was used to individually predict bvFTD from deformation-based morphometry differences in isolation and together with semantic fluency. Tenfold cross validation was used to assess the performance of the classifier within the training cohort. A second held-out cohort of genetically confirmed bvFTD cases was used for additional validation. RESULTS: Average 10-fold cross-validation accuracy was 89% (82% sensitivity, 93% specificity) using only MRI and 94% (89% sensitivity, 98% specificity) with the addition of semantic fluency. In the separate validation cohort of definite bvFTD, accuracy was 88% (81% sensitivity, 92% specificity) with MRI and 91% (79% sensitivity, 96% specificity) with added semantic fluency scores. CONCLUSION: Our results show that structural MRI and semantic fluency can accurately predict bvFTD at the individual subject level within a completely independent validation cohort coming from a different and independent database.

Overview

CoChat Summary

## TL;DR

The paper develops an MRI-based random forest classifier for individual-level diagnosis of behavioural variant frontotemporal dementia (bvFTD) using deformation-based morphometry (DBM), with semantic fluency as an optional added feature. In an independent validation cohort, the model reached 88% accuracy with MRI alone and 91% with MRI plus semantic fluency.

## Key findings

  • In 10-fold cross-validation within the training cohort, the classifier achieved 89% accuracy with MRI alone (82% sensitivity, 93% specificity) and 94% accuracy with added semantic fluency (89% sensitivity, 98% specificity).
  • In the independent validation cohort of genetically confirmed bvFTD, performance was 88% accuracy with MRI alone (81% sensitivity, 92% specificity) and 91% accuracy with MRI plus semantic fluency (79% sensitivity, 96% specificity).
  • The paper reports AUCs of 0.90 for DBM alone and 0.92 for DBM + semantic fluency in the independent validation cohort.
  • The validation cohort had 19% false negatives with DBM alone and 4% false positives among controls; false negatives were younger and had shorter estimated time from onset, while false positives were older.

## Methods

  • Design: Two-cohort machine-learning study: a training cohort from FTLDNI and an independent held-out validation cohort from GENFI2; the model was built on the training cohort and tested on the separate validation cohort.
  • Sample/data: 515 subjects total: training cohort 70 bvFTD and 123 cognitively normal controls (CNCs); validation cohort 75 bvFTD and 247 CNCs. Only subjects with matching clinical visits and usable T1-weighted MRI were included.
  • Analysis: Voxel-wise deformation-based morphometry (DBM) with mixed-effects modeling identified bvFTD-related regions; the resulting ROI was reduced with PCA; a random forest classifier with 500 trees predicted bvFTD using DBM features alone or DBM plus semantic fluency. Performance was assessed with 10-fold cross-validation in training and ROC/likelihood ratios in validation.

## Limitations

  • The paper states that the main limitation is that the results are not yet validated prospectively in a clinically representative cohort including diverse primary psychiatric disorders.
  • The authors also state that classification accuracy remains to be demonstrated in cohorts with other dementias and cardiovascular comorbidities, which were uncommon in their dataset.
  • Evident from the text: the validation cohort consisted of genetically confirmed bvFTD cases and family-member controls, so the reported performance may not fully generalize to all real-world bvFTD presentations.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1136/jnnp-2020-324106

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

11 Valid · 3 Not valid · 4 Not checked · 51 Own results and interpretations

31 more claims · 3 with their cited sources checked

Create a free account to see all 69 claims and every source verdict.

See all claims — free account
  • It may state two separate claims as one. 25
  • Probably not a substantial claim. 13

Create a free account to see these claims.

Citations

Cites

Show all 46 references

Cited by

See all 24

Metadata

Authors
Manera, A. L., Dadar, M., Van Swieten, J. C., Borroni, B., Sanchez-Valle, R., Moreno, F., Laforce Jr, R., Graff, C., Synofzik, M., Galimberti, D., Rowe, J. B., Masellis, M., Tartaglia, M. C., Finger, E., Vandenberghe, R., de Mendonca, A., Tagliavini, F., Santana, I., Butler, C. R., Gerhard, A., Danek, A., Levin, J., Otto, M., Frisoni, G., Ghidoni, R., Sorbi, S., Rohrer, J. D., Ducharme, S., Collins, D. L., & FTLDNI investigators
Affiliations
  • Montreal Neurological Institute and Hospital (CA)
  • University of Brescia (IT)
  • Karolinska University Hospital (SE)
  • Hertie Institute for Clinical Brain Research (DE)
  • Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (IT)
  • University of Cambridge (GB)
  • Sunnybrook Health Science Centre (CA)
  • Toronto Western Hospital (CA)
  • Western University (CA)
  • KU Leuven (BE)
  • Fondazione IRCCS Istituto Neurologico Carlo Besta (IT)
  • Unidade Local de Saúde de Coimbra (PT)
  • University of Oxford (GB)
  • German Center for Neurodegenerative Diseases (DE)
  • University Hospital Ulm (DE)
  • University of Geneva (CH)
  • Centro San Giovanni di Dio Fatebenefratelli (IT)
  • University of Florence (IT)
  • UCL Queen Square Institute of Neurology (GB)
Corresponding author
Manera, Ana L
Venue
Journal of Neurology, Neurosurgery & Psychiatry
Publisher
BMJ
Published
2021-03-15
Volume
92
Issue
6
Pages
608-616
ISSN
  • 0022-3050 (ISSN-L)
  • 1468-330X
OpenAlex
W3136953959
Cited by
23
References
46
Citations by year
2026: 2 · 2025: 8 · 2024: 3 · 2023: 2 · 2022: 6 · 2021: 2
FWCI
2.33
Type
journal article
Language
en
Open access
Licence
other-oa
Locations
  • Journal of Neurology Neurosurgery & Psychiatry (publishedVersion)
  • PubMed (publishedVersion)
  • Amsterdam UMC (VU Amsterdam) - Institutional Repository (publishedVersion, other-oa)
  • EUR Research Repository (Erasmus University Rotterdam) (publishedVersion, cc-by-nc)
  • LSHTM Research Online (London School of Hygiene and Tropical Medicine) (acceptedVersion)
  • Institutional Research Information System (Università degli Studi di Trento) (submittedVersion, cc-by-nc)
  • Pure Amsterdam UMC (submittedVersion, cc-by)
  • EUR Research Repository (Erasmus University Rotterdam) (submittedVersion, cc-by-nc)
  • ArTS Archivio della ricerca di Trieste (University of Trieste https://www.units.it/) (submittedVersion)
  • DIGITAL.CSIC (Spanish National Research Council (CSIC)) (submittedVersion)
  • UCL Discovery (University College London) (submittedVersion)
  • Florence Research (University of Florence) (submittedVersion)
  • Institutional Research Information System (Università degli Studi di Brescia) (submittedVersion)
  • Lirias (submittedVersion)
  • DZNE Pub (submittedVersion)
  • Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) (submittedVersion)
  • Archive ouverte UNIGE (University of Geneva) (submittedVersion)
  • Apollo (University of Cambridge) (submittedVersion)
  • Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
  • Apollo
Funders
  • Canadian Institutes of Health Research (MOP 111169)
  • Fonds de Recherche du Québec - Santé (25262)
  • Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada (4140438 - 2012)
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Health Sciences › Medicine › Clinical Neurology › Amyotrophic Lateral Sclerosis Research
  • Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Alzheimer's disease research and treatments
Keywords
behavioral variant frontotemporal dementia, MRI diagnosis, deformation-based morphometry, semantic fluency, random forest, structural neuroimaging, neurodegenerative disease prediction

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: MRI data-driven algorithm for the diagnosis of behavioural variant frontotemporal dementia. https://app.cochat.ai/papers/10.1136/jnnp-2020-324106
The paper
Manera, A. L., Dadar, M., Van Swieten, J. C., Borroni, B., Sanchez-Valle, R., Moreno, F., Laforce Jr, R., Graff, C., Synofzik, M., Galimberti, D., Rowe, J. B., Masellis, M., Tartaglia, M. C., Finger, E., Vandenberghe, R., de Mendonca, A., Tagliavini, F., Santana, I., Butler, C. R., . . . FTLDNI investigators. (2021). MRI data-driven algorithm for the diagnosis of behavioural variant frontotemporal dementia. Journal of Neurology, Neurosurgery & Psychiatry. https://doi.org/10.1136/jnnp-2020-324106

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.