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 accessAbstract
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
Cites
Statistics
Verification
Claims the paper makes
11 Valid · 3 Not valid · 4 Not checked · 51 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“In the absence of molecular biomarkers, and when combined with the syndromic overlap with other neurodegenerative disorders and psychiatric disorders, a confirmed behavioral variant frontotemporal dementia (bvFTD) diagnosis is often difficult to achieve and heavily relies on brain imaging. 6”
What the sources say
- Disputedcites [6] sourceExperimental — accuracy not yet measured
The Abstract agrees that bvFTD diagnosis is challenging because of absent molecular biomarkers and symptomatic overlap with psychiatric disorders. But it explicitly says diagnosis relies predominantly on clinical assessment because neuroimaging has limited accuracy in early disease—not that it relies heavily on brain imaging. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In general, they achieved moderate to high accuracy distinguishing bvFTD.”
What the sources say
- Not checked — no full text of the sourcecites [9] source
- Partly supportedcites [10] sourceExperimental — accuracy not yet measured
The Results (Comparison of Diffusivity Metrics; page unavailable) report sensitivity and specificity ranging from moderate to high when distinguishing bvFTD from healthy controls or patients with Alzheimer’s disease. However, the paper reports its own diffusion-metric ROC analysis, not accuracy achieved by prior machine-learning studies. (LLM, conf=0.83)
- Supportedcites [11] Meyer, 2017, Predicting behavioral variant frontotemporal dementia with pattern classification in multi-center structural MRI data, Neuroimage Clin source
The Results report 71.1%–84.6% accuracy for this study’s machine-learning classification of bvFTD patients versus healthy controls. The Discussion also reports that previous studies differentiated bvFTD/FTLD from Alzheimer’s disease with high accuracy, supporting the broad claim about prior work. The comparison groups differ between those studies. (LLM, conf=0.87)
- Supportedcites [12] source
The Training-set results (p. 11) report 72.3% balanced accuracy distinguishing bvFTD from controls and 78.7% distinguishing AD from bvFTD. The test-set results (p. 11) report 84.7% and 82.1% correct classification for those comparisons, supporting the characterization of moderate to high accuracy. (LLM, conf=0.92)
- Partly supportedcites [13] Raamana, 2014, Three-Class differential diagnosis among Alzheimer disease, frontotemporal dementia, and controls, Front Neurol sourceExperimental — accuracy not yet measured
The Discussion reports that a prior pair-wise classification study achieved 100% accuracy distinguishing dementia groups from controls, but cautions that this did not represent predictive value. The Introduction says most earlier studies grouped FTD variants together and few studied bvFTD alone, so the reported accuracy cannot be attributed specifically to distinguishing bvFTD. (LLM, conf=0.83)
- Supportedcites [14] Canu, 2017, Multiparametric MRI to distinguish early onset Alzheimer's disease and behavioural variant of frontotemporal dementia, Neuroimage Clin source
The Results (Discrimination analysis; page unavailable) report that this study’s random-forest MRI models distinguished bvFTD from early-onset Alzheimer’s disease with accuracies of 0.78–0.82. The paper is therefore an example of the machine-learning studies described, though its reported comparison is specifically between those two diagnoses. (LLM, conf=0.88)
- Supportedcites [15] source
The Results (Annualised brain volumetric changes) report a post-hoc binary logistic regression distinguishing bvFTD from AD, correctly classifying 79% of cases using caudate volume and 83% when gyrus rectus volume was added. This supports the paper as an example of a study achieving moderate-to-high classification accuracy, specifically against AD. (LLM, conf=0.86)
- Partly supportedcites [16] Wang, 2016, A comparison of magnetic resonance imaging and neuropsychological examination in the diagnostic distinction of Alzheimer’s disease and behavioral variant frontotemporal dementia, Front Aging Neurosci sourceExperimental — accuracy not yet measured
The Discussion reports that this study distinguished AD from bvFTD with approximately 51.4% accuracy using cortical volume and 62.4% using neuropsychological scores. It also reports high sensitivity and specificity in an earlier study, but that study distinguished AD from the broader FTLD group, not bvFTD specifically. The source therefore supports a moderate result for bvFTD, not the claim that prior studies generally achieved moderate to high accuracy for that distinction. (LLM, conf=0.86)
- Not checked — no full text of the sourcecites [17] source
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Recently, machine learning techniques have been applied to distinguish between bvFTD and Cognitively Normal Subjects (CNCs), Alzheimer Disease or other psychiatric and neurologic disorders on an individual level using MRI-based features. 9-17”
What the sources say
- Not checked — no full text of the sourcecites [9] source
- Partly supportedcites [10] sourceExperimental — accuracy not yet measured
The Methods section, “Sensitivity and Specificity of Diffusion Metrics in Predicting Group Membership” (page unavailable), describes ROC analysis of MRI-derived diffusivity metrics to classify individual participants as bvFTD, healthy controls, or Alzheimer’s disease. It does not describe a machine-learning technique or classification against other psychiatric or neurologic disorders. (LLM, conf=0.87)
- Partly supportedcites [11] Meyer, 2017, Predicting behavioral variant frontotemporal dementia with pattern classification in multi-center structural MRI data, Neuroimage Clin sourceExperimental — accuracy not yet measured
The Materials & methods and Conclusion describe MRI-based support vector machine classification of individual bvFTD patients versus healthy controls. The Discussion also reports that previous studies distinguished bvFTD/FTLD from Alzheimer’s disease using similar approaches. The passages do not establish the claimed distinction from other psychiatric or neurologic disorders. (LLM, conf=0.86)
- Partly supportedcites [12] sourceExperimental — accuracy not yet measured
The Training-set results (p. 11) report MRI-based SVM classification of bvFTD versus controls and versus Alzheimer disease; the paper also describes its approach as single-subject classification (Radiology, p. 15). It does not report distinguishing bvFTD from other psychiatric or neurologic disorders: the Discussion (p. 14) says it used only binary classifiers. (LLM, conf=0.88)
- Partly supportedcites [13] Raamana, 2014, Three-Class differential diagnosis among Alzheimer disease, frontotemporal dementia, and controls, Front Neurol sourceExperimental — accuracy not yet measured
The Abstract and Materials and Methods describe an MRI-based classifier distinguishing bvFTD, Alzheimer disease, and normal controls. The Discussion describes including other neurodegenerative diseases only as a possible future extension; this paper does not support the claim about distinguishing bvFTD from other psychiatric or neurologic disorders. (LLM, conf=0.89)
- Partly supportedcites [14] Canu, 2017, Multiparametric MRI to distinguish early onset Alzheimer's disease and behavioural variant of frontotemporal dementia, Neuroimage Clin sourceExperimental — accuracy not yet measured
The Abstract and Discussion describe random-forest classification of individual patients with bvFTD versus early-onset Alzheimer’s disease using MRI features. They do not report individual-level classification of bvFTD versus cognitively normal subjects or other psychiatric and neurologic disorders. (LLM, conf=0.86)
- Partly supportedcites [15] sourceExperimental — accuracy not yet measured
The Results (Annualised brain volumetric changes; page unavailable) report binary logistic regression using MRI-derived volumes to distinguish individual bvFTD cases from AD cases, correctly classifying 23 of 29 with caudate volume alone. The paper also compares bvFTD with healthy controls, but does not report individual-level classification against controls or examine other psychiatric or neurologic disorders. (LLM, conf=0.88)
- Partly supportedcites [16] Wang, 2016, A comparison of magnetic resonance imaging and neuropsychological examination in the diagnostic distinction of Alzheimer’s disease and behavioral variant frontotemporal dementia, Front Aging Neurosci sourceExperimental — accuracy not yet measured
The Discussion (page unavailable) reports MRI-feature-based machine-learning classification of AD and bvFTD, including a three-way analysis with healthy controls. The paper does not report classifying bvFTD against other psychiatric or neurologic disorders, so that extension is unsupported by this source. (LLM, conf=0.87)
- Not checked — no full text of the sourcecites [17] source
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“The performance of our classifier is superior than the performance reported in several articles that have analyzed the standard diagnostic methods currently used in the clinical practice.”
What the sources say
- Could not verifycites [7] sourceExperimental — accuracy not yet measured
The indexed passages are labelled as a paper on primary progressive aphasia, despite the cited DOI being for Rascovsky et al. The Discussion passage addresses consistency of diagnostic criteria across centres, but none of the available passages reports the performance of standard clinical diagnostic methods for comparison with the citing authors’ classifier. Searches for revised behavioural-variant frontotemporal dementia criteria and diagnostic sensitivity returned only the aphasia passages; no page numbers were supplied. (LLM, conf=0.76)
- Supportedcites [43] source
The ‘Sensitivity and Specificity for Probable and Possible bvFTD’ section reports performance figures for the FTDC diagnostic criteria, providing a benchmark for the citing authors’ comparison. The source does not assess the citing authors’ classifier; the conclusion that it performs better is their own. (LLM, conf=0.86)
- Not checked — no full text of the sourcecites [8] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The best AUC was reported by Raamana et al 13 (AUC 0.938, 100% sensitivity and 88% specificity).”
What the sources say
- Partly supportedcites [13] Raamana, 2014, Three-Class differential diagnosis among Alzheimer disease, frontotemporal dementia, and controls, Front Neurol sourceExperimental — accuracy not yet measured
The Discussion reports an AUC of 0.938 for lateral-ventricle features on an independent test set in the controls-versus-FTD comparison. The text of our copy does not give the claimed 100% sensitivity or 88% specificity for that result. It also reports an AUC of 1 for another pair, so 0.938 is not the paper’s highest reported AUC. (LLM, conf=0.85)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
31 more claims · 3 with their cited sources checked
Create a free account to see all 69 claims and every source verdict.
- It may state two separate claims as one. 25
- Probably not a substantial claim. 13
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Folstein, M. F., Folstein, S. E., & McHugh, P. R. (1975) · Journal of Psychiatric Research · doi:10.1016/0022-3956(75)90026-6 · Cited by 88,282
The Montreal Cognitive Assessment, MoCA: a brief screening tool for mild cognitive impairment
Nasreddine, Z. S., Phillips, N. A., Bédirian, V., Charbonneau, S., Whitehead, V., Collin, I., Cummings, J. L., & Chertkow, H. (2005) · Journal of the American Geriatrics Society · doi:10.1111/j.1532-5415.2005.53221.x · Cited by 25,553
Voxel-Based Morphometry—The Methods
Ashburner, J., & Friston, K. J. (2000) · NeuroImage · doi:10.1006/nimg.2000.0582 · Cited by 8,676
AVANTS, B., EPSTEIN, C., GROSSMAN, M., & GEE, J. (2008) · Medical Image Analysis · doi:10.1016/j.media.2007.06.004 · Cited by 5,669
Sensitivity of revised diagnostic criteria for the behavioural variant of frontotemporal dementia
Rascovsky, K., Hodges, J. R., Knopman, D., Mendez, M. F., Kramer, J. H., Neuhaus, J., van Swieten, J. C., Seelaar, H., Dopper, E. G. P., Onyike, C. U., et al. (2011) · Brain · doi:10.1093/brain/awr179 · Cited by 5,221
Self-citationA nonparametric method for automatic correction of intensity nonuniformity in MRI data
Sled, J. G., Zijdenbos, A. P., & Evans, A. C. (1998) · IEEE Transactions on Medical Imaging · doi:10.1109/42.668698 · Cited by 4,731
Automatic 3D intersubject registration of MR volumetric data in standardized Talairach space
Collins, D. L., Neelin, P., Peters, T. M., & Evans, A. C. (1994) · Journal of Computer Assisted Tomography · doi:10.1097/00004728-199403000-00005 · Cited by 3,431 · cited 1×
“Each native T1w volume from each timepoint was linearly registered first to the subject-specific template which was then registered to the ICBM152 template.(32) All images were then non-linearly registered to the ICBM152 template using ANTs diffeomorphic registration pipeline.”
MethodSelf-citationThe clinical global impressions scale: applying a research tool in clinical practice.
Busner, J., & Targum, S. D. (2007) · PubMed · Cited by 2,760
An Optimized Blockwise Non Local Means Denoising Filter for 3D Magnetic Resonance Images
Barillot, C., Inserm, H. I., & Barillot, C. (2007) · Cited by 1,208
Cited by
Dadar, M., Manera, A. L., Ducharme, S., & Collins, D. L. (2022) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2021.11.007 · Cited by 78
Self-citationGarcia‐Gutierrez, F., Delgado‐Alvarez, A., Delgado‐Alonso, C., Díaz‐Álvarez, J., Pytel, V., Valles‐Salgado, M., Gil, M. J., Hernández‐Lorenzo, L., Matías‐Guiu, J., Ayala, J. L., et al. (2022) · International Journal of Geriatric Psychiatry · doi:10.1002/gps.5667 · Cited by 56
Bottani, S., Burgos, N., Maire, A., Saracino, D., Ströer, S., Dormont, D., & Olivier Colliot, A. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102903 · Cited by 27
Ventricular features as reliable differentiators between bvFTD and other dementias
Manera, A. L., Dadar, M., Collins, D. L., & Ducharme, S. (2022) · NeuroImage Clinical · doi:10.1016/j.nicl.2022.102947 · Cited by 23
Self-citationMetal Toxicity and Dementia Including Frontotemporal Dementia: Current State of Knowledge
Gorini, F., & Tonacci, A. (2024) · Antioxidants · doi:10.3390/antiox13080938 · Cited by 18
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
- ORCID
- Manera, Ana L
- Dadar, Mahsa
- Van Swieten, John Cornelis
- Borroni, Barbara
- Graff, Caroline
- Synofzik, Matthis
- Galimberti, Daniela
- Rowe, James Benedict
- Masellis, Mario
- Tartaglia, Maria Carmela
- Finger, Elizabeth
- Vandenberghe, Rik
- Tagliavini, Fabrizio
- Santana, Isabel
- Butler, Christopher R
- Danek, Adrian
- Levin, Johannes
- Otto, Markus
- Frisoni, Giovanni
- Ghidoni, Roberta
- Sorbi, Sandro
- Rohrer, Jonathan Daniel
- Ducharme, Simon
- Collins, D Louis
- 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
- Semantic Scholar
- f7058caf95bab42342b0214160e2fc23d8f69323
- 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
- green
- research.vumc.nl
- 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.