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

The DOI matches its Crossref record; 174 of the 176 references it cites were found in a registry or an index; 36 of the 125 sources its claims cite were checked for support.

Multiclass characterization of frontotemporal dementia variants via multimodal brain network computational inference

Open access
Gonzalez-Gomez, Raul, Ibañez, Agustín, Moguilner, Sebastian · 2023 · Network Neuroscience

Abstract

Characterizing a particular neurodegenerative condition against others possible diseases remains a challenge along clinical, biomarker, and neuroscientific levels. This is the particular case of frontotemporal dementia (FTD) variants, where their specific characterization requires high levels of expertise and multidisciplinary teams to subtly distinguish among similar physiopathological processes. Here, we used a computational approach of multimodal brain networks to address simultaneous multiclass classification of 298 subjects (one group against all others), including five FTD variants: behavioral variant FTD, corticobasal syndrome, nonfluent variant primary progressive aphasia, progressive supranuclear palsy, and semantic variant primary progressive aphasia, with healthy controls. Fourteen machine learning classifiers were trained with functional and structural connectivity metrics calculated through different methods. Due to the large number of variables, dimensionality was reduced, employing statistical comparisons and progressive elimination to assess feature stability under nested cross-validation. The machine learning performance was measured through the area under the receiver operating characteristic curves, reaching 0.81 on average, with a standard deviation of 0.09. Furthermore, the contributions of demographic and cognitive data were also assessed via multifeatured classifiers. An accurate simultaneous multiclass classification of each FTD variant against other variants and controls was obtained based on the selection of an optimum set of features. The classifiers incorporating the brain’s network and cognitive assessment increased performance metrics. Multimodal classifiers evidenced specific variants’ compromise, across modalities and methods through feature importance analysis. If replicated and validated, this approach may help to support clinical decision tools aimed to detect specific affectations in the context of overlapping diseases.

Overview

CoChat Summary

TL;DR

This study used multimodal functional and structural brain-network features plus demographic/cognitive variables to perform simultaneous multiclass classification of five frontotemporal dementia variants and healthy controls. XGBoost models achieved up to AUC = 0.95, with cognitive features generally improving performance and feature-importance analyses highlighting variant-specific network alterations.

Key findings

  • In 298 subjects (HC n = 99; bvFTD n = 47; CBS n = 38; nfvPPA n = 34; PSP n = 42; svPPA n = 38), multiclass classification reached an average AUC of 0.81 (SD = 0.09) across models, with the best model—raw functional connectivity plus cognitive features—reaching AUC = 0.95.
  • Adding cognitive/demographic features increased performance across modalities: raw functional connectivity rose from AUC = 0.92 to 0.95; ROI-to-ROI functional from 0.75 to 0.80; functional graph from 0.63 to 0.89; raw structural from 0.84 to 0.85; ROI-to-ROI structural from 0.70 to 0.80; structural graph from 0.73 to 0.83; and all combined connectivity from 0.80 to 0.89.
  • The top three models were the raw functional multifeatured model, the raw functional connectivity model, and the multimodal multifeatured model; differences among these top models were not statistically significant (p > 0.05).
  • Feature-importance analyses showed variant-specific patterns, including frontal/insular/temporal alterations in bvFTD, speech-language and left-hemisphere regions in nfvPPA, temporal disconnection in svPPA, motor/parietal areas in CBS, and thalamic connections in PSP.

Methods

  • Data came from LONI’s NIFD and 4RTNI databases; clinical diagnosis followed current criteria, and healthy controls were split into two matched subsamples (HCsub1 and HCsub2, each n = 50) for age, sex, and education matching.
  • Brain-network features included two modalities (functional and structural connectivity) and three methods (raw/voxel-level, ROI-to-ROI, and graph connectivity), derived from rs-fMRI and DWI; structural DWI data were available for 264 subjects.
  • Fourteen XGBoost models were trained for one-vs-all multiclass classification, with dimensionality reduction via group-level statistical filtering and progressive feature elimination under nested cross-validation; performance was evaluated with microaverage AUC, using 80% training/validation and 20% independent testing.

Limitations

  • The paper states that the sample came from a single database, lacked histopathological diagnosis confirmation, did not compare against standard PET/plasma biomarkers, used only the MMSE rather than FTD-specific cognitive tests, relied mainly on the AAL atlas (with a representative HCP-atlas comparison), and included mostly early-to-moderate-stage patients.
  • The text also makes evident that the study is cross-sectional, so it cannot assess disease progression or longitudinal monitoring, and that despite scanner-variability checks, MRI data were acquired from two scanners.

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

Integrity signals

Registry

Crossref · 10.1162/netn_a_00285

Cites

174 of 174 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1. Goal and pipeline. (A) Graphic representation of multiclass classification where each group is differentiated from the other groups. In this case, there are six comparisons (k = 6). (B) Pipeline representation. I: MRI and the sequences employed. II: Preprocessing steps depended on the sequence type. III: Connectivity analysis included two modalities (functional and structural) and three methods (raw, ROI-to-ROI, and graph connectivity). IV: XGBoost algorithms were used for multiclass classification of groups, using both modalities and three methods of connectivity, with and without demographic and cognitive measures. bvFTD = behavioral variant of FTD; CBS = corticobasal syndrome; DWI = diffusion-weighted images; HC = healthy control; nfvPPA = nonfluent variant primary progressive aphasia; PSP = progressive supranuclear palsy; rs-fMRI; resting-state fMRI; svPPA = semantic variant primary progressive aphasia.
Figure 1. Goal and pipeline. (A) Graphic representation of multiclass classification where each group is differentiated from the other groups. In this case, there are six comparisons (k = 6). (B) Pipeline representation. I: MRI and the sequences employed. II: Preprocessing steps depended on the sequence type. III: Connectivity analysis included two modalities (functional and structural) and three methods (raw, ROI-to-ROI, and graph connectivity). IV: XGBoost algorithms were used for multiclass classification of groups, using both modalities and three methods of connectivity, with and without demographic and cognitive measures. bvFTD = behavioral variant of FTD; CBS = corticobasal syndrome; DWI = diffusion-weighted images; HC = healthy control; nfvPPA = nonfluent variant primary progressive aphasia; PSP = progressive supranuclear palsy; rs-fMRI; resting-state fMRI; svPPA = semantic variant primary progressive aphasia.CC BY · PubMed Central
Figure 2. Raw functional connectivity in five frontotemporal dementia variants. Each variant group was compared to a subsample of the healthy control group matched for sex, age, and years of education. Connectivity metrics were calculated at the voxel level and corrected by TFCE, pFEW < 0.05, where clusters represent statistically significant differences with respect to the healthy controls. ALFF = amplitude of low-frequency fluctuations; bvFTD = behavioral variant; CBS = corticobasal syndrome; fALFF = fractional amplitude of low-frequency fluctuations; L = left; nfvPPA = progressive nonfluent aphasia; PSP = progressive supranuclear palsy; R = right; svPPA = semantic variant of FTD; TFCE = threshold-free cluster enhancement.
Figure 2. Raw functional connectivity in five frontotemporal dementia variants. Each variant group was compared to a subsample of the healthy control group matched for sex, age, and years of education. Connectivity metrics were calculated at the voxel level and corrected by TFCE, pFEW < 0.05, where clusters represent statistically significant differences with respect to the healthy controls. ALFF = amplitude of low-frequency fluctuations; bvFTD = behavioral variant; CBS = corticobasal syndrome; fALFF = fractional amplitude of low-frequency fluctuations; L = left; nfvPPA = progressive nonfluent aphasia; PSP = progressive supranuclear palsy; R = right; svPPA = semantic variant of FTD; TFCE = threshold-free cluster enhancement.CC BY · PubMed Central
Figure 3. ROI-to-ROI connectivity in five variants of frontotemporal dementia. Functional connectivity (A) employing linear correlation among ROIs, while structural connectivity (B) using fractional anisotropy means of the tracts that end in each ROI. Each variant group was compared with a subsample of the HC group matched for sex, age, and years of education based on the 116 ROIs in the AAL atlas. Multiple comparisons were corrected by TFCE, pFEW < 0.05, where ROIs with similar effect patterns were grouped through a hierarchical algorithm method to achieve more meaningful results. Ant = anterior; Amyg = amygdala; bvFTD = behavioral variant; CBS = corticobasal syndrome; Cereb = cerebellum; Cing = Cingulum; Fr = frontal; Hpp = hippocampus; Inf = inferior; L = left; M = medial; Mid = middle; nfvPPA = progressive nonfluent aphasia; Occ = occipital; Op = opercular; Oper = operculum; Or = orbital; Pol M = middle pole; Pol S = superior pole; Post = posterior; PSP = progressive supranuclear palsy; R = right; Sup = superior; Supramarg = supramarginal; Supp = supplementary; svPPA = semantic variant of FTD; TFCE = threshold-free cluster enhancement; Temp = temporal; Tri = triangularis; Ver = vermis.
Figure 3. ROI-to-ROI connectivity in five variants of frontotemporal dementia. Functional connectivity (A) employing linear correlation among ROIs, while structural connectivity (B) using fractional anisotropy means of the tracts that end in each ROI. Each variant group was compared with a subsample of the HC group matched for sex, age, and years of education based on the 116 ROIs in the AAL atlas. Multiple comparisons were corrected by TFCE, pFEW < 0.05, where ROIs with similar effect patterns were grouped through a hierarchical algorithm method to achieve more meaningful results. Ant = anterior; Amyg = amygdala; bvFTD = behavioral variant; CBS = corticobasal syndrome; Cereb = cerebellum; Cing = Cingulum; Fr = frontal; Hpp = hippocampus; Inf = inferior; L = left; M = medial; Mid = middle; nfvPPA = progressive nonfluent aphasia; Occ = occipital; Op = opercular; Oper = operculum; Or = orbital; Pol M = middle pole; Pol S = superior pole; Post = posterior; PSP = progressive supranuclear palsy; R = right; Sup = superior; Supramarg = supramarginal; Supp = supplementary; svPPA = semantic variant of FTD; TFCE = threshold-free cluster enhancement; Temp = temporal; Tri = triangularis; Ver = vermis.CC BY · PubMed Central
Figure 4. Graph connectivity in five variants of frontotemporal dementia. The 116 ROIs in the AAL atlas were considered the nodes. The edges of functional connectivity (A) were linear correlation coefficients greater than 0.3, and those of structural connectivity (B) were the fractional anisotropy means of the tracts that ended in every ROI with a threshold of 0.2. Each variant group was compared with a subsample of the healthy control group matched for sex, age, and years of education based on the 116 ROIs in the AAL atlas. Multiple comparisons were corrected by FDR. Ant = anterior; BC = betweenness centrality; bvFTD = behavioral variant; CBS = corticobasal syndrome; CC = clustering coefficient; Cereb = cerebellum; Cing = cingulum; D = degree; Fr = frontal; GL = global efficiency; Hpp = hippocampus; Inf = inferior; L = left; LE = local efficiency; Med = medial; Mid = middle; nfvPPA = progressive nonfluent aphasia; Op = opercular; Oper = operculum; Orb = orbital; PSP = progressive supranuclear palsy; R = right; svPPA = semantic variant of FTD; Str = strength; Sup = superior; Supp = supplementary; Temp = temporal; Tri = triangularis.
Figure 4. Graph connectivity in five variants of frontotemporal dementia. The 116 ROIs in the AAL atlas were considered the nodes. The edges of functional connectivity (A) were linear correlation coefficients greater than 0.3, and those of structural connectivity (B) were the fractional anisotropy means of the tracts that ended in every ROI with a threshold of 0.2. Each variant group was compared with a subsample of the healthy control group matched for sex, age, and years of education based on the 116 ROIs in the AAL atlas. Multiple comparisons were corrected by FDR. Ant = anterior; BC = betweenness centrality; bvFTD = behavioral variant; CBS = corticobasal syndrome; CC = clustering coefficient; Cereb = cerebellum; Cing = cingulum; D = degree; Fr = frontal; GL = global efficiency; Hpp = hippocampus; Inf = inferior; L = left; LE = local efficiency; Med = medial; Mid = middle; nfvPPA = progressive nonfluent aphasia; Op = opercular; Oper = operculum; Orb = orbital; PSP = progressive supranuclear palsy; R = right; svPPA = semantic variant of FTD; Str = strength; Sup = superior; Supp = supplementary; Temp = temporal; Tri = triangularis.CC BY · PubMed Central
Figure 5. Raw structural connectivity in five frontotemporal dementia variants. Each variant group was compared to a subsample of the healthy control group matched for sex, age, and years of education. Connectivity was analyzed with a determinist tractography method, and multiple comparisons were controlled for by FDR (pFDR < 0.05). The results showed tracts significantly different from healthy controls. AD = axial diffusivity; bvFTD = behavioral variant; CBS = corticobasal syndrome; FA = fractional anisotropy; ISO = isotropic diffusion component derived; L = left; MD = mean diffusivity; NQA = normalized quantitative anisotropy; nfvPPA = progressive nonfluent aphasia; PSP = progressive supranuclear palsy; R = right; RD = radial diffusivity; RDI = restricted diffusion imaging; svPPA = semantic variant of FTD.
Figure 5. Raw structural connectivity in five frontotemporal dementia variants. Each variant group was compared to a subsample of the healthy control group matched for sex, age, and years of education. Connectivity was analyzed with a determinist tractography method, and multiple comparisons were controlled for by FDR (pFDR < 0.05). The results showed tracts significantly different from healthy controls. AD = axial diffusivity; bvFTD = behavioral variant; CBS = corticobasal syndrome; FA = fractional anisotropy; ISO = isotropic diffusion component derived; L = left; MD = mean diffusivity; NQA = normalized quantitative anisotropy; nfvPPA = progressive nonfluent aphasia; PSP = progressive supranuclear palsy; R = right; RD = radial diffusivity; RDI = restricted diffusion imaging; svPPA = semantic variant of FTD.CC BY · PubMed Central
Figure 6. XGBoost classifier performance with functional connectivity data for the multiclass classifications of five variants of FTD and HCs. The rows correspond to the three methods used for the analyses of functional connectivity: raw, ROI-to-ROI, and graph connectivity. The first column corresponds to the performance of models with only connectivity data from the three methods (A, D, and G). The second column presents the feature importance for both models corresponding to the same method (B, E, and H). The third column shows the multifeatured approach where connectivity data were used along with demographic and cognitive variables (C, F, and I). Additional details on classification performance are provided in Supporting Information, Supplementary data 4. ALFF: amplitude of low-frequency fluctuations; Ant = anterior; AUC = area under the ROC curve; bvFTD = behavioral variant; CBS = corticobasal syndrome; CC = clustering coefficient; Cereb = cerebellum; Cing = cingulum; cl = cluster; D = degree; Fr = frontal; GCOR = global correlation; GL = global efficiency; HC = healthy controls; Hipp; hippocampus; Inf = inferior; L = left; LCOR = local correlation; LE = local efficiency; nfvPPA = progressive nonfluent aphasia; Med = medial; Mid = middle; MMSE = Mini-Mental State Examination; Occ = occipital; Oper = operculum; Orb = orbital; PSP = progressive supranuclear palsy; R = right; Rolan = rolandic; Sup = superior; svPPA = semantic variant of FTD; Str = strength; Temp = temporal.
Figure 6. XGBoost classifier performance with functional connectivity data for the multiclass classifications of five variants of FTD and HCs. The rows correspond to the three methods used for the analyses of functional connectivity: raw, ROI-to-ROI, and graph connectivity. The first column corresponds to the performance of models with only connectivity data from the three methods (A, D, and G). The second column presents the feature importance for both models corresponding to the same method (B, E, and H). The third column shows the multifeatured approach where connectivity data were used along with demographic and cognitive variables (C, F, and I). Additional details on classification performance are provided in Supporting Information, Supplementary data 4. ALFF: amplitude of low-frequency fluctuations; Ant = anterior; AUC = area under the ROC curve; bvFTD = behavioral variant; CBS = corticobasal syndrome; CC = clustering coefficient; Cereb = cerebellum; Cing = cingulum; cl = cluster; D = degree; Fr = frontal; GCOR = global correlation; GL = global efficiency; HC = healthy controls; Hipp; hippocampus; Inf = inferior; L = left; LCOR = local correlation; LE = local efficiency; nfvPPA = progressive nonfluent aphasia; Med = medial; Mid = middle; MMSE = Mini-Mental State Examination; Occ = occipital; Oper = operculum; Orb = orbital; PSP = progressive supranuclear palsy; R = right; Rolan = rolandic; Sup = superior; svPPA = semantic variant of FTD; Str = strength; Temp = temporal.CC BY · PubMed Central
Figure 7. XGBoost classifier performance with structural connectivity data for the multiclass classifications of five variants of FTD and HCs. The rows correspond to the three methods used for the analyses of functional connectivity: raw, ROI-to-ROI, and graph connectivity. The first column corresponds to the performance of models with connectivity data only from the three methods (A, D, and G). The second column presents the feature importance for both models corresponding to the same method (B, E, and H). The third column shows the multifeatured approach where connectivity data were used along with demographic and cognitive variables (C, F, and I). Additional details on classification performance are provided in Supporting Information, Supplementary data 4. Ant = anterior; AUC = area under the ROC curve; bvFTD = behavioral variant; CBS = corticobasal syndrome; CC = clustering coefficient; Cereb = cerebellum; Cing = cingulum; D = degree; FA = fractional anisotropy; Fasc = fasciculus; Fr = frontal; GL = global efficiency; HC = healthy controls; Hipp = hippocampus; Inf = inferior; L = left; LE = local efficiency; Long = longitudinal; MD = mean diffusivity; Med = medial; NQA = normalized quantitative anisotropy; nfvPPA = progressive nonfluent aphasia; MMSE = Mini-Mental State Examination; Orb = orbital; PSP = progressive supranuclear palsy; R = right; RD = radial diffusivity; Sup = superior; Supp = supplementary; svPPA = semantic variant of FTD; Str = strength; Temp = temporal; Tri = pars triangularis.
Figure 7. XGBoost classifier performance with structural connectivity data for the multiclass classifications of five variants of FTD and HCs. The rows correspond to the three methods used for the analyses of functional connectivity: raw, ROI-to-ROI, and graph connectivity. The first column corresponds to the performance of models with connectivity data only from the three methods (A, D, and G). The second column presents the feature importance for both models corresponding to the same method (B, E, and H). The third column shows the multifeatured approach where connectivity data were used along with demographic and cognitive variables (C, F, and I). Additional details on classification performance are provided in Supporting Information, Supplementary data 4. Ant = anterior; AUC = area under the ROC curve; bvFTD = behavioral variant; CBS = corticobasal syndrome; CC = clustering coefficient; Cereb = cerebellum; Cing = cingulum; D = degree; FA = fractional anisotropy; Fasc = fasciculus; Fr = frontal; GL = global efficiency; HC = healthy controls; Hipp = hippocampus; Inf = inferior; L = left; LE = local efficiency; Long = longitudinal; MD = mean diffusivity; Med = medial; NQA = normalized quantitative anisotropy; nfvPPA = progressive nonfluent aphasia; MMSE = Mini-Mental State Examination; Orb = orbital; PSP = progressive supranuclear palsy; R = right; RD = radial diffusivity; Sup = superior; Supp = supplementary; svPPA = semantic variant of FTD; Str = strength; Temp = temporal; Tri = pars triangularis.CC BY · PubMed Central
Figure 8. XGBoost classifier performance combining functional and structural connectivity for the multiclass classification of five variants of FTD and HCs. Performance with multimodal (A) and multifetured data (C) is presented individually, as well as the feature importance for both models (B). Additional details on classification performance are provided in Supporting Information, Supplementary data 4. AUC = area under the ROC curve; bvFTD = behavioral variant; CBS = corticobasal syndrome; CC = clustering coefficient; Cereb = cerebellum; D = degree; F = functional; Fr = frontal; GL = global efficiency; HC = healthy controls; Hpp = hippocampus; Inf = inferior; L = left; LE = local efficiency; nfvPPA = progressive nonfluent aphasia; Med = medial; Mid = middle; MMSE = Mini-Mental State Examination; Oper = operculum; Orb = orbital; PSP = progressive supranuclear palsy; R = right; Rolan = rolandic; S = structural; Sup = superior; sup = supplementary; svPPA = semantic variant of FTD; Temp = temporal; Tri = pars triangularis.
Figure 8. XGBoost classifier performance combining functional and structural connectivity for the multiclass classification of five variants of FTD and HCs. Performance with multimodal (A) and multifetured data (C) is presented individually, as well as the feature importance for both models (B). Additional details on classification performance are provided in Supporting Information, Supplementary data 4. AUC = area under the ROC curve; bvFTD = behavioral variant; CBS = corticobasal syndrome; CC = clustering coefficient; Cereb = cerebellum; D = degree; F = functional; Fr = frontal; GL = global efficiency; HC = healthy controls; Hpp = hippocampus; Inf = inferior; L = left; LE = local efficiency; nfvPPA = progressive nonfluent aphasia; Med = medial; Mid = middle; MMSE = Mini-Mental State Examination; Oper = operculum; Orb = orbital; PSP = progressive supranuclear palsy; R = right; Rolan = rolandic; S = structural; Sup = superior; sup = supplementary; svPPA = semantic variant of FTD; Temp = temporal; Tri = pars triangularis.CC BY · PubMed Central
Figure 9. Performance metrics of the ML models. Mean for accuracy (A), sensitivity (B), specificity (C), F1 (D), and AUC (E) for the 14 ML models employed. *Microaverage AUC.
Figure 9. Performance metrics of the ML models. Mean for accuracy (A), sensitivity (B), specificity (C), F1 (D), and AUC (E) for the 14 ML models employed. *Microaverage AUC.CC BY · PubMed Central
Figure 10. XGBoost classifier performance with graph connectivity data for the multiclass classifications of five variants of FTD and HCs using Human Connectome Project atlas parcellation. The rows correspond to the two modalities: functional and structural. The first column corresponds to the performance of models with connectivity data only (A and D). The second column presents the feature importance (B and E). The third column shows the multifeatured approach where connectivity data were used along with demographic and cognitive variables (C and F). 10v = area 10v (anterior cingulate and medial prefrontal cortices); 24dv = ventral area 24d (paracentral and mid cingulate cortices); 4 = primary motor cortex; 45 = Area 45 (inferior frontal cortex); 47l = area 47 lateral (inferior frontal cortex); 7AL = lateral area 7A (superior parietal cortex); 8Ad (dorsolateral prefrontal cortex); AUC = area under the ROC curve; a47r = area anterior 47r (inferior frontal cortex), bvFTD = behavioral variant; CBS = corticobasal syndrome; D = degree; GL = global efficiency; HC = healthy controls; IP0 = area intraparietal 0; L = left; MMSE = Mini-Mental State Examination; MST = medial superior temporal area; MT = middle temporal area; nfvPPA = progressive nonfluent aphasia; OFC = orbital frontal complex; PeEc = perirhinal ectorhinal cortex; POS2 = parieto-occipital sulcus area 2; PSL = perisylvian language area; PSP = progressive supranuclear palsy; R = right; STSvp = superior temporal sulcus ventral posterior; svPPA = semantic variant of FTD; TE2a = temporal area 2 anterior; V1 = primary visual cortex; V7 = seventh visual area.
Figure 10. XGBoost classifier performance with graph connectivity data for the multiclass classifications of five variants of FTD and HCs using Human Connectome Project atlas parcellation. The rows correspond to the two modalities: functional and structural. The first column corresponds to the performance of models with connectivity data only (A and D). The second column presents the feature importance (B and E). The third column shows the multifeatured approach where connectivity data were used along with demographic and cognitive variables (C and F). 10v = area 10v (anterior cingulate and medial prefrontal cortices); 24dv = ventral area 24d (paracentral and mid cingulate cortices); 4 = primary motor cortex; 45 = Area 45 (inferior frontal cortex); 47l = area 47 lateral (inferior frontal cortex); 7AL = lateral area 7A (superior parietal cortex); 8Ad (dorsolateral prefrontal cortex); AUC = area under the ROC curve; a47r = area anterior 47r (inferior frontal cortex), bvFTD = behavioral variant; CBS = corticobasal syndrome; D = degree; GL = global efficiency; HC = healthy controls; IP0 = area intraparietal 0; L = left; MMSE = Mini-Mental State Examination; MST = medial superior temporal area; MT = middle temporal area; nfvPPA = progressive nonfluent aphasia; OFC = orbital frontal complex; PeEc = perirhinal ectorhinal cortex; POS2 = parieto-occipital sulcus area 2; PSL = perisylvian language area; PSP = progressive supranuclear palsy; R = right; STSvp = superior temporal sulcus ventral posterior; svPPA = semantic variant of FTD; TE2a = temporal area 2 anterior; V1 = primary visual cortex; V7 = seventh visual area.CC BY · PubMed Central

Verification

Claims the paper makes

18 Valid · 1 Not valid · 41 Not checked · 98 Own results and interpretations

93 more claims · 8 with their cited sources checked

Create a free account to see all 158 claims and to verify the 86 references still open.

See all claims — free account
  • Probably not a substantial claim. 36
  • It may state two separate claims as one. 33
  • The quote only partly states this claim. 3

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

Show all 176 references

Research works printed but not linked: 2

  1. Koyejo, 2015, Advances in neural information processing systems
  2. Wade, 2020, Hands-on gradient boosting with XGBoost and scikit-learn: Perform accessible machine learning and extreme gradient boosting with Python

Cited by

See all 10

Metadata

Authors
Gonzalez-Gomez, R., Ibañez, A., & Moguilner, S.
Affiliations
  • Latin American Brain Health Institute (BrainLat), Universidad Adolfo Ibañez, Santiago de Chile, Chile
  • Center for Social and Cognitive Neuroscience, School of Psychology, Universidad Adolfo Ibañez, Santiago de Chile, Chile
Venue
Network Neuroscience
Publisher
MIT Press
Published
2023-01-01
Volume
7
Issue
1
Pages
322-350
ISSN
2472-1751 (ISSN-L)
OpenAlex
W4304956754
Cited by
10
References
176
Citations by year
2026: 1 · 2025: 2 · 2024: 5 · 2023: 2
FWCI
1.16
Type
journal article
Language
en
Open access
Locations
  • Network Neuroscience (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Takeda Pharmaceutical Company (CW2680521)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Health Sciences › Medicine › Clinical Neurology › Traumatic Brain Injury Research
Keywords
frontotemporal dementia, multi-class classification, multimodal brain networks, functional connectivity, structural connectivity, behavioral variant FTD, corticobasal syndrome, primary progressive aphasia, progressive supranuclear palsy, semantic dementia, feature selection, feature importance, neurodegenerative disease diagnosis

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 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-05 (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: Multiclass characterization of frontotemporal dementia variants via multimodal brain network computational inference. https://app.cochat.ai/papers/10.1162/netn_a_00285
The paper
Gonzalez-Gomez, R., Ibañez, A., & Moguilner, S. (2023). Multiclass characterization of frontotemporal dementia variants via multimodal brain network computational inference. Network Neuroscience. https://doi.org/10.1162/netn_a_00285

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.