Interpretable Transformer Models for rs-fMRI Epilepsy Classification and Biomarker Discovery Article Swipe
A. Sundar
,
Varina L. Boerwinkle
,
B. Vimala
,
Olivia Leggio
,
Masoomeh Kazemi
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1101/2025.09.02.25334737
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1101/2025.09.02.25334737
Background Automated interpretation of resting-state fMRI (rs-fMRI) for epilepsy diagnosis remains a challenge. We developed a regularized transformer that models parcel-wise spatial patterns and long-range temporal dynamics to classify epilepsy and generate interpretable, network-level candidate biomarkers. Methods Inputs were Schaefer-200 parcel time series extracted after standardized preprocessing (fMRIPrep). The Regularized Transformer is an attention-based sequence model with learned positional encoding and multi-head self-attention, combined with fMRI-specific regularization (dropout, weight decay, gradient clipping) and augmentation to improve robustness on modest clinical cohorts. Training used stratified group 4-fold cross-validation on n=65 (30 epilepsy, 35 controls) with fMRI-specific augmentation (time-warping, adaptive noise, structured masking). We compared the transformer to seven baselines (MLP, 1D-CNN, LSTM, CNN–LSTM, GCN, GAT, Attention-Only). External validation used an independent set (10 UNC epilepsy cohort, 10 controls). Biomarker discovery combined gradient-based attributions with parcelwise statistics and connectivity contrasts. Results On an illustrative best-performing fold, the transformer attained Accuracy 0.77, Sensitivity 0.83, Specificity 0.88, F1-Score 0.77, and AUC 0.76. Averaged cross-validation performance was lower but consistent with these findings. External testing yielded Accuracy 0.60, AUC 0.64, Specificity 0.80, Sensitivity 0.40. Attribution-guided analysis identified distributed, network-level candidate biomarkers concentrated in limbic, somatomotor, default-mode and salience systems. Conclusions A regularized transformer on parcel-level rs-fMRI can achieve strong within-fold discrimination and produce interpretable candidate biomarkers. Results are encouraging but preliminary larger multi-site validation, stability testing and multiple-comparison control are required prior to clinical translation.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1101/2025.09.02.25334737
- https://www.medrxiv.org/content/medrxiv/early/2025/09/04/2025.09.02.25334737.full.pdf
- OA Status
- green
- References
- 37
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4413974885
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4413974885Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1101/2025.09.02.25334737Digital Object Identifier
- Title
-
Interpretable Transformer Models for rs-fMRI Epilepsy Classification and Biomarker DiscoveryWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-09-04Full publication date if available
- Authors
-
A. Sundar, Varina L. Boerwinkle, B. Vimala, Olivia Leggio, Masoomeh KazemiList of authors in order
- Landing page
-
https://doi.org/10.1101/2025.09.02.25334737Publisher landing page
- PDF URL
-
https://www.medrxiv.org/content/medrxiv/early/2025/09/04/2025.09.02.25334737.full.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://www.medrxiv.org/content/medrxiv/early/2025/09/04/2025.09.02.25334737.full.pdfDirect OA link when available
- Concepts
-
Epilepsy, Biomarker discovery, Biomarker, Transformer, Artificial intelligence, Computer science, Neuroscience, Machine learning, Psychology, Biology, Engineering, Gene, Electrical engineering, Biochemistry, Voltage, ProteomicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
37Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4413974885 |
|---|---|
| doi | https://doi.org/10.1101/2025.09.02.25334737 |
| ids.doi | https://doi.org/10.1101/2025.09.02.25334737 |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/40950490 |
| ids.openalex | https://openalex.org/W4413974885 |
| fwci | |
| type | preprint |
| title | Interpretable Transformer Models for rs-fMRI Epilepsy Classification and Biomarker Discovery |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10429 |
| topics[0].field.id | https://openalex.org/fields/28 |
| topics[0].field.display_name | Neuroscience |
| topics[0].score | 0.9876000285148621 |
| topics[0].domain.id | https://openalex.org/domains/1 |
| topics[0].domain.display_name | Life Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2805 |
| topics[0].subfield.display_name | Cognitive Neuroscience |
| topics[0].display_name | EEG and Brain-Computer Interfaces |
| topics[1].id | https://openalex.org/T10241 |
| topics[1].field.id | https://openalex.org/fields/28 |
| topics[1].field.display_name | Neuroscience |
| topics[1].score | 0.9765999913215637 |
| topics[1].domain.id | https://openalex.org/domains/1 |
| topics[1].domain.display_name | Life Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2805 |
| topics[1].subfield.display_name | Cognitive Neuroscience |
| topics[1].display_name | Functional Brain Connectivity Studies |
| topics[2].id | https://openalex.org/T11948 |
| topics[2].field.id | https://openalex.org/fields/25 |
| topics[2].field.display_name | Materials Science |
| topics[2].score | 0.9053000211715698 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2505 |
| topics[2].subfield.display_name | Materials Chemistry |
| topics[2].display_name | Machine Learning in Materials Science |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2778186239 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6680938005447388 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q41571 |
| concepts[0].display_name | Epilepsy |
| concepts[1].id | https://openalex.org/C124535831 |
| concepts[1].level | 4 |
| concepts[1].score | 0.5106125473976135 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q4915074 |
| concepts[1].display_name | Biomarker discovery |
| concepts[2].id | https://openalex.org/C2781197716 |
| concepts[2].level | 2 |
| concepts[2].score | 0.45173555612564087 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q864574 |
| concepts[2].display_name | Biomarker |
| concepts[3].id | https://openalex.org/C66322947 |
| concepts[3].level | 3 |
| concepts[3].score | 0.43970224261283875 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[3].display_name | Transformer |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4355012774467468 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C41008148 |
| concepts[5].level | 0 |
| concepts[5].score | 0.42385855317115784 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[5].display_name | Computer science |
| concepts[6].id | https://openalex.org/C169760540 |
| concepts[6].level | 1 |
| concepts[6].score | 0.42121583223342896 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q207011 |
| concepts[6].display_name | Neuroscience |
| concepts[7].id | https://openalex.org/C119857082 |
| concepts[7].level | 1 |
| concepts[7].score | 0.35348159074783325 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[7].display_name | Machine learning |
| concepts[8].id | https://openalex.org/C15744967 |
| concepts[8].level | 0 |
| concepts[8].score | 0.299096018075943 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[8].display_name | Psychology |
| concepts[9].id | https://openalex.org/C86803240 |
| concepts[9].level | 0 |
| concepts[9].score | 0.1840514838695526 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[9].display_name | Biology |
| concepts[10].id | https://openalex.org/C127413603 |
| concepts[10].level | 0 |
| concepts[10].score | 0.17822381854057312 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[10].display_name | Engineering |
| concepts[11].id | https://openalex.org/C104317684 |
| concepts[11].level | 2 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[11].display_name | Gene |
| concepts[12].id | https://openalex.org/C119599485 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q43035 |
| concepts[12].display_name | Electrical engineering |
| concepts[13].id | https://openalex.org/C55493867 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[13].display_name | Biochemistry |
| concepts[14].id | https://openalex.org/C165801399 |
| concepts[14].level | 2 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[14].display_name | Voltage |
| concepts[15].id | https://openalex.org/C46111723 |
| concepts[15].level | 3 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q471857 |
| concepts[15].display_name | Proteomics |
| keywords[0].id | https://openalex.org/keywords/epilepsy |
| keywords[0].score | 0.6680938005447388 |
| keywords[0].display_name | Epilepsy |
| keywords[1].id | https://openalex.org/keywords/biomarker-discovery |
| keywords[1].score | 0.5106125473976135 |
| keywords[1].display_name | Biomarker discovery |
| keywords[2].id | https://openalex.org/keywords/biomarker |
| keywords[2].score | 0.45173555612564087 |
| keywords[2].display_name | Biomarker |
| keywords[3].id | https://openalex.org/keywords/transformer |
| keywords[3].score | 0.43970224261283875 |
| keywords[3].display_name | Transformer |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.4355012774467468 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/computer-science |
| keywords[5].score | 0.42385855317115784 |
| keywords[5].display_name | Computer science |
| keywords[6].id | https://openalex.org/keywords/neuroscience |
| keywords[6].score | 0.42121583223342896 |
| keywords[6].display_name | Neuroscience |
| keywords[7].id | https://openalex.org/keywords/machine-learning |
| keywords[7].score | 0.35348159074783325 |
| keywords[7].display_name | Machine learning |
| keywords[8].id | https://openalex.org/keywords/psychology |
| keywords[8].score | 0.299096018075943 |
| keywords[8].display_name | Psychology |
| keywords[9].id | https://openalex.org/keywords/biology |
| keywords[9].score | 0.1840514838695526 |
| keywords[9].display_name | Biology |
| keywords[10].id | https://openalex.org/keywords/engineering |
| keywords[10].score | 0.17822381854057312 |
| keywords[10].display_name | Engineering |
| language | en |
| locations[0].id | doi:10.1101/2025.09.02.25334737 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306402567 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | bioRxiv (Cold Spring Harbor Laboratory) |
| locations[0].source.host_organization | https://openalex.org/I2750212522 |
| locations[0].source.host_organization_name | Cold Spring Harbor Laboratory |
| locations[0].source.host_organization_lineage | https://openalex.org/I2750212522 |
| locations[0].license | other-oa |
| locations[0].pdf_url | https://www.medrxiv.org/content/medrxiv/early/2025/09/04/2025.09.02.25334737.full.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/other-oa |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.1101/2025.09.02.25334737 |
| locations[1].id | pmid:40950490 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306525036 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | PubMed |
| locations[1].source.host_organization | https://openalex.org/I1299303238 |
| locations[1].source.host_organization_name | National Institutes of Health |
| locations[1].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | publishedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | medRxiv : the preprint server for health sciences |
| locations[1].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/40950490 |
| indexed_in | crossref, pubmed |
| authorships[0].author.id | https://openalex.org/A5108769945 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | A. Sundar |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I114027177 |
| authorships[0].affiliations[0].raw_affiliation_string | University of North Carolina at Chapel Hill |
| authorships[0].institutions[0].id | https://openalex.org/I114027177 |
| authorships[0].institutions[0].ror | https://ror.org/0130frc33 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I114027177 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | University of North Carolina at Chapel Hill |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Andrew Jeyabose Sundar |
| authorships[0].is_corresponding | True |
| authorships[0].raw_affiliation_strings | University of North Carolina at Chapel Hill |
| authorships[1].author.id | https://openalex.org/A5000141923 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-1429-2994 |
| authorships[1].author.display_name | Varina L. Boerwinkle |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I114027177 |
| authorships[1].affiliations[0].raw_affiliation_string | University of North Carolina at Chapel Hill |
| authorships[1].institutions[0].id | https://openalex.org/I114027177 |
| authorships[1].institutions[0].ror | https://ror.org/0130frc33 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I114027177 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | University of North Carolina at Chapel Hill |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Varina Louise Boerwinkle |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of North Carolina at Chapel Hill |
| authorships[2].author.id | https://openalex.org/A5029046461 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | B. Vimala |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I114027177 |
| authorships[2].affiliations[0].raw_affiliation_string | University of North Carolina at Chapel Hill |
| authorships[2].institutions[0].id | https://openalex.org/I114027177 |
| authorships[2].institutions[0].ror | https://ror.org/0130frc33 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I114027177 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | University of North Carolina at Chapel Hill |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Belfin Robinson Vimala |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | University of North Carolina at Chapel Hill |
| authorships[3].author.id | https://openalex.org/A5107691337 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Olivia Leggio |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I114027177 |
| authorships[3].affiliations[0].raw_affiliation_string | University of North Carolina at Chapel Hill |
| authorships[3].institutions[0].id | https://openalex.org/I114027177 |
| authorships[3].institutions[0].ror | https://ror.org/0130frc33 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I114027177 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | University of North Carolina at Chapel Hill |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Olivia Leggio |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | University of North Carolina at Chapel Hill |
| authorships[4].author.id | https://openalex.org/A5102738531 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-4031-8967 |
| authorships[4].author.display_name | Masoomeh Kazemi |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I114027177 |
| authorships[4].affiliations[0].raw_affiliation_string | University of North Carolina at Chapel Hill |
| authorships[4].institutions[0].id | https://openalex.org/I114027177 |
| authorships[4].institutions[0].ror | https://ror.org/0130frc33 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I114027177 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | University of North Carolina at Chapel Hill |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Meitra Kazemi |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | University of North Carolina at Chapel Hill |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.medrxiv.org/content/medrxiv/early/2025/09/04/2025.09.02.25334737.full.pdf |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-09-05T00:00:00 |
| display_name | Interpretable Transformer Models for rs-fMRI Epilepsy Classification and Biomarker Discovery |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10429 |
| primary_topic.field.id | https://openalex.org/fields/28 |
| primary_topic.field.display_name | Neuroscience |
| primary_topic.score | 0.9876000285148621 |
| primary_topic.domain.id | https://openalex.org/domains/1 |
| primary_topic.domain.display_name | Life Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2805 |
| primary_topic.subfield.display_name | Cognitive Neuroscience |
| primary_topic.display_name | EEG and Brain-Computer Interfaces |
| related_works | https://openalex.org/W112583468, https://openalex.org/W96119380, https://openalex.org/W3023706879, https://openalex.org/W4298030740, https://openalex.org/W4404588215, https://openalex.org/W2108949684, https://openalex.org/W4246773350, https://openalex.org/W1965976436, https://openalex.org/W2012655824, https://openalex.org/W3177170977 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1101/2025.09.02.25334737 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306402567 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | bioRxiv (Cold Spring Harbor Laboratory) |
| best_oa_location.source.host_organization | https://openalex.org/I2750212522 |
| best_oa_location.source.host_organization_name | Cold Spring Harbor Laboratory |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I2750212522 |
| best_oa_location.license | other-oa |
| best_oa_location.pdf_url | https://www.medrxiv.org/content/medrxiv/early/2025/09/04/2025.09.02.25334737.full.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/other-oa |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.1101/2025.09.02.25334737 |
| primary_location.id | doi:10.1101/2025.09.02.25334737 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306402567 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | bioRxiv (Cold Spring Harbor Laboratory) |
| primary_location.source.host_organization | https://openalex.org/I2750212522 |
| primary_location.source.host_organization_name | Cold Spring Harbor Laboratory |
| primary_location.source.host_organization_lineage | https://openalex.org/I2750212522 |
| primary_location.license | other-oa |
| primary_location.pdf_url | https://www.medrxiv.org/content/medrxiv/early/2025/09/04/2025.09.02.25334737.full.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/other-oa |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.1101/2025.09.02.25334737 |
| publication_date | 2025-09-04 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4412492677, https://openalex.org/W4389009956, https://openalex.org/W4407341458, https://openalex.org/W4405383218, https://openalex.org/W2917996785, https://openalex.org/W4284989178, https://openalex.org/W1992328374, https://openalex.org/W2157106546, https://openalex.org/W2009494091, https://openalex.org/W1510928716, https://openalex.org/W2951617899, https://openalex.org/W4295750005, https://openalex.org/W4403091601, https://openalex.org/W4404040781, https://openalex.org/W4383215297, https://openalex.org/W2998311683, https://openalex.org/W2038068904, https://openalex.org/W2526511911, https://openalex.org/W4403294039, https://openalex.org/W4283784208, https://openalex.org/W4205445870, https://openalex.org/W4283727927, https://openalex.org/W4401895152, https://openalex.org/W6925522492, https://openalex.org/W4392747348, https://openalex.org/W2157825442, https://openalex.org/W1966716734, https://openalex.org/W2117897510, https://openalex.org/W2138790588, https://openalex.org/W3007453563, https://openalex.org/W2119910794, https://openalex.org/W4404094317, https://openalex.org/W2964936018, https://openalex.org/W4392143827, https://openalex.org/W3095479837, https://openalex.org/W4226224676, https://openalex.org/W4402192457 |
| referenced_works_count | 37 |
| abstract_inverted_index.A | 196 |
| abstract_inverted_index.a | 12, 16 |
| abstract_inverted_index.10 | 126 |
| abstract_inverted_index.35 | 92 |
| abstract_inverted_index.On | 140 |
| abstract_inverted_index.We | 14, 102 |
| abstract_inverted_index.an | 53, 119, 141 |
| abstract_inverted_index.in | 188 |
| abstract_inverted_index.is | 52 |
| abstract_inverted_index.of | 4 |
| abstract_inverted_index.on | 78, 88, 199 |
| abstract_inverted_index.to | 28, 75, 106, 228 |
| abstract_inverted_index.(10 | 122 |
| abstract_inverted_index.(30 | 90 |
| abstract_inverted_index.AUC | 157, 174 |
| abstract_inverted_index.The | 49 |
| abstract_inverted_index.UNC | 123 |
| abstract_inverted_index.and | 24, 31, 61, 73, 136, 156, 192, 207, 222 |
| abstract_inverted_index.are | 213, 225 |
| abstract_inverted_index.but | 164, 215 |
| abstract_inverted_index.can | 202 |
| abstract_inverted_index.for | 8 |
| abstract_inverted_index.set | 121 |
| abstract_inverted_index.the | 104, 145 |
| abstract_inverted_index.was | 162 |
| abstract_inverted_index.GAT, | 114 |
| abstract_inverted_index.GCN, | 113 |
| abstract_inverted_index.fMRI | 6 |
| abstract_inverted_index.n=65 | 89 |
| abstract_inverted_index.that | 19 |
| abstract_inverted_index.time | 42 |
| abstract_inverted_index.used | 83, 118 |
| abstract_inverted_index.were | 39 |
| abstract_inverted_index.with | 57, 65, 94, 133, 166 |
| abstract_inverted_index.(MLP, | 109 |
| abstract_inverted_index.0.40. | 179 |
| abstract_inverted_index.0.60, | 173 |
| abstract_inverted_index.0.64, | 175 |
| abstract_inverted_index.0.76. | 158 |
| abstract_inverted_index.0.77, | 149, 155 |
| abstract_inverted_index.0.80, | 177 |
| abstract_inverted_index.0.83, | 151 |
| abstract_inverted_index.0.88, | 153 |
| abstract_inverted_index.LSTM, | 111 |
| abstract_inverted_index.after | 45 |
| abstract_inverted_index.fold, | 144 |
| abstract_inverted_index.group | 85 |
| abstract_inverted_index.lower | 163 |
| abstract_inverted_index.model | 56 |
| abstract_inverted_index.prior | 227 |
| abstract_inverted_index.seven | 107 |
| abstract_inverted_index.these | 167 |
| abstract_inverted_index.4-fold | 86 |
| abstract_inverted_index.Inputs | 38 |
| abstract_inverted_index.decay, | 70 |
| abstract_inverted_index.larger | 217 |
| abstract_inverted_index.models | 20 |
| abstract_inverted_index.modest | 79 |
| abstract_inverted_index.noise, | 99 |
| abstract_inverted_index.parcel | 41 |
| abstract_inverted_index.series | 43 |
| abstract_inverted_index.strong | 204 |
| abstract_inverted_index.weight | 69 |
| abstract_inverted_index.1D-CNN, | 110 |
| abstract_inverted_index.Methods | 37 |
| abstract_inverted_index.Results | 139, 212 |
| abstract_inverted_index.achieve | 203 |
| abstract_inverted_index.cohort, | 125 |
| abstract_inverted_index.control | 224 |
| abstract_inverted_index.improve | 76 |
| abstract_inverted_index.learned | 58 |
| abstract_inverted_index.limbic, | 189 |
| abstract_inverted_index.produce | 208 |
| abstract_inverted_index.remains | 11 |
| abstract_inverted_index.rs-fMRI | 201 |
| abstract_inverted_index.spatial | 22 |
| abstract_inverted_index.testing | 170, 221 |
| abstract_inverted_index.yielded | 171 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.Accuracy | 148, 172 |
| abstract_inverted_index.Averaged | 159 |
| abstract_inverted_index.External | 116, 169 |
| abstract_inverted_index.F1-Score | 154 |
| abstract_inverted_index.Training | 82 |
| abstract_inverted_index.adaptive | 98 |
| abstract_inverted_index.analysis | 181 |
| abstract_inverted_index.attained | 147 |
| abstract_inverted_index.classify | 29 |
| abstract_inverted_index.clinical | 80, 229 |
| abstract_inverted_index.cohorts. | 81 |
| abstract_inverted_index.combined | 64, 130 |
| abstract_inverted_index.compared | 103 |
| abstract_inverted_index.dynamics | 27 |
| abstract_inverted_index.encoding | 60 |
| abstract_inverted_index.epilepsy | 9, 30, 124 |
| abstract_inverted_index.generate | 32 |
| abstract_inverted_index.gradient | 71 |
| abstract_inverted_index.patterns | 23 |
| abstract_inverted_index.required | 226 |
| abstract_inverted_index.salience | 193 |
| abstract_inverted_index.sequence | 55 |
| abstract_inverted_index.systems. | 194 |
| abstract_inverted_index.temporal | 26 |
| abstract_inverted_index.(dropout, | 68 |
| abstract_inverted_index.(rs-fMRI) | 7 |
| abstract_inverted_index.Automated | 2 |
| abstract_inverted_index.Biomarker | 128 |
| abstract_inverted_index.baselines | 108 |
| abstract_inverted_index.candidate | 35, 185, 210 |
| abstract_inverted_index.clipping) | 72 |
| abstract_inverted_index.controls) | 93 |
| abstract_inverted_index.developed | 15 |
| abstract_inverted_index.diagnosis | 10 |
| abstract_inverted_index.discovery | 129 |
| abstract_inverted_index.epilepsy, | 91 |
| abstract_inverted_index.extracted | 44 |
| abstract_inverted_index.findings. | 168 |
| abstract_inverted_index.masking). | 101 |
| abstract_inverted_index.stability | 220 |
| abstract_inverted_index.Background | 1 |
| abstract_inverted_index.biomarkers | 186 |
| abstract_inverted_index.challenge. | 13 |
| abstract_inverted_index.consistent | 165 |
| abstract_inverted_index.contrasts. | 138 |
| abstract_inverted_index.controls). | 127 |
| abstract_inverted_index.identified | 182 |
| abstract_inverted_index.long-range | 25 |
| abstract_inverted_index.multi-head | 62 |
| abstract_inverted_index.multi-site | 218 |
| abstract_inverted_index.parcelwise | 134 |
| abstract_inverted_index.positional | 59 |
| abstract_inverted_index.robustness | 77 |
| abstract_inverted_index.statistics | 135 |
| abstract_inverted_index.stratified | 84 |
| abstract_inverted_index.structured | 100 |
| abstract_inverted_index.validation | 117 |
| abstract_inverted_index.(fMRIPrep). | 48 |
| abstract_inverted_index.CNN–LSTM, | 112 |
| abstract_inverted_index.Conclusions | 195 |
| abstract_inverted_index.Regularized | 50 |
| abstract_inverted_index.Sensitivity | 150, 178 |
| abstract_inverted_index.Specificity | 152, 176 |
| abstract_inverted_index.Transformer | 51 |
| abstract_inverted_index.biomarkers. | 36, 211 |
| abstract_inverted_index.encouraging | 214 |
| abstract_inverted_index.independent | 120 |
| abstract_inverted_index.parcel-wise | 21 |
| abstract_inverted_index.performance | 161 |
| abstract_inverted_index.preliminary | 216 |
| abstract_inverted_index.regularized | 17, 197 |
| abstract_inverted_index.transformer | 18, 105, 146, 198 |
| abstract_inverted_index.validation, | 219 |
| abstract_inverted_index.within-fold | 205 |
| abstract_inverted_index.Schaefer-200 | 40 |
| abstract_inverted_index.attributions | 132 |
| abstract_inverted_index.augmentation | 74, 96 |
| abstract_inverted_index.concentrated | 187 |
| abstract_inverted_index.connectivity | 137 |
| abstract_inverted_index.default-mode | 191 |
| abstract_inverted_index.distributed, | 183 |
| abstract_inverted_index.illustrative | 142 |
| abstract_inverted_index.parcel-level | 200 |
| abstract_inverted_index.somatomotor, | 190 |
| abstract_inverted_index.standardized | 46 |
| abstract_inverted_index.translation. | 230 |
| abstract_inverted_index.fMRI-specific | 66, 95 |
| abstract_inverted_index.interpretable | 209 |
| abstract_inverted_index.network-level | 34, 184 |
| abstract_inverted_index.preprocessing | 47 |
| abstract_inverted_index.resting-state | 5 |
| abstract_inverted_index.(time-warping, | 97 |
| abstract_inverted_index.discrimination | 206 |
| abstract_inverted_index.gradient-based | 131 |
| abstract_inverted_index.interpretable, | 33 |
| abstract_inverted_index.interpretation | 3 |
| abstract_inverted_index.regularization | 67 |
| abstract_inverted_index.attention-based | 54 |
| abstract_inverted_index.best-performing | 143 |
| abstract_inverted_index.self-attention, | 63 |
| abstract_inverted_index.Attention-Only). | 115 |
| abstract_inverted_index.cross-validation | 87, 160 |
| abstract_inverted_index.Attribution-guided | 180 |
| abstract_inverted_index.multiple-comparison | 223 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5108769945 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 5 |
| corresponding_institution_ids | https://openalex.org/I114027177 |
| citation_normalized_percentile.value | 0.44066608 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |