View in EDS

Deep learning on brief interictal intracranial recordings can accurately characterize seizure onset zones.

Saved in:
Bibliographic Details
Title: Deep learning on brief interictal intracranial recordings can accurately characterize seizure onset zones.
Authors: Sundrani, Sameer (AUTHOR), Johnson, Graham W. (AUTHOR), Doss, Derek J. (AUTHOR), Makhoul, Ghassan S. (AUTHOR), Hidalgo Monroy Lerma, Bruno (AUTHOR), Reda, Anas (AUTHOR), Cavender, Addison C. (AUTHOR), Liao, Emily (AUTHOR), Rogers, Baxter P. (AUTHOR), Williams Roberson, Shawniqua (AUTHOR), Bick, Sarah K. (AUTHOR), Morgan, Victoria L. (AUTHOR), Englot, Dario J. (AUTHOR)
Source: Epilepsia (Series 4). Sep2025, Vol. 66 Issue 9, p3180-3192. 13p.
Subjects: Epilepsy, Seizures (Medicine), Medical needs assessment, Artificial neural networks, Electroencephalography, Detection algorithms, Deep learning
Abstract: Objective: Epilepsy is a debilitating disorder affecting more than 50 million people worldwide, and one third of patients continue to have seizures despite maximal medical management. If patients' seizures localize to a discrete brain region, termed a seizure onset zone, resection may be curative. Localization is often confirmed with stereotactic electroencephalography; however, this may require patients to stay in the hospital for weeks to capture spontaneous seizures. Automated localization of seizure onset zones could therefore improve presurgical evaluation and decrease morbidity. Methods: Using more than 1 000 000 interictal stereotactic electroencephalography segments collected from 78 patients, we performed five‐fold cross‐validation and testing on a multichannel, multiscale, one‐dimensional convolutional neural network to classify seizure onset zones. Results: Across held‐out test sets, our models achieved a seizure onset zone classification sensitivity of.702 (95% confidence interval [CI] =.549–.805), specificity of.741 (95% CI =.652–.835), and accuracy of.738 (95% CI =.687–.795), which was significantly better than models trained on random labels. The models performed well across the entire brain, with top five region performance demonstrating accuracies between 70.0% and 88.4%. When split by outcomes, the models performed significantly better on patients with favorable Engel outcomes after resection or who were responsive neurostimulation responders. Finally, SHAP (Shapley Additive Explanation) value analysis on median‐normalized input data assigned consistently high feature importance to interictal spikes and large deflections, whereas similar analyses on histogram‐equalized data revealed differences in feature importance assignments to low‐amplitude segments. Significance: This work serves as evidence that deep learning on brief interictal intracranial data can classify seizure onset zones across the brain. Furthermore, our findings corroborate current understandings of interictal epileptiform discharges and may help uncover novel interictal morphologies. Clinical application of our models may reduce dependence on recorded seizures for localization and shorten presurgical evaluation time for drug‐resistant epilepsy patients, reducing patient morbidity and hospital costs. [ABSTRACT FROM AUTHOR]
Copyright of Epilepsia (Series 4) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Psychology and Behavioral Sciences Collection
FullText Text:
  Availability: 0
Header DbId: pbh
DbLabel: Psychology and Behavioral Sciences Collection
An: 188366472
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Deep learning on brief interictal intracranial recordings can accurately characterize seizure onset zones.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Sundrani%2C+Sameer%22">Sundrani, Sameer</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Johnson%2C+Graham+W%2E%22">Johnson, Graham W.</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Doss%2C+Derek+J%2E%22">Doss, Derek J.</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Makhoul%2C+Ghassan+S%2E%22">Makhoul, Ghassan S.</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hidalgo+Monroy+Lerma%2C+Bruno%22">Hidalgo Monroy Lerma, Bruno</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Reda%2C+Anas%22">Reda, Anas</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cavender%2C+Addison+C%2E%22">Cavender, Addison C.</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liao%2C+Emily%22">Liao, Emily</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Rogers%2C+Baxter+P%2E%22">Rogers, Baxter P.</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Williams+Roberson%2C+Shawniqua%22">Williams Roberson, Shawniqua</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bick%2C+Sarah+K%2E%22">Bick, Sarah K.</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Morgan%2C+Victoria+L%2E%22">Morgan, Victoria L.</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Englot%2C+Dario+J%2E%22">Englot, Dario J.</searchLink> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Epilepsia+%28Series+4%29%22">Epilepsia (Series 4)</searchLink>. Sep2025, Vol. 66 Issue 9, p3180-3192. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Epilepsy%22">Epilepsy</searchLink><br /><searchLink fieldCode="DE" term="%22Seizures+%28Medicine%29%22">Seizures (Medicine)</searchLink><br /><searchLink fieldCode="DE" term="%22Medical+needs+assessment%22">Medical needs assessment</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Electroencephalography%22">Electroencephalography</searchLink><br /><searchLink fieldCode="DE" term="%22Detection+algorithms%22">Detection algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Objective: Epilepsy is a debilitating disorder affecting more than 50 million people worldwide, and one third of patients continue to have seizures despite maximal medical management. If patients' seizures localize to a discrete brain region, termed a seizure onset zone, resection may be curative. Localization is often confirmed with stereotactic electroencephalography; however, this may require patients to stay in the hospital for weeks to capture spontaneous seizures. Automated localization of seizure onset zones could therefore improve presurgical evaluation and decrease morbidity. Methods: Using more than 1 000 000 interictal stereotactic electroencephalography segments collected from 78 patients, we performed five‐fold cross‐validation and testing on a multichannel, multiscale, one‐dimensional convolutional neural network to classify seizure onset zones. Results: Across held‐out test sets, our models achieved a seizure onset zone classification sensitivity of.702 (95% confidence interval [CI] =.549–.805), specificity of.741 (95% CI =.652–.835), and accuracy of.738 (95% CI =.687–.795), which was significantly better than models trained on random labels. The models performed well across the entire brain, with top five region performance demonstrating accuracies between 70.0% and 88.4%. When split by outcomes, the models performed significantly better on patients with favorable Engel outcomes after resection or who were responsive neurostimulation responders. Finally, SHAP (Shapley Additive Explanation) value analysis on median‐normalized input data assigned consistently high feature importance to interictal spikes and large deflections, whereas similar analyses on histogram‐equalized data revealed differences in feature importance assignments to low‐amplitude segments. Significance: This work serves as evidence that deep learning on brief interictal intracranial data can classify seizure onset zones across the brain. Furthermore, our findings corroborate current understandings of interictal epileptiform discharges and may help uncover novel interictal morphologies. Clinical application of our models may reduce dependence on recorded seizures for localization and shorten presurgical evaluation time for drug‐resistant epilepsy patients, reducing patient morbidity and hospital costs. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Epilepsia (Series 4) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=pbh&AN=188366472
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/epi.18478
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 3180
    Subjects:
      – SubjectFull: Epilepsy
        Type: general
      – SubjectFull: Seizures (Medicine)
        Type: general
      – SubjectFull: Medical needs assessment
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Electroencephalography
        Type: general
      – SubjectFull: Detection algorithms
        Type: general
      – SubjectFull: Deep learning
        Type: general
    Titles:
      – TitleFull: Deep learning on brief interictal intracranial recordings can accurately characterize seizure onset zones.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sundrani, Sameer
      – PersonEntity:
          Name:
            NameFull: Johnson, Graham W.
      – PersonEntity:
          Name:
            NameFull: Doss, Derek J.
      – PersonEntity:
          Name:
            NameFull: Makhoul, Ghassan S.
      – PersonEntity:
          Name:
            NameFull: Hidalgo Monroy Lerma, Bruno
      – PersonEntity:
          Name:
            NameFull: Reda, Anas
      – PersonEntity:
          Name:
            NameFull: Cavender, Addison C.
      – PersonEntity:
          Name:
            NameFull: Liao, Emily
      – PersonEntity:
          Name:
            NameFull: Rogers, Baxter P.
      – PersonEntity:
          Name:
            NameFull: Williams Roberson, Shawniqua
      – PersonEntity:
          Name:
            NameFull: Bick, Sarah K.
      – PersonEntity:
          Name:
            NameFull: Morgan, Victoria L.
      – PersonEntity:
          Name:
            NameFull: Englot, Dario J.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: Sep2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 00139580
          Numbering:
            – Type: volume
              Value: 66
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: Epilepsia (Series 4)
              Type: main
ResultId 1