Please use this identifier to cite or link to this item: https://ahro.austin.org.au/austinjspui/handle/1/31942
Full metadata record
DC FieldValueLanguage
dc.contributor.authorNhu, D-
dc.contributor.authorJanmohamed, M-
dc.contributor.authorShakhatreh, L-
dc.contributor.authorGonen, O-
dc.contributor.authorPerucca, P-
dc.contributor.authorGilligan, A-
dc.contributor.authorKwan, P-
dc.contributor.authorO'Brien, T J-
dc.contributor.authorTan, C W-
dc.contributor.authorKuhlmann, L-
dc.date2023-
dc.date.accessioned2023-01-12T05:33:51Z-
dc.date.available2023-01-12T05:33:51Z-
dc.date.issued2023-01-05-
dc.identifier.citationInternational Journal of Neural Systems 2023; 33(1)en_US
dc.identifier.issn1793-6462-
dc.identifier.urihttps://ahro.austin.org.au/austinjspui/handle/1/31942-
dc.description.abstractDeep learning for automated interictal epileptiform discharge (IED) detection has been topical with many published papers in recent years. All existing works viewed EEG signals as time-series and developed specific models for IED classification; however, general time-series classification (TSC) methods were not considered. Moreover, none of these methods were evaluated on any public datasets, making direct comparisons challenging. This paper explored two state-of-the-art convolutional-based TSC algorithms, InceptionTime and Minirocket, on IED detection. We fine-tuned and cross-evaluated them on a public (Temple University Events - TUEV) and two private datasets and provided ready metrics for benchmarking future work. We observed that the optimal parameters correlated with the clinical duration of an IED and achieved the best area under precision-recall curve (AUPRC) of 0.98 and F1 of 0.80 on the private datasets, respectively. The AUPRC and F1 on the TUEV dataset were 0.99 and 0.97, respectively. While algorithms trained on the private sets maintained their performance when tested on the TUEV data, those trained on TUEV could not generalize well to the private data. These results emerge from differences in the class distributions across datasets and indicate a need for public datasets with a better diversity of IED waveforms, background activities and artifacts to facilitate standardization and benchmarking of algorithms.en_US
dc.language.isoeng-
dc.subjectInterictal epileptiform dischargeen_US
dc.subjectclinical decision supporten_US
dc.subjectdeep learningen_US
dc.subjectelectroencephalogramen_US
dc.subjectepileptic spikesen_US
dc.subjecttime-seriesen_US
dc.titleAutomated Interictal Epileptiform Discharge Detection from Scalp EEG Using Scalable Time-series Classification Approaches.en_US
dc.typeJournal Articleen_US
dc.identifier.journaltitleInternational Journal of Neural Systemsen_US
dc.identifier.affiliationDepartment of Data Science and Artificial Intelligence, Faculty of Information Technology, Monash University, Melbourne, VIC, Australia.en_US
dc.identifier.affiliationNeurologyen_US
dc.identifier.affiliationEpilepsy Research Centreen_US
dc.identifier.affiliationDepartment of Neuroscience, Central Clinical School, Monash University, Melbourne, VIC, Australia.en_US
dc.identifier.affiliationMedicineen_US
dc.identifier.affiliationBladin-Berkovic Comprehensive Epilepsy Program, Department of Neurology, Austin Health, Melbourne, VIC, Australia.en_US
dc.identifier.doi10.1142/S0129065723500016en_US
dc.type.contentTexten_US
dc.identifier.pubmedid36599664-
dc.description.startpage2350001-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.languageiso639-1en-
item.openairetypeJournal Article-
item.grantfulltextnone-
item.cerifentitytypePublications-
Appears in Collections:Journal articles
Show simple item record

Page view(s)

26
checked on May 26, 2024

Google ScholarTM

Check


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.