A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approaches
ABSTRACT : In this research, we sought to delineate the epileptogenic zone using a dataset from the Cleveland Clinic, encompassing 28 patients who successfully underwent resective surgery and had prior SEEG recordings from both ictal and interictal periods. From time-windowed segments of these recor...
- Autores:
-
Mantilla Ramos, Yorguin José
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2023
- Institución:
- Universidad de Antioquia
- Repositorio:
- Repositorio UdeA
- Idioma:
- eng
- OAI Identifier:
- oai:bibliotecadigital.udea.edu.co:10495/37371
- Acceso en línea:
- https://hdl.handle.net/10495/37371
- Palabra clave:
- Epilepsia
Epilepsy
Electroencefalografía
Electroencephalography
Aprendizaje automático
Machine Learning
Modelos Logísticos
Logistic Models
Zona epileptogénica
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-sa/2.5/co/
| id |
UDEA2_de7f0901c51e95203325f390bcd72a2d |
|---|---|
| oai_identifier_str |
oai:bibliotecadigital.udea.edu.co:10495/37371 |
| network_acronym_str |
UDEA2 |
| network_name_str |
Repositorio UdeA |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approaches |
| dc.title.translated.spa.fl_str_mv |
Una huella de complejidad para la localización de la Zona Epileptogénica utilizando aprendizaje automático y enfoques basados en datos |
| title |
A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approaches |
| spellingShingle |
A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approaches Epilepsia Epilepsy Electroencefalografía Electroencephalography Aprendizaje automático Machine Learning Modelos Logísticos Logistic Models Zona epileptogénica |
| title_short |
A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approaches |
| title_full |
A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approaches |
| title_fullStr |
A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approaches |
| title_full_unstemmed |
A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approaches |
| title_sort |
A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approaches |
| dc.creator.fl_str_mv |
Mantilla Ramos, Yorguin José |
| dc.contributor.advisor.none.fl_str_mv |
Leahy, Richard Jerbi, Karim García Arias, Hernán Felipe |
| dc.contributor.author.none.fl_str_mv |
Mantilla Ramos, Yorguin José |
| dc.contributor.researchgroup.spa.fl_str_mv |
Grupo Neuropsicología y Conducta |
| dc.subject.decs.none.fl_str_mv |
Epilepsia Epilepsy Electroencefalografía Electroencephalography Aprendizaje automático Machine Learning Modelos Logísticos Logistic Models |
| topic |
Epilepsia Epilepsy Electroencefalografía Electroencephalography Aprendizaje automático Machine Learning Modelos Logísticos Logistic Models Zona epileptogénica |
| dc.subject.proposal.spa.fl_str_mv |
Zona epileptogénica |
| description |
ABSTRACT : In this research, we sought to delineate the epileptogenic zone using a dataset from the Cleveland Clinic, encompassing 28 patients who successfully underwent resective surgery and had prior SEEG recordings from both ictal and interictal periods. From time-windowed segments of these recordings, we derived complexity features and characterized them using their mean and standard deviation. Our analysis incorporated features such as Lempel-Ziv complexity, various entropies, fractal dimensions, and the 1/f slope of the brain activity spectrum, among others. We trained three distinct Logistic Regression Models: one using only ictal data, another using only interictal data, and a hybrid model leveraging both periods. Additionally, we trained a model using the Bern-Barcelona dataset, a known benchmark in interictal prediction. Our findings underscored that while the interictal period might be less informative in isolation, it enhances the insights drawn from the ictal phase when combined. A pivotal aspect of our research was discerning a distinctive epileptogenic zone fingerprint. Feature importance analysis pinpointed the Mean Lempel-Ziv Complexity, the standard deviation of the 1/f Slope, and the standard deviation of specific fractal dimensions as the most significant characteristics differentiating resected locations. These results not only contribute to understanding the epileptogenic zone but also foster discussions about complexity in the brain, particularly in the context of the brain criticality hypothesis. |
| publishDate |
2023 |
| dc.date.accessioned.none.fl_str_mv |
2023-11-20T15:53:15Z |
| dc.date.available.none.fl_str_mv |
2023-11-20T15:53:15Z |
| dc.date.issued.none.fl_str_mv |
2023 |
| dc.type.spa.fl_str_mv |
Tesis/Trabajo de grado - Monografía - Pregrado |
| dc.type.coar.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_7a1f |
| dc.type.redcol.spa.fl_str_mv |
https://purl.org/redcol/resource_type/TP |
| dc.type.coarversion.spa.fl_str_mv |
http://purl.org/coar/version/c_b1a7d7d4d402bcce |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
| dc.type.version.spa.fl_str_mv |
info:eu-repo/semantics/draft |
| format |
http://purl.org/coar/resource_type/c_7a1f |
| status_str |
draft |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/10495/37371 |
| url |
https://hdl.handle.net/10495/37371 |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.rights.uri.*.fl_str_mv |
http://creativecommons.org/licenses/by-nc-sa/2.5/co/ |
| dc.rights.uri.spa.fl_str_mv |
https://creativecommons.org/licenses/by-nc-sa/4.0/ |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.coar.spa.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-sa/2.5/co/ https://creativecommons.org/licenses/by-nc-sa/4.0/ http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.spa.fl_str_mv |
119 |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.spa.fl_str_mv |
Universidad de Antioquia |
| dc.publisher.place.spa.fl_str_mv |
Medellín, Colombia |
| dc.publisher.faculty.spa.fl_str_mv |
Facultad de Ingeniería. Ingeniería Electrónica |
| institution |
Universidad de Antioquia |
| bitstream.url.fl_str_mv |
https://bibliotecadigital.udea.edu.co/bitstreams/a664b5db-3a68-4dd0-a548-066f9a3a1ed1/download https://bibliotecadigital.udea.edu.co/bitstreams/990c809d-61ef-4c42-93cd-c7f9b8e9ba92/download https://bibliotecadigital.udea.edu.co/bitstreams/20132247-bcec-4b86-b0d2-ee1b303ede9c/download https://bibliotecadigital.udea.edu.co/bitstreams/9f1ed5c8-e098-471b-a9fa-f317320e9ae3/download https://bibliotecadigital.udea.edu.co/bitstreams/cb53dca1-1d6d-4957-8e9b-5e640a113c89/download |
| bitstream.checksum.fl_str_mv |
30bc04c60446da7ac844d53884e1b616 e2060682c9c70d4d30c83c51448f4eed 8a4605be74aa9ea9d79846c1fba20a33 99d2f5b07966ad251e1c83bea70a4e17 70b51299333bd8c5479e85c83db96177 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional de la Universidad de Antioquia |
| repository.mail.fl_str_mv |
aplicacionbibliotecadigitalbiblioteca@udea.edu.co |
| _version_ |
1851052623673688064 |
| spelling |
Leahy, RichardJerbi, KarimGarcía Arias, Hernán FelipeMantilla Ramos, Yorguin JoséGrupo Neuropsicología y Conducta2023-11-20T15:53:15Z2023-11-20T15:53:15Z2023https://hdl.handle.net/10495/37371ABSTRACT : In this research, we sought to delineate the epileptogenic zone using a dataset from the Cleveland Clinic, encompassing 28 patients who successfully underwent resective surgery and had prior SEEG recordings from both ictal and interictal periods. From time-windowed segments of these recordings, we derived complexity features and characterized them using their mean and standard deviation. Our analysis incorporated features such as Lempel-Ziv complexity, various entropies, fractal dimensions, and the 1/f slope of the brain activity spectrum, among others. We trained three distinct Logistic Regression Models: one using only ictal data, another using only interictal data, and a hybrid model leveraging both periods. Additionally, we trained a model using the Bern-Barcelona dataset, a known benchmark in interictal prediction. Our findings underscored that while the interictal period might be less informative in isolation, it enhances the insights drawn from the ictal phase when combined. A pivotal aspect of our research was discerning a distinctive epileptogenic zone fingerprint. Feature importance analysis pinpointed the Mean Lempel-Ziv Complexity, the standard deviation of the 1/f Slope, and the standard deviation of specific fractal dimensions as the most significant characteristics differentiating resected locations. These results not only contribute to understanding the epileptogenic zone but also foster discussions about complexity in the brain, particularly in the context of the brain criticality hypothesis.RESUMEN : En este trabajo, se buscó delimitar la zona epileptogénica utilizando un conjunto de datos de la clínica de Cleveland, la cual abarca 28 pacientes que se sometieron con éxito a cirugía resectiva. A dichos pacientes se les adquirieron registros intracraneales de EEG durante períodos ictales e interictales. A partir de segmentos de estas grabaciones, derivamos características de complejidad y las caracterizamos utilizando su media y desviación estándar. Nuestro análisis incorporó características como la complejidad de Lempel-Ziv, varias entropías, dimensiones fractales y la pendiente 1/f del espectro de actividad cerebral, entre otros. Entrenamos tres modelos distintos de Regresión Logística: uno utilizando solo datos ictales, otro utilizando solo datos interictales y un modelo híbrido que aprovecha ambos períodos. Además, se entrenó un modelo utilizando el conjunto de datos "Bern-Barcelona", el cual es un punto de referencia conocido en la predicción interictal. Nuestros hallazgos subrayaron que, a pesar de que el período interictal es menos informativo de forma aislada, puede potenciar las predicciones obtenidas de la fase ictal cuando se combinan. Un aspecto importante de la investigación fue discernir una huella electrofisiológica de la zona epileptogénica. El análisis de importancia de las características que se llevó a cabo señaló la complejidad media de Lempel-Ziv, la desviación estándar de la pendiente 1/f y la desviación estándar de dimensiones fractales específicas como las características más significativas que diferencian las ubicaciones extirpadas. Estos resultados no solo contribuyen a la comprensión de la zona epileptogénica, sino que también fomentan discusiones sobre la complejidad en el cerebro, particularmente en el contexto de la hipótesis de la criticalidad cerebral.PregradoIngeniero Electrónico119application/pdfengUniversidad de AntioquiaMedellín, ColombiaFacultad de Ingeniería. Ingeniería Electrónicahttp://creativecommons.org/licenses/by-nc-sa/2.5/co/https://creativecommons.org/licenses/by-nc-sa/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2A complexity fingerprint for the localization of the Epileptogenic Zone using machine learning and data-driven approachesUna huella de complejidad para la localización de la Zona Epileptogénica utilizando aprendizaje automático y enfoques basados en datosTesis/Trabajo de grado - Monografía - Pregradohttp://purl.org/coar/resource_type/c_7a1fhttps://purl.org/redcol/resource_type/TPhttp://purl.org/coar/version/c_b1a7d7d4d402bcceinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/draftEpilepsiaEpilepsyElectroencefalografíaElectroencephalographyAprendizaje automáticoMachine LearningModelos LogísticosLogistic ModelsZona epileptogénicaPublicationORIGINALMantillaYorguin_2023_LearningEpilepsyComplexity.pdfMantillaYorguin_2023_LearningEpilepsyComplexity.pdfTrabajo de grado de pregradoapplication/pdf10004290https://bibliotecadigital.udea.edu.co/bitstreams/a664b5db-3a68-4dd0-a548-066f9a3a1ed1/download30bc04c60446da7ac844d53884e1b616MD51trueAnonymousREADCC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-81051https://bibliotecadigital.udea.edu.co/bitstreams/990c809d-61ef-4c42-93cd-c7f9b8e9ba92/downloade2060682c9c70d4d30c83c51448f4eedMD52falseAnonymousREADLICENSElicense.txtlicense.txttext/plain; charset=utf-81748https://bibliotecadigital.udea.edu.co/bitstreams/20132247-bcec-4b86-b0d2-ee1b303ede9c/download8a4605be74aa9ea9d79846c1fba20a33MD53falseAnonymousREADTEXTMantillaYorguin_2023_LearningEpilepsyComplexity.pdf.txtMantillaYorguin_2023_LearningEpilepsyComplexity.pdf.txtExtracted texttext/plain100635https://bibliotecadigital.udea.edu.co/bitstreams/9f1ed5c8-e098-471b-a9fa-f317320e9ae3/download99d2f5b07966ad251e1c83bea70a4e17MD54falseAnonymousREADTHUMBNAILMantillaYorguin_2023_LearningEpilepsyComplexity.pdf.jpgMantillaYorguin_2023_LearningEpilepsyComplexity.pdf.jpgGenerated Thumbnailimage/jpeg6237https://bibliotecadigital.udea.edu.co/bitstreams/cb53dca1-1d6d-4957-8e9b-5e640a113c89/download70b51299333bd8c5479e85c83db96177MD55falseAnonymousREAD10495/37371oai:bibliotecadigital.udea.edu.co:10495/373712025-03-27 01:13:27.061http://creativecommons.org/licenses/by-nc-sa/2.5/co/open.accesshttps://bibliotecadigital.udea.edu.coRepositorio Institucional de la Universidad de Antioquiaaplicacionbibliotecadigitalbiblioteca@udea.edu.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 |