Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning Approach
Objectives: Hemispherotomy (HT) is a surgical option for treatment of drug-resistant seizures due to hemispheric structural lesions. Factors affecting seizure outcome have not been fully clarified. In our study, we used a brain Machine Learning (ML) approach to evaluate the possible role of Inter-he...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3425/13/1/71 |
| _version_ | 1797445261004374016 |
|---|---|
| author | Chiara Pepi Mattia Mercier Giusy Carfì Pavia Alessandro de Benedictis Federico Vigevano Maria Camilla Rossi-Espagnet Giovanni Falcicchio Carlo Efisio Marras Nicola Specchio Luca de Palma |
| author_facet | Chiara Pepi Mattia Mercier Giusy Carfì Pavia Alessandro de Benedictis Federico Vigevano Maria Camilla Rossi-Espagnet Giovanni Falcicchio Carlo Efisio Marras Nicola Specchio Luca de Palma |
| author_sort | Chiara Pepi |
| collection | DOAJ |
| description | Objectives: Hemispherotomy (HT) is a surgical option for treatment of drug-resistant seizures due to hemispheric structural lesions. Factors affecting seizure outcome have not been fully clarified. In our study, we used a brain Machine Learning (ML) approach to evaluate the possible role of Inter-hemispheric EEG Connectivity (IC) in predicting post-surgical seizure outcome. Methods: We collected 21 pediatric patients with drug-resistant epilepsy; who underwent HT in our center from 2009 to 2020; with a follow-up of at least two years. We selected 5-s windows of wakefulness and sleep pre-surgical EEG and we trained Artificial Neuronal Network (ANN) to estimate epilepsy outcome. We extracted EEG features as input data and selected the ANN with best accuracy. Results: Among 21 patients, 15 (71%) were seizure and drug-free at last follow-up. ANN showed 73.3% of accuracy, with 85% of seizure free and 40% of non-seizure free patients appropriately classified. Conclusions: The accuracy level that we reached supports the hypothesis that pre-surgical EEG features may have the potential to predict epilepsy outcome after HT. Significance: The role of pre-surgical EEG data in influencing seizure outcome after HT is still debated. We proposed a computational predictive model, with an ML approach, with a high accuracy level. |
| first_indexed | 2024-03-09T13:23:12Z |
| format | Article |
| id | doaj.art-46f5c539db4e4de490e0de41abdab254 |
| institution | Directory Open Access Journal |
| issn | 2076-3425 |
| language | English |
| last_indexed | 2024-03-09T13:23:12Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj.art-46f5c539db4e4de490e0de41abdab2542023-11-30T21:27:13ZengMDPI AGBrain Sciences2076-34252022-12-011317110.3390/brainsci13010071Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning ApproachChiara Pepi0Mattia Mercier1Giusy Carfì Pavia2Alessandro de Benedictis3Federico Vigevano4Maria Camilla Rossi-Espagnet5Giovanni Falcicchio6Carlo Efisio Marras7Nicola Specchio8Luca de Palma9Rare and Complex Epilepsies Unit, Department of Neuroscience, Bambino Gesù Children’s Hospital, IRCCS, Full Member of European Reference Network EpiCARE, 00165 Rome, ItalyRare and Complex Epilepsies Unit, Department of Neuroscience, Bambino Gesù Children’s Hospital, IRCCS, Full Member of European Reference Network EpiCARE, 00165 Rome, ItalyRare and Complex Epilepsies Unit, Department of Neuroscience, Bambino Gesù Children’s Hospital, IRCCS, Full Member of European Reference Network EpiCARE, 00165 Rome, ItalyNeurosurgery Unit, Bambino Gesù Children’s Hospital, IRCCS, Full Member of European Reference Network EpiCARE, 00165 Rome, ItalyNeurology Unit, Bambino Gesù Children’s Hospital, IRCCS, Full Member of European Reference Network EpiCARE, 00165 Rome, ItalyNeuroradiology Unit, Imaging Department, Bambino Gesù Children’s Hospital, 00165 Rome, ItalyDepartment of Basic Medical Sciences, Neurosciences and Sense Organs, University of Bari Aldo Moro, 70121 Bari, ItalyNeurosurgery Unit, Bambino Gesù Children’s Hospital, IRCCS, Full Member of European Reference Network EpiCARE, 00165 Rome, ItalyRare and Complex Epilepsies Unit, Department of Neuroscience, Bambino Gesù Children’s Hospital, IRCCS, Full Member of European Reference Network EpiCARE, 00165 Rome, ItalyRare and Complex Epilepsies Unit, Department of Neuroscience, Bambino Gesù Children’s Hospital, IRCCS, Full Member of European Reference Network EpiCARE, 00165 Rome, ItalyObjectives: Hemispherotomy (HT) is a surgical option for treatment of drug-resistant seizures due to hemispheric structural lesions. Factors affecting seizure outcome have not been fully clarified. In our study, we used a brain Machine Learning (ML) approach to evaluate the possible role of Inter-hemispheric EEG Connectivity (IC) in predicting post-surgical seizure outcome. Methods: We collected 21 pediatric patients with drug-resistant epilepsy; who underwent HT in our center from 2009 to 2020; with a follow-up of at least two years. We selected 5-s windows of wakefulness and sleep pre-surgical EEG and we trained Artificial Neuronal Network (ANN) to estimate epilepsy outcome. We extracted EEG features as input data and selected the ANN with best accuracy. Results: Among 21 patients, 15 (71%) were seizure and drug-free at last follow-up. ANN showed 73.3% of accuracy, with 85% of seizure free and 40% of non-seizure free patients appropriately classified. Conclusions: The accuracy level that we reached supports the hypothesis that pre-surgical EEG features may have the potential to predict epilepsy outcome after HT. Significance: The role of pre-surgical EEG data in influencing seizure outcome after HT is still debated. We proposed a computational predictive model, with an ML approach, with a high accuracy level.https://www.mdpi.com/2076-3425/13/1/71hemispherotomyseizure predictionoutcomebrain machine learning |
| spellingShingle | Chiara Pepi Mattia Mercier Giusy Carfì Pavia Alessandro de Benedictis Federico Vigevano Maria Camilla Rossi-Espagnet Giovanni Falcicchio Carlo Efisio Marras Nicola Specchio Luca de Palma Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning Approach Brain Sciences hemispherotomy seizure prediction outcome brain machine learning |
| title | Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning Approach |
| title_full | Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning Approach |
| title_fullStr | Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning Approach |
| title_full_unstemmed | Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning Approach |
| title_short | Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning Approach |
| title_sort | can presurgical interhemispheric eeg connectivity predict outcome in hemispheric surgery a brain machine learning approach |
| topic | hemispherotomy seizure prediction outcome brain machine learning |
| url | https://www.mdpi.com/2076-3425/13/1/71 |
| work_keys_str_mv | AT chiarapepi canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach AT mattiamercier canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach AT giusycarfipavia canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach AT alessandrodebenedictis canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach AT federicovigevano canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach AT mariacamillarossiespagnet canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach AT giovannifalcicchio canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach AT carloefisiomarras canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach AT nicolaspecchio canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach AT lucadepalma canpresurgicalinterhemisphericeegconnectivitypredictoutcomeinhemisphericsurgeryabrainmachinelearningapproach |