Estimating The Quality of Electroconvulsive Therapy Induced Seizures Using Decision Tree and Fuzzy Inference System Classifiers
| Autor: | Steve S. H. Ling, Alaa M. Al-Kaysi, Ahmed Al-Ani, W. Tjeerd Boonstra, K. Colleen Loo, Verònica Gálvez |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Computer science
media_common.quotation_subject medicine.medical_treatment Decision tree Word error rate Electroencephalography Machine learning computer.software_genre Fuzzy logic 03 medical and health sciences 0302 clinical medicine Electroconvulsive therapy Seizures medicine Humans Quality (business) Electroconvulsive Therapy Set (psychology) media_common Depressive Disorder Major medicine.diagnostic_test business.industry Decision Trees medicine.disease 030227 psychiatry Major depressive disorder Artificial intelligence business computer 030217 neurology & neurosurgery |
| Zdroj: | EMBC |
| DOI: | 10.1109/embc.2018.8513334 |
| Popis: | © 2018 IEEE. Electroconvulsive therapy (ECT) is an effective and widely used treatment for major depressive disorder, in which a brief electric current is passed through the brain to trigger a brief seizure. This study aims to identify seizure quality rating by utilizing a set of seizure parameters. We used 750 ECT EEG recordings in this experiment. Four seizure related parameters, (time of slowing, regularity, stereotypy and post-ictal suppression) are used as inputs to two classifiers, decision tree and fuzzy inference system (FIS), to predict seizure quality ratings. The two classifiers produced encouraging results with error rate of 0.31 and 0.25 for FIS and decision tree, respectively. The classification results show that the four seizure parameters provide relevant information about the rating of seizure quality. Automatic scoring of seizure quality may be beneficial to clinicians working in this field. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|