Nonconvulsive seizure and status epilepticus detection with deep learning in high-risk adult critically ill patients
3
4
Issued Date
2021
Copyright Date
2021
Resource Type
Language
eng
File Type
application/pdf
No. of Pages/File Size
xii, 109 leaves : ill.
Access Rights
open access
Rights
ผลงานนี้เป็นลิขสิทธิ์ของมหาวิทยาลัยมหิดล ขอสงวนไว้สำหรับเพื่อการศึกษาเท่านั้น ต้องอ้างอิงแหล่งที่มา ห้ามดัดแปลงเนื้อหา และห้ามนำไปใช้เพื่อการค้า
Rights Holder(s)
Mahidol University
Bibliographic Citation
Thesis (M.Sc. (Data Science for Health Care))--Mahidol University, 2021)
Suggested Citation
Jitsama Tanlamai Nonconvulsive seizure and status epilepticus detection with deep learning in high-risk adult critically ill patients. Thesis (M.Sc. (Data Science for Health Care))--Mahidol University, 2021). doi:10.67546/MU.TH.6136815 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/113815
Title
Nonconvulsive seizure and status epilepticus detection with deep learning in high-risk adult critically ill patients
Author(s)
Abstract
Nonconvulsive seizure (NCS) is an electrographic seizure activity without manifest motor activity, and prolonged NCS is Nonconvulsive status epilepticus (NCSE). Their delayed treatment could lead to patients’ permanent neurological damage and poor outcomes. Electroencephalogram (EEG) is mandatory for NCS/NCSE detection in critically ill patients, but its interpretation is challenging even though there are Salzburg criteria, the recent consensus on NCS/NCSE conclusion from EEG. This study is a multicenter data collection. The objective is to develop a deep learning model to detect the NCS/NCSE. The two model inputs are variable-length EEG and patients’ clinical information. The 25-component Mel-Frequency Cepstrum Coefficients (MFCC) are the EEG representation while the patients’ clinical data were directly input into the model. The deep learning model consists of two main components. Gated Recurrent Unit (GRU) performs as the feature extraction model, and Neural Network (NN) is the classifier. A total of 337 EEG diagnoses were labeled following the Salzburg criteria, and the positive cases are approximately 27 percent. The final model presents a promising performance. Its recall rate is 86.7 percent during internal validation, and the false-negative rate is 13.3 percent. Implication of the Thesis: The proposed model could be used as a screening tool in the clinical setting to reduce the prone to delayed treatment and underdiagnosis, provided that its performance resulting from external validation is satisfied.
Degree Name
Master of Science
Degree Level
Master's degree
Degree Department
Faculty of Medicine Ramathibodi Hospital
Degree Discipline
Data Science for Health Care
Degree Grantor(s)
Mahidol University