TY - JOUR
T1 - Integrating old and new complexity measures toward automated seizure detection from long-term video EEG recordings
AU - Ruiz Marín, Manuel
AU - Villegas Martínez, Irene
AU - Rodríguez Bermúdez, Germán
AU - Porfiri, Maurizio
N1 - Funding Information:
This study is part of the collaborative activities carried out under the programs of the region of Murcia (Spain): “Groups of Excellence of the region of Murcia, the Fundación Séneca, Science and Technology Agency” project 19884/GERM/15 and “Call for Fellowships for Guest Researcher Stays at Universities and OPIS” project 21144/IV/19. M.P. would like to express his gratitude to the Technical University of Cartagena for hosting him during a Sabbatical leave and acknowledge partial support from the National Science Foundation under grant number ECCS 1928614 . The authors are also grateful to the Regional Healthcare Service of Murcia (SMS) and Drs. Diego Tortosa and María López for providing LEM recordings.
Funding Information:
This study is part of the collaborative activities carried out under the programs of the region of Murcia (Spain): ?Groups of Excellence of the region of Murcia, the Fundaci?n S?neca, Science and Technology Agency? project 19884/GERM/15 and ?Call for Fellowships for Guest Researcher Stays at Universities and OPIS? project 21144/IV/19. M.P. would like to express his gratitude to the Technical University of Cartagena for hosting him during a Sabbatical leave and acknowledge partial support from the National Science Foundation under grant number ECCS 1928614. The authors are also grateful to the Regional Healthcare Service of Murcia (SMS) and Drs. Diego Tortosa and Mar?a L?pez for providing LEM recordings. Conceptualization, M.R.M. I.V.M. G.R.B. and M.P.; Methodology, M.R.M. I.V.M. and M.P.; Software, M.R.M.; Investigation and Data Curation, I.V.M.; Visualization, M.R.M. I.V.M. and G.R.B.; Writing?Original Draft, M.R.M. I.V.M. G.R.B. and M.P.; Writing?review and editing, I.V.M. and M.P.; Supervision, M.P. The authors declare no competing interests. We confirm that we have read the Journal position on issues involved in ethical publication and affirm that this report is consistent with those guidelines.
Publisher Copyright:
© 2020 The Authors
PY - 2021/1/22
Y1 - 2021/1/22
N2 - Automated seizure detection in long-term video-EEG recordings is far from being integrated into common clinical practice. Here, we leverage classical and state-of-the-art complexity measures to robustly and automatically detect seizures from scalp recordings. Brain activity is scored through eight features, encompassing traditional time domain and novel measures of recurrence. A binary classification algorithm tailored to treat unbalanced dataset is used to determine whether a time window is ictal or non-ictal from its features. The application of the algorithm on a cohort of ten adult patients with focal refractory epilepsy indicates sensitivity, specificity, and accuracy of 90%, along with a true alarm rate of 95% and less than four false alarms per day. The proposed approach emphasizes ictal patterns against noisy background without the need of data preprocessing. Finally, we benchmark our approach against previous studies on two publicly available datasets, demonstrating the good performance of our algorithm.
AB - Automated seizure detection in long-term video-EEG recordings is far from being integrated into common clinical practice. Here, we leverage classical and state-of-the-art complexity measures to robustly and automatically detect seizures from scalp recordings. Brain activity is scored through eight features, encompassing traditional time domain and novel measures of recurrence. A binary classification algorithm tailored to treat unbalanced dataset is used to determine whether a time window is ictal or non-ictal from its features. The application of the algorithm on a cohort of ten adult patients with focal refractory epilepsy indicates sensitivity, specificity, and accuracy of 90%, along with a true alarm rate of 95% and less than four false alarms per day. The proposed approach emphasizes ictal patterns against noisy background without the need of data preprocessing. Finally, we benchmark our approach against previous studies on two publicly available datasets, demonstrating the good performance of our algorithm.
KW - Algorithms
KW - Clinical Neuroscience
KW - Computer Application in Medicine
KW - Computer-Aided Diagnosis Method
KW - Techniques in Neuroscience
UR - http://www.scopus.com/inward/record.url?scp=85099254563&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099254563&partnerID=8YFLogxK
U2 - 10.1016/j.isci.2020.101997
DO - 10.1016/j.isci.2020.101997
M3 - Article
AN - SCOPUS:85099254563
SN - 2589-0042
VL - 24
JO - iScience
JF - iScience
IS - 1
M1 - 101997
ER -