Key result
A novel patient-independent seizure detection approach using CNN and BiLSTM achieved segment-based average accuracies of 97.51% and 93.70% on the CHB-MIT and SH-SDU databases, respectively.
Why the study?
Most existing seizure detection methods are highly patient-dependent and suffer from poor generalization performance.
Does a patient-independent seizure detection approach using CNN and BiLSTM improve seizure detection accuracy in EEG recordings?
Does a patient-independent seizure detection approach using CNN and BiLSTM improve seizure detection accuracy in EEG recordings?
A novel patient-independent seizure detection approach using CNN and BiLSTM achieved high accuracy and sensitivity on two EEG databases.
Answers are grounded in this paper and cite their sources.
May support generalizable automated seizure detection; hypothesis-generating pending prospective validation before clinical use.
Automatic seizure detection is of great significance for epilepsy diagnosis and alleviating the massive burden caused by manual inspection of long-term EEG. At present, most seizure detection methods are highly patient-dependent and have poor generalization performance. In this study, a novel patient-independent approach is proposed to effectively detect seizure onsets. First, the multi-channel EEG recordings are preprocessed by wavelet decomposition. Then, the Convolutional Neural Network (CNN) with proper depth works as an EEG feature extractor. Next, the obtained features are fed into a Bidirectional Long Short-Term Memory (BiLSTM) network to further capture the temporal variation characteristics. Finally, aiming to reduce the false detection rate (FDR) and improve the sensitivity, the postprocessing, including smoothing and collar, is performed on the outputs of the model. During the training stage, a novel channel perturbation technique is introduced to enhance the model generalization ability. The proposed approach is comprehensively evaluated on the CHB-MIT public scalp EEG database as well as a more challenging SH-SDU scalp EEG database we collected. Segment-based average accuracies of 97.51% and 93.70%, event-based average sensitivities of 86.51% and 89.89%, and average AUC-ROC of 90.82% and 90.75% are yielded on the CHB-MIT database and SH-SDU database, respectively.
No takes yet. Share an insight, caveat, or question.
A 2021 study studied Epilepsy. Patient-independent seizure detection based on channel-perturbation CNN and BiLSTM was evaluated on Segment-based average accuracy, event-based average sensitivity, and average AUC-ROC. A novel patient-independent seizure detection approach using CNN and BiLSTM achieved segment-based average accuracies of 97.51% and 93.70% on the CHB-MIT and SH-SDU databases, respectively.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: