Key result
The independently recurrent neural network (IndRNN) approach achieved an average sensitivity of 87.3% and specificity of 86.7% for seizure classification, outperforming LSTM and CNN methods.
Why the study?
Manual reviews of EEG are laborious and error prone, creating a need for automatic and accurate seizure/non-seizure classification despite considerable variability in seizure morphologies.
Does an IndRNN deep learning model improve seizure/non-seizure classification in EEG data compared to LSTM and CNN models?
Does an IndRNN deep learning model improve seizure/non-seizure classification in EEG data compared to LSTM and CNN models?
The IndRNN deep learning model outperforms standard LSTM and CNN approaches for automated seizure detection in noisy EEG data.
Advances machine learning options for seizure classification; leaves open whether gains translate to clinical benefit.
In current clinical practices, electroencephalograms (EEG) are reviewed and analyzed by trained neurologists to provide supports for therapeutic decisions. Manual reviews can be laborious and error prone. Automatic and accurate seizure/non-seizure classification methods are desirable. A critical challenge is that seizure morphologies exhibit considerable variabilities. In order to capture essential seizure features, this paper leverages an emerging deep learning model, the independently recurrent neural network (IndRNN), to construct a new approach for the seizure/non-seizure classification. This new approach gradually expands the time scales, thereby extracting temporal and spatial features from the local time duration to the entire record. Evaluations are conducted with cross-validation experiments across subjects over the noisy data of CHB-MIT. Experimental results demonstrate that the proposed approach outperforms the current state-of-the-art methods. In addition, we explore how the segment length affects the classification performance. Thirteen different segment lengths are assessed, showing that the classification performance varies over the segment lengths, and the maximal fluctuating margin is more than 4%. Thus, the segment length is an important factor influencing the classification performance.
No takes yet. Share an insight, caveat, or question.
Yao et al. (2019) studied Epilepsy (n=23). Independently Recurrent Neural Network (IndRNN) vs. LSTM and CNN approaches was evaluated on Seizure/non-seizure classification sensitivity. The independently recurrent neural network (IndRNN) approach achieved an average sensitivity of 87.3% and specificity of 86.7% for seizure classification, outperforming LSTM and CNN methods.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: