Application of machine learning with electroencephalography in seizure detection.

[摘要] INTRODUCTION: Seizures are periods of abnormal electrical activity in the brain, which induce brain injury to the sufferer. A patient that suffer seizuresmay need to be monitored for several hours, days, or even weeks. Seizure identification using electroencephalography (EEG) can be achieved throughthe use of seizure detection algorithms. Continuous EEG monitoring with early-detection algorithms to warn of the onset of seizures has many benefitsas it allows for early intervention. In this study, the desired seizure monitoring software is designed for immediate application in the clinical environment to anypatient. The aim of this research is to develop a robust, completely automatic software solution intended for real-time whole-brain seizure detection that uses EEG data, and no patient- or seizure-specific tuning. The training and testing is performed using a large, publicly available data corpus. The current state-of-the-art algorithm is improved upon. Detection should be possible assoon as a patient is rushed into the intensive care unit (ICU) and the EEG electrodes are connected properly.METHODS: The CHB-MIT data corpus is used. Included for analysis are 24 patients, 185 seizures, 979.9 hours of data, and 18 channels. Independent training and testing sets are used, with a train:test ratio of 80:20. Preprocessing:If a frame is corrupted by abnormal channel amplitude, mains noise, or phase reversal, then it is rejected without being passed to the next processes. Otherwise,the frame is bandpass filtered between 0.5 and 70 Hz, and a 5-level db2 wavelet filterbank is used for sub-band coding. Frequency bands (high), (low), ß, α,Φ, and δ are thereby approximated. The Relative Average Amplitude (RAA), Relative Scale Energy (RSE), and Coefficient of Variation of Amplitude (CVA) features of bands ß, α, and Φ are taken. Classification: A probabilistic Bayesclassifier is trained and used for classification. Ictal/inter-ictal and high-/low-α classifiers are used. A novel automatic procedure for α training-data selectionis implemented. Postprocessing: A sequential hypothesis test and persistence is used for false positive reduction. The objective function in the train-validate phase is the F1 score, which is the harmonic mean of Positive Predictive Value (PPV ) and True Positive Rate (TPR). Leave-one-out-cross-validation (LOOCV) is used in the train-validate phase. The TPR, PPV , and FalsePositive Rate (FPR) are reported for convenience.RESULTS: The offline train-validate phase yielded TPR = 58.73 %, PPV = 59.89 %, FPR = 0.2045 /h. The online test phase yielded TPR = 58.5 %, PPV = 40.61 %, FPR = 0.3536 /h.CONCLUSIONS: The algorithm presented here is an improvement to the current state-of-the-art. For clinical applicability, the issues of overall algorithm performance and inter-patient variability should be further improved.

[发布机构] Stellenbosch University