Low power real-time seizure detection for ambulatory EEG

Ambulatory Electroencephalograph (AEEG) technology is becoming popular because it facilitates the continuous monitoring of epilepsy patients without interrupting their routine life. As long term monitoring requires low power processing on the device, a low power real time seizure detection algorithm suitable for AEEG devices is proposed herein. The performance of various classifiers was tested and the most effective was found to be the Linear Discriminant Analysis classifier (LDA). The algorithm presented in this paper provides 87.7 (100–70.2)% accuracy with 94.2 (100–78)% sensitivity and 77.9 (100–52.1)% specificity in patient dependent experiments. It provides 76.5 (79.0–73.3)% accuracy with 90.9 (96.2–85.8)% sensitivity and 59.5 (70.9–52.6)% specificity in patient independent experiments. We also suggest how power can be saved at the lost of a small amount of accuracy by applying different techniques. The algorithm was simulated on a DSP processor and on an ASIC and the power estimation results for both implementations are presented. Seizure detection using the presented algorithm is approximately 100% more power efficient than other AEEG processing methods. The implementation using an ASIC can reduce power consumption by 25% relative to the implementation on a DSP processor with reduction of only 1% of accuracy.