Energy-Efficient Seizure Detection Suitable for low-power Applications
This work addresses the critical need for low-power, accurate seizure detection in medical implants for epilepsy patients, though it is incremental as it builds on existing neural network methods.
The paper tackles the problem of energy-efficient seizure detection for low-power neural implants by presenting a TC-ResNet and time-series analysis approach, achieving 95.28% accuracy, 92.34% sensitivity, and 0.9384 AUC with a 4-bit fixed point model while consuming only 495 nW on average.
Epilepsy is the most common, chronic, neurological disease worldwide and is typically accompanied by reoccurring seizures. Neuro implants can be used for effective treatment by suppressing an upcoming seizure upon detection. Due to the restricted size and limited battery lifetime of those medical devices, the employed approach also needs to be limited in size and have low energy requirements. We present an energy-efficient seizure detection approach involving a TC-ResNet and time-series analysis which is suitable for low-power edge devices. The presented approach allows for accurate seizure detection without preceding feature extraction while considering the stringent hardware requirements of neural implants. The approach is validated using the CHB-MIT Scalp EEG Database with a 32-bit floating point model and a hardware suitable 4-bit fixed point model. The presented method achieves an accuracy of 95.28%, a sensitivity of 92.34% and an AUC score of 0.9384 on this dataset with 4-bit fixed point representation. Furthermore, the power consumption of the model is measured with the low-power AI accelerator UltraTrail, which only requires 495 nW on average. Due to this low-power consumption this classification approach is suitable for real-time seizure detection on low-power wearable devices such as neural implants.