Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
A programmable patient-customized epileptic seizure detector is proposed in this paper to enable neurologists and patients to have constructive interactions with the implantable medical device. The programmability feature is enabled by designing a low-power 32-bit MIPS-based RISC processor which consists of five stages and supports three types of instructions. This work exhibits superiority over the existing seizure detectors since the RISC processor can be programmed by physicians to define different therapy options that are safe and efficient for each patient. Moreover, the patients have the opportunity of adjusting the seizure detection parameters by switching between different therapy options available under the permission of their physicians in order to enhance seizure detection performance. Seizure detection is performed by exploiting widely-used computational complexity-efficient time-domain features in conjunction with a feature ranking unit. The classification task is conducted by three logical functions which are defined to reach specific therapeutic goals such as rapid seizure detection and minimum false positive detections. Patients can dynamically adjust the critical seizure detection parameters such as sensitivity, specificity, and detection delay to make the medical device compatible with their current condition. The proposed programmable seizure detector is implemented on an ALTERA DE10-standard board with a Cyclone V FPGA and tested on 10 patients with 65 seizure events of the SWEC-ETHZ database from the Inselspital Bern which reveals a low dynamic power consumption of 0.78 mW which confirms its compatibility with low-power implantable devices.
Viktor Kuncak, Simon Guilloud, Mario Bucev
Simon Nessim Henein, Hubert Pierre-Marie Benoît Schneegans, Ilan Vardi, Mohamed Gamal Abdelrahman Ahmed Zanaty
,