To address the issues related to the comparison of the performance of seizure detection algorithms we have developed a framework and benchmark for the validation of EEG-based seizure detection algorithms.
We have just published it as a pre-print on Arxiv:
https://arxiv.org/abs/2402.13005
I would be very interested to have your opinion on the paper and to know if you feel these are recommendations and standards you would be implementing in your future work.
I would also like to know if you would be interested in benchmarking one of your algorithms using the described methodology and data. I could assist you if you would like to get started.
You will find additional resources to use the framework here:
Online description of the framework:
Libraries and source code:
Jonathan Dan, PhD
EPFL, Embedded Systems Laboratory