Pathological and functional HFOs can be distinguished by unsupervised clustering method 

HFOs are not alway specific to epileptogenic zone. They can be generated not only by epileptic cerebral tissue but also by non-epileptic sites often including motor cortex, visual cortex and language areas. In this project we observed that HFOs generated from epileptogenic regions tended to be similar in wave shape, and repetitively occur throughout the recording. 

We developed a pipeline of unsupervised machine learning techniques to capture recurrent stereotyped HFO waveforms in large iEEG recordings automatically, and to identify HFOs that are specifically indicative to SOZ.