A comparison between detectors of high frequency oscillations

ObjectiveHigh frequency oscillations (HFOs) are a biomarker of epileptogenicity. Visual marking of HFOs is highly time-consuming and inevitably subjective, making automatic detection necessary. We compare four existing detectors on the same dataset.MethodsHFOs and baselines were identified by experienced reviewers in intracerebral EEGs from 20 patients. A new feature of our detector to deal with channels where baseline cannot be found is presented. The original and an optimal configuration are implemented. Receiver operator curves, false discovery rate, and channel ranking are used to evaluate performance.ResultsAll detectors improve performance with the optimal configuration. Our detector had higher sensitivity, lower false positives than the others, and similar false detections. The main difference in performance was in very active channels.ConclusionsEach detector was developed for different recordings and with different aims. Our detector performed better in this dataset, but was developed on data similar to the test data. Moreover, optimizing on a particular data type improves performance in any detector.SignificanceAutomatic HFO detection is crucial to propel their clinical use as biomarkers of epileptogenic tissue. Comparing detectors on a single dataset is important to analyze their performance and to emphasize the issues involved in validation.

► The automatic detection of HFOs is crucial to propel the clinical use of HFOs as biomarkers of epileptogenic tissue.
► A comparison of existing detectors on the same dataset is presented to analyze their performance and to emphasize the issues involved in validation.
► Optimizing on a particular type of data could improve performance in any detector.