High-Frequency Oscillations in the Scalp Electroencephalogram: Mission Impossible without Computational Intelligence

Computational Intelligence and Neuroscience, 2018 · DOI: https://doi.org/10.1155/2018/1638097 · Published: August 7, 2018

Neurology

Simple Explanation

High-frequency oscillations (HFOs) in the electroencephalogram (EEG) are thought to be a promising marker for epileptogenicity. Automated detection algorithms for detection of HFOs on the scalp are highly warranted because the available algorithms were all developed for invasively recorded EEG and do not perform satisfactorily in scalp EEG because of the low signal-to-noise ratio and numerous artefacts as well as physiological activity that obscures the tiny phenomena in the high-frequency range. Visual identiﬁcation is prone to errors and extremely time-consuming, thus calling again for automation.

Study Duration

Not specified

Participants

Not specified

Evidence Level

Review Article

Key Findings

1
HFOs may be a reliable and accurate (spatial) marker that should be taken into account in presurgical evaluation of patients.
2
Scalp HFOs are less sensitive but more speciﬁc than epileptic spikes, with the highest HFO rates cooccurring with the highest IED rate.
3
HFOs originating from small patches of cortical tissue are in fact visible in the scalp EEG, provided that the signal-to-noise ratio is suﬃciently large.

Research Summary

This review discusses the challenges and potential of automated detection algorithms for high-frequency oscillations (HFOs) in scalp EEG, highlighting their importance as markers for epileptogenicity. The authors emphasize the limitations of visual detection methods and the need for algorithms tailored to scalp EEG due to its low signal-to-noise ratio and various artifacts. The review explores the role of computational intelligence, particularly machine learning, in distinguishing pathological from physiological HFOs and suggests future research directions to improve automated HFO detection for clinical use.

Practical Implications

Improved Epilepsy Diagnosis

Automated HFO detection could improve the accuracy and efficiency of epilepsy diagnosis, leading to better patient outcomes.

Enhanced Surgical Planning

More reliable HFO detection can enhance presurgical evaluation, enabling more precise resection of epileptogenic zones.

Advancements in EEG Technology

The development of tailored algorithms for HD-EEG could broaden the use of scalp HFOs as biomarkers.