Most Experts Agree … But What About Other EEG Readers?

Noe, Katherine H.

doi:10.1177/1535759720901511

Cited by 3 publications

(2 citation statements)

References 10 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, a study by Piccinelli et al reported an IRA of 88.6% for expert agreement for classifying EEGs into three classes: EEGs with IEDs, EEGs with slow waves, and normal EEGs [329]. Another study on the IRA of IEDs in EEG reported that the median IRA between 9 experts is 80%, comparable to our current observation [330].…”

Section: Intra-rater Agreement (Ira)supporting

confidence: 89%

“…This suggests that the DLDS system can detect EEG slowing channel-and segment-wise on par with a human expert. Similarly, the EEG-level results for the three systems are comparable to human experts, as it lies within the range of the inter-rater agreement of 80% for detecting IED patterns in EEG [330]. Unfortunately, there are no similar inter-rater agreement studies for EEG slowing, which would be a more relevant benchmark for automated detection of EEG slowing.…”

Section: Summary and Future Worksupporting

confidence: 55%

See 1 more Smart Citation

Deep learning methods for diagnosis of epilepsy from electroencephalograms

Peh¹

View full text Add to dashboard Cite

Section: Intra-rater Agreement (Ira)supporting

confidence: 89%

Section: Summary and Future Worksupporting

confidence: 55%

Deep learning methods for diagnosis of epilepsy from electroencephalograms

Peh¹

View full text Add to dashboard Cite

EEG parameters as endpoints in epilepsy clinical trials - An expert panel opinion paper

Buchhalter¹,

Neuray

Cheng

et al. 2022

Epilepsy Research

View full text Add to dashboard Cite

Multi-Center Validation Study of Automated Classification of Pathological Slowing in Adult Scalp Electroencephalograms Via Frequency Features

Peh

Thomas

Bagheri

et al. 2021

Int. J. Neur. Syst.

View full text Add to dashboard Cite

Pathological slowing in the electroencephalogram (EEG) is widely investigated for the diagnosis of neurological disorders. Currently, the gold standard for slowing detection is the visual inspection of the EEG by experts, which is time-consuming and subjective. To address those issues, we propose three automated approaches to detect slowing in EEG: Threshold-based Detection System (TDS), Shallow Learning-based Detection System (SLDS), and Deep Learning-based Detection System (DLDS). These systems are evaluated on channel-, segment-, and EEG-level. The three systems perform prediction via detecting slowing at individual channels, and those detections are arranged in histograms for detection of slowing at the segment- and EEG-level. We evaluate the systems through Leave-One-Subject-Out (LOSO) cross-validation (CV) and Leave-One-Institution-Out (LOIO) CV on four datasets from the US, Singapore, and India. The DLDS achieved the best overall results: LOIO CV mean balanced accuracy (BAC) of 71.9%, 75.5%, and 82.0% at channel-, segment- and EEG-level, and LOSO CV mean BAC of 73.6%, 77.2%, and 81.8% at channel-, segment-, and EEG-level. The channel- and segment-level performance is comparable to the intra-rater agreement (IRA) of an expert of 72.4% and 82%. The DLDS can process a 30 min EEG in 4 s and can be deployed to assist clinicians in interpreting EEGs.

show abstract

Most Experts Agree … But What About Other EEG Readers?

Abstract: [Box: see text]

Cited by 3 publications

References 10 publications

Deep learning methods for diagnosis of epilepsy from electroencephalograms

Deep learning methods for diagnosis of epilepsy from electroencephalograms

EEG parameters as endpoints in epilepsy clinical trials - An expert panel opinion paper

Multi-Center Validation Study of Automated Classification of Pathological Slowing in Adult Scalp Electroencephalograms Via Frequency Features

Contact Info

Product

Resources

About