Semi-supervised training data selection improves seizure forecasting in canines with epilepsy

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F20%3A00346819" target="_blank" >RIV/68407700:21730/20:00346819 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1016/j.bspc.2019.101743" target="_blank" >https://doi.org/10.1016/j.bspc.2019.101743</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.bspc.2019.101743" target="_blank" >10.1016/j.bspc.2019.101743</a>

Result language

angličtina

Original language name

Semi-supervised training data selection improves seizure forecasting in canines with epilepsy

Original language description

Objective: Conventional selection of pre-ictal EEG epochs for seizure prediction algorithm training datatypically assumes a continuous pre-ictal brain state preceding a seizure. This is carried out by defin-ing a fixed duration, pre-ictal time period before seizures from which pre-ictal training data epochs areuniformly sampled. However, stochastic physiological and pathological fluctuations in EEG data char-acteristics and underlying brain states suggest that pre-ictal state dynamics may be more complex, andselection of pre-ictal training data segments to reflect this could improve algorithm performance.Methods: We propose a semi-supervised technique to select pre-ictal training data most distinguishablefrom interictal EEG according to pre-specified data characteristics. The proposed method uses hierarchicalclustering to identify optimal pre-ictal data epochs.Results: In this paper we compare the performance of a seizure forecasting algorithm with and withouthierarchical clustering of pre-ictal periods in chronic iEEG recordings from six canines with naturallyoccurring epilepsy. Hierarchical clustering of training data improved results for Time In Warning (TIW)(0.18 vs. 0.23) and False Positive Rate (FPR) (0.5 vs. 0.59) when evaluated across all subjects (p < 0.001,n = 6). Results were mixed when evaluating TIW, FPR, and Sensitivity for individual dogs.Conclusion: Hierarchical clustering is a helpful method for training data selection overall, but should beevaluated on a subject-wise basis.Significance: The clustering method can be used to optimize results of forecasting towards sensitivity orTIW or FPR, and therefore can be useful for epilepsy management.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2020

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Biomedical Signal Processing and Control

ISSN

1746-8094

e-ISSN

1746-8108

Volume of the periodical

57

Issue of the periodical within the volume

March

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

7

Pages from-to

—

UT code for WoS article

000512481800017

EID of the result in the Scopus database

2-s2.0-85074854563