Affordable Access

Access to the full text

Double-Step Machine Learning Based Procedure for HFOs Detection and Classification

Authors
  • Sciaraffa, Nicolina1, 2
  • Klados, Manousos A.
  • Borghini, Gianluca1, 2, 3
  • Di Flumeri, Gianluca1, 2, 3
  • Babiloni, Fabio1, 2, 4
  • Aricò, Pietro1, 2, 3
  • 1 (P.A.)
  • 2 BrainSigns srl, Lungotevere Michelangelo, 9, 00192 Rome, Italy
  • 3 IRCCS Fondazione Santa Lucia, Neuroelectrical Imaging and BCI Lab, Via Ardeatina, 306, 00179 Rome, Italy
  • 4 College of Computer Science and Technology, Hangzhou Dianzi University, Xiasha Higher Education Zone, Hangzhou 310018, China
Type
Published Article
Journal
Brain Sciences
Publisher
MDPI AG
Publication Date
Apr 08, 2020
Volume
10
Issue
4
Identifiers
DOI: 10.3390/brainsci10040220
PMID: 32276318
PMCID: PMC7226084
Source
PubMed Central
Keywords
Disciplines
  • Article
License
Green

Abstract

The need for automatic detection and classification of high-frequency oscillations (HFOs) as biomarkers of the epileptogenic tissue is strongly felt in the clinical field. In this context, the employment of artificial intelligence methods could be the missing piece to achieve this goal. This work proposed a double-step procedure based on machine learning algorithms and tested it on an intracranial electroencephalogram (iEEG) dataset available online. The first step aimed to define the optimal length for signal segmentation, allowing for an optimal discrimination of segments with HFO relative to those without. In this case, binary classifiers have been tested on a set of energy features. The second step aimed to classify these segments into ripples, fast ripples and fast ripples occurring during ripples. Results suggest that LDA applied to 10 ms segmentation could provide the highest sensitivity (0.874) and 0.776 specificity for the discrimination of HFOs from no-HFO segments. Regarding the three-class classification, non-linear methods provided the highest values (around 90%) in terms of specificity and sensitivity, significantly different to the other three employed algorithms. Therefore, this machine-learning-based procedure could help clinicians to automatically reduce the quantity of irrelevant data.

Report this publication

Statistics

Seen <100 times