Extendable Hybrid approach to detect conscious states in a CLIS patient using machine learning

Volafidy Sophie Adama, Shang-Ju Wu, Nicoletta Nicolaou, Martin Bogdan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this study a method for uncovering consciousness in complete
locked-in syndrome (CLIS) patients is proposed. The main characteristic of CLIS
patients is sufficiently intact cognition, but complete paralysis. It is, thus, vital
to develop alternative means of communicating with CLIS patients, and brain computer interfaces offer a possible platform to do so. A major issue in the study of consciousness in CLIS patients is that there is no certitude regarding their actual state of consciousness. Existing methods provide only a probability of what the states of the patients might be at each moment. This paper proposes a hybrid system based on the combination of complex coherence, sample entropy and Granger causality to uncover the underlying state of consciousness in a CLIS patient from electrocorticography signals. The contribution of each method to the system is determined using machine learning techniques. The aim of the research is to increase the probability of correctly detecting the patients’ consciousness states and, ultimately, use that to develop a reliable brain-computer interface-based communication tool.
Original languageEnglish
Title of host publication10th EUROSIM Congress on Modelling and Simulation (EUROSIM 2019)
Place of PublicationSpain
Number of pages13
Publication statusPublished - 2019

Keywords

  • Consciousness
  • Electrocorticography
  • Locked-in state
  • Coherency
  • Multiscale entropy
  • Granger causality

Fingerprint

Dive into the research topics of 'Extendable Hybrid approach to detect conscious states in a CLIS patient using machine learning'. Together they form a unique fingerprint.

Cite this