Portable Brain-Computer Interface for the Intensive Care Unit Patient Communication Using Subject-Dependent SSVEP Identification.

Omid Dehzangi,Muhamed Farooq

doi:10.1155/2018/9796238

Abstract

A major predicament for Intensive Care Unit (ICU) patients is inconsistent and ineffective communication means. Patients rated most communication sessions as difficult and unsuccessful. This, in turn, can cause distress, unrecognized pain, anxiety, and fear. As such, we designed a portable BCI system for ICU communications (BCI4ICU) optimized to operate effectively in an ICU environment. The system utilizes a wearable EEG cap coupled with an Android app designed on a mobile device that serves as visual stimuli and data processing module. Furthermore, to overcome the challenges that BCI systems face today in real-world scenarios, we propose a novel subject-specific Gaussian Mixture Model- (GMM-) based training and adaptation algorithm. First, we incorporate subject-specific information in the training phase of the SSVEP identification model using GMM-based training and adaptation. We evaluate subject-specific models against other subjects. Subsequently, from the GMM discriminative scores, we generate the transformed vectors, which are passed to our predictive model. Finally, the adapted mixture mean scores of the subject-specific GMMs are utilized to generate the high-dimensional supervectors. Our experimental results demonstrate that the proposed system achieved 98.7% average identification accuracy, which is promising in order to provide effective and consistent communication for patients in the intensive care.

Highlights

A major problem for mechanically ventilated patients in the Intensive Care Unit (ICU) is their inability to consistently and effectively communicate their most fundamental physical needs
(3) The novel Gaussian Mixture Model- (GMM-)based signal processing and SSVEP identification module: in order to fit the technical requirements of the ICU application, we propose a subject-specific Gaussian Mixture Models (GMMs)-based SSVEP identification solution
We attempted to address the needs of patients in the intensive care by developing a rapid and effective communication system that utilizes an state visual evoked potential- (SSVEP-)based Brain-Computer Interface (BCI), a wearable EEG cap, and an Android tablet to serve as the visual stimuli

Summary

Introduction

A major problem for mechanically ventilated patients in the Intensive Care Unit (ICU) is their inability to consistently and effectively communicate their most fundamental physical needs. Caregivers frequently report feeling anxious and frustrated in not being able to adequately assess the needs of their patients [4] This inability to communicate effectively can lead to the inappropriate use of sedatives and prolongation of time spent on the ventilator [5], which may lead to increased ICU length of stay and costs [3]. After performing GMM training and adaptation, the subject-specific GMMs (i.e., MAP-adapted GMMs using target subject SSVEP segments) can generate scores for the input data. We can consider the set of subject-specific GMMs as a discriminative feature space transformation In this way, the GMM likelihood scores were converted into log-likelihood ratios (LLRs) [40]. SVM identification model training Figure 9: GMM-based discriminative likelihood vector and supervector transformation

Objectives

Results

Conclusion