DOCUMENT
1/1
A Word Communication System with Partner Assist for Amyotrophic Lateral Sclerosis Patients in Late Stages
preprint
posted on 2021-09-09, 18:01 authored by Kuniaki OzawaKuniaki Ozawa, Masayoshi Naito,, Naoki Tanaka, Shiryu WadaPeople with severe physical impairment such as amyotrophic lateral
sclerosis (ALS) in a completely locked-in state (CLIS) suffer from inability to express
their thoughts to others. To solve this problem, many brain-computer interface
(BCI) systems have been developed, but they have not proven sufficient for
CLIS. In this paper, we propose a word communication system: a BCI with partner
assist, in which partners play an active role in helping patients express a
word. We report here that five ALS patients in late stages (one in CLIS and
four almost in CLIS) succeeded in
expressing their own words (in Japanese) in response to wh-questions that could
not be answered “yes/no.” Each subject sequentially selected vowels (maximum
three) contained in the word that he or she wanted to express, by using a
“yes/no” communication aid based on near-infrared spectroscopy. Then, a partner
entered the selected vowels into a dictionary with vowel entries, which
returned candidate words having those vowels. When there were no appropriate
words, the partner changed one vowel and searched again or started over from
the beginning. When an appropriate word was selected, it was confirmed by the
subject via “yes/no” answers. Two subjects confirmed the selected word six
times out of eight (credibility of 91.0% by a statistical measure); two
subjects, including the one in CLIS, did so five times out of eight (74.6%);
and one subject did so three times out of four (81.3%). We have thus taken the
first step toward a practical word communication system for such patients.
Funding
This work was supported in part by the New Energy and Industrial Technology Development Organization (NEDO, fund number 28F002), which is an independent administrative institution.
History
Email Address of Submitting Author
ozawa@m.ieice.orgORCID of Submitting Author
0000-0002-0090-1154Submitting Author's Institution
Research Institute of Industrial Technology, Toyo UniversitySubmitting Author's Country
- Japan