this article and any supplementary material should be cited as follows: hill k, kovacs t, shin s....

This article and any supplementary material should be cited as follows: Hill K, Kovacs T, Shin S. Reliability of brain-computer interface language sample transcription procedures. J Rehabil Res Dev. 2014;51(4):579–90. http://dx.doi.org/10.1682/JRRD.2013.05.0102

Slideshow ProjectDOI:10.1682/JRRD.2013.05.0102JSP

Reliability of brain-computer interface language sample transcription

procedures

Katya Hill, PhD, CCC-SLP; Thomas Kovacs, MA; Sangeun Shin



• Aim– Test reliability of transcribing language samples of

daily brain-computer interface (BCI) communication recorded as language activity monitoring (LAM) logfiles.

• Relevance– Establishing reliable transcription procedures is

important for reporting valid measures as study results and evaluating overall effectiveness of expressive communication.



Method• Veterans with amyotrophic lateral sclerosis used

P300-based BCI as augmentative and alternative communication system.

• KeyLAM software recorded logfiles in universal logfile format during use of BCI-controlled email and word processing applications.

• These logfiles were encrypted and sent to our laboratory for decryption, transcription, and analysis.



Results• Results on transcription of 345 daily logfile

samples. • Procedure was accurate across transcribers/ raters. • Interrater reliability (frequency of agreement ratio) – Total number of words: 97.6%. – Total utterances: 93.5% .

• Interjudge agreement – 100% for both measures.



Conclusion

• Transcribing language samples using LAM data is highly reliable and fidelity of process can be maintained.

• LAM data supported transcription of large number of samples that could not have been completed using audio and video recordings.

this article and any supplementary material should be cited as follows: hill k, kovacs t, shin s....

Documents