A user evaluation of speech/phrase recognition software in critically ill patients: a DECIDE-AI feasibility study

M. Musalia, S. Lala, L Cazalilla-Chica , J Allan, L Roach, J Twamley, S Nanda, M Verlander, A Williams, I Kempe, II Patel, F Campbell-West, B. Blackwood, D. F. McAuley

Research output: Contribution to journalArticlepeer-review


Evaluating effectiveness of speech/phrase recognition software in critically ill patients with speech impairments.

Prospective study.

Tertiary hospital critical care unit in the northwest of England.

14 patients with tracheostomies, 3 female and 11 male.

Main outcome measures
Evaluation of dynamic time warping (DTW) and deep neural networks (DNN) methods in a speech/phrase recognition application. Using speech/phrase recognition app for voice impaired (SRAVI), patients attempted mouthing various supported phrases with recordings evaluated by both DNN and DTW processing methods. Then, a trio of potential recognition phrases was displayed on the screen, ranked from first to third in order of likelihood.

A total of 616 patient recordings were taken with 516 phrase identifiable recordings. The overall results revealed a total recognition accuracy across all three ranks of 86% using the DNN method. The rank 1 recognition accuracy of the DNN method was 75%. The DTW method had a total recognition accuracy of 74%, with a rank 1 accuracy of 48%.

This feasibility evaluation of a novel speech/phrase recognition app using SRAVI demonstrated a good correlation between spoken phrases and app recognition. This suggests that speech/phrase recognition technology could be a therapeutic option to bridge the gap in communication in critically ill patients.
Original languageEnglish
Article number277
Number of pages6
JournalCritical Care
Publication statusPublished - 10 Jul 2023

Cite this