Related Experiment Video
Updated: Apr 12, 2026

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS
Published on: February 21, 2011
A user evaluation of speech/phrase recognition software in critically ill patients: a DECIDE-AI feasibility study
M Musalia1, S Laha2,3, J Cazalilla-Chica1
1Critical Care Unit, Lancashire Teaching Hospitals NHS Foundation Trust, Preston, UK.
Speech/phrase recognition software shows promise for critically ill patients with speech impairments. Deep neural networks achieved 75% rank 1 accuracy, offering a new communication aid.
Area of Science:
- Medical technology
- Artificial intelligence in healthcare
- Critical care medicine
Background:
- Critically ill patients often experience speech impairments, necessitating alternative communication methods like visual charts or gestures.
- Existing communication aids may not fully restore natural interaction for patients with severe speech difficulties.
Purpose of the Study:
- To evaluate the effectiveness of a novel speech/phrase recognition app in critically ill patients with speech impairments.
- To assess the performance of dynamic time warping (DTW) and deep neural networks (DNN) for recognizing mouthed phrases.
Main Methods:
- A prospective study was conducted in a tertiary hospital critical care unit.
- 14 patients with tracheostomies used a speech/phrase recognition app for voice impaired (SRAVI) to mouth phrases.
- Recordings were analyzed using DNN and DTW methods, with results ranked by likelihood.
Main Results:
- The DNN method achieved an overall recognition accuracy of 86% and a rank 1 accuracy of 75%.
- The DTW method yielded a total recognition accuracy of 74% and a rank 1 accuracy of 48%.
- 516 out of 616 (83.8%) recorded phrases were identifiable.
Conclusions:
- Speech/phrase recognition software, particularly using DNN, demonstrates feasibility and effectiveness in aiding communication for critically ill patients.
- This technology has the potential to significantly improve communication for patients with speech impairments.
- Further research and development could enhance its role as a therapeutic option in critical care settings.
Related Concept Videos
Respiratory Assessment: Purpose and Indications
Objectives and Importance:
The primary goal of respiratory assessment is to evaluate patients at early risk of clinical deterioration. Since respiratory distress often precedes other signs of declining health, breathing patterns and sounds become a...
Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
Respiratory System Abnormal Finding II: Palpation and Auscultation
Palpation Findings
During a respiratory assessment, palpation can reveal several vital abnormalities:
Acute Respiratory Failure-IV
Cardiopulmonary Resuscitation II: ACLS Airway Management
Cardiopulmonary Resuscitation V: Advanced Airway Management Techniques

