Trial Outcomes & Findings for A Speech Recognition Application as a Communication Aid for Acute and Critical Care Patients With Tracheostomies (NCT NCT06027866)

NCT ID: NCT06027866

Last Updated: 2025-09-18

Results Overview

Recruitment status

COMPLETED

Target enrollment

31 participants

Primary outcome timeframe

From date of study enrolment until SRAVI no longer required by participant (due to return of natural voice) whilst in the study site or participant has been discharged from study site, an average of 8 weeks.

Results posted on

2025-09-18

Participant Flow

Participant milestones

Participant milestones
Measure
Tracheostomy Patients
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Overall Study
STARTED
31
Overall Study
COMPLETED
29
Overall Study
NOT COMPLETED
2

Reasons for withdrawal

Reasons for withdrawal
Measure
Tracheostomy Patients
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Overall Study
Withdrawal by Subject
2

Baseline Characteristics

Race and Ethnicity were not collected from any participant.

Baseline characteristics by cohort

Baseline characteristics by cohort
Measure
Tracheostomy Patients
n=31 Participants
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Age, Continuous
61 years
n=31 Participants
Sex: Female, Male
Female
14 Participants
n=31 Participants
Sex: Female, Male
Male
17 Participants
n=31 Participants
Primary admission diagnosis
Neurological
11 Participants
n=31 Participants
Primary admission diagnosis
Respiratory
6 Participants
n=31 Participants
Primary admission diagnosis
Gastrointestinal
5 Participants
n=31 Participants
Primary admission diagnosis
Cancer
5 Participants
n=31 Participants
Primary admission diagnosis
Infection
3 Participants
n=31 Participants
Primary admission diagnosis
Cardiac
1 Participants
n=31 Participants

PRIMARY outcome

Timeframe: From date of study enrolment until SRAVI no longer required by participant (due to return of natural voice) whilst in the study site or participant has been discharged from study site, an average of 8 weeks.

Outcome measures

Outcome measures
Measure
Tracheostomy Patients
n=31 Participants
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Number of Participants Using SRAVI at Least Once
31 Participants

PRIMARY outcome

Timeframe: From study enrolment until SRAVI no longer required by participant (due to return of natural voice) whilst in study site or participant has been discharged from study site, an average of 8 weeks.

Population: 468 videos were captured by the SRAVI app, of which 135 videos returned the correct word/phrase mouthed by the participant.

Outcome measures

Outcome measures
Measure
Tracheostomy Patients
n=468 Videos captured
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Number of Words/Phrases Correctly Identified by SRAVI App
135 Videos captured

SECONDARY outcome

Timeframe: From critical care admission to critical care discharge, censored at 8-weeks

Population: 26 of 31 participants were recruited from a critical care setting (5 participants were from an acute care setting and thus did not have a critical care LOS).

Total number of days patient spent in critical care

Outcome measures

Outcome measures
Measure
Tracheostomy Patients
n=26 Participants
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Length of Critical Care Stay
43.5 Days
Interval 34.0 to 58.0

SECONDARY outcome

Timeframe: From hospital admission to hospital discharge, censored at 3-months

Population: 31 participants were recruited into the cohort study (26 from a critical care setting and 5 from an acute care setting). 2 participants from the critical care setting withdrew from the study and did not use the SRAVI app but did consent to LOS data being included in analysis.

Total number of days patient spent in hospital

Outcome measures

Outcome measures
Measure
Tracheostomy Patients
n=31 Participants
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Duration of Hospital Length of Stay
66 Days
Interval 43.0 to 94.0

SECONDARY outcome

Timeframe: Assessed twice per shift using the validated delirium screening tool used in each unit from date of study enrolment until SRAVI no longer used or discharge from critical care. Censored at 8-weeks

Population: Of 31 participants recruited into the cohort study, 26 were from a critical care setting were delirium screening was performed (delirium screening was not performed in the acute care setting where 5 patients were recruited). Of these 26 participants, 2 withdrew from the study and thus delirium data was not collected and analysed for these 2 participants.

Did participants have delirium during their critical care stay?

Outcome measures

Outcome measures
Measure
Tracheostomy Patients
n=24 Participants
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Count of Participants With Delirium During Critical Care Stay
21 Participants

SECONDARY outcome

Timeframe: Three months following acute/critical care discharge

Population: Of 31 participants recruited to the cohort study, 22 were eligible to complete follow-up questionnaires (2 participants withdrew from the cohort study; 3 participants died and 4 participants were censored). Of the 22 eligible participants, 13 completed follow-up questionnaires and 9 were lost to follow-up.

Measured by the European Quality of Life-5 Dimensions (EQoL-5D) a generic health-related quality of life questionnaire. Respondents describe their current health state in five dimensions: mobility, ability to self-care, ability to undertake usual activities, pain and discomfort, and anxiety and depression. Each dimension has 5 levels: no problems (score of 1), slight problems (score of 2), moderate problems (score of 3), severe problems (score of 4) and extreme problems (score of 5). The digits for the five dimensions can be combined into a 5-digit number that describes the patient's health state. The questionnaire also features a visual analogue scale ranging from 'best imaginable health state' (score of 100) to 'worst imaginable health state' (score of 0).

Outcome measures

Outcome measures
Measure
Tracheostomy Patients
n=13 Participants
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Health Related Quality of Life
65 units on a scale
Interval 40.0 to 69.0

SECONDARY outcome

Timeframe: Three months following acute/critical care discharge

Population: Of 31 participants recruited to the cohort study, 22 were eligible to complete follow-up questionnaires (2 participants withdrew from the cohort study; 3 participants died and 4 participants were censored). Of the 22 eligible participants, 13 completed follow-up questionnaires and 9 were lost to follow-up.

The Hospital Anxiety and Depression Scale (HADS) is a fourteen item scale. Seven of the items relate to anxiety and seven relate to depression. The anxiety and depression subscales each range from 0 to 21, with higher scores indicating higher anxiety/depression. Patients were defined as having anxiety or depression or both if the score was 8 or more in the corresponding subscales.

Outcome measures

Outcome measures
Measure
Tracheostomy Patients
n=13 Participants
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Number of Patients Experiencing Symptoms of Anxiety and Depression
7 Participants

SECONDARY outcome

Timeframe: Three months following acute/critical care discharge

Population: Of 31 participants recruited to the cohort study, 22 were eligible to complete follow-up questionnaires (2 participants withdrew from the cohort study; 3 participants died and 4 participants were censored). Of the 22 eligible participants, 13 completed follow-up questionnaires and 9 were lost to follow-up.

The Impact of Events Scale Revised (IES-R) measures severity of Posttraumatic Stress Disorder (PTSD) symptoms. Items are rated on a 5-point scale ranging from 0 ('not at all') to 4 ('extremely'). The IES-R yields a total score (ranging from 0 to 88); higher scores mean worse symptoms.

Outcome measures

Outcome measures
Measure
Tracheostomy Patients
n=13 Participants
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Post-traumatic Stress Disorder
25 units on a scale
Interval 13.5 to 44.5

SECONDARY outcome

Timeframe: Three months following acute/critical care discharge

Population: Of 31 participants recruited to the cohort study, 22 were eligible to complete follow-up questionnaires (2 participants withdrew from the cohort study; 3 participants died and 4 participants were censored). Of the 22 eligible participants, 13 completed follow-up questionnaires and 9 were lost to follow-up.

The Montreal Cognitive Assessment-BLIND (MoCA-BLIND) is a test used to detect cognitive decline. The MoCA-BLIND test examines seven domains (executive/visuospatial function, naming, attention, language, abstraction, recall and orientation) of cognitive function with a total of 11 questions with a maximum score of 30. A score of 26 or over is considered to be normal. A score of less than 26 indicates cognitive impairment (worse outcome). Minimum score is 0.

Outcome measures

Outcome measures
Measure
Tracheostomy Patients
n=13 Participants
All consenting participants will receive access to SRAVI (Speech Recognition Application for the Voice Impaired), a communication aid for speech-impaired patients. SRAVI is a software-based mobile application ('app') and can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). SRAVI has been registered with the Medical and Healthcare products Regulatory Agency (MHRA) and CE marked for intended use. SRAVI is based on Visual Speech Recognition (VSR) technology. Specifically, the LipRead technology can determine speech by analysing the movements of a user's lips as they speak into a camera. SRAVI (Speech Recognition Application for the Voice Impaired): Speech Recognition Application for the Voice Impaired (SRAVI) is a novel communication aid developed by Liopa (a company formed by Queen's University Belfast (QUB) and the Centre for Security Information Technologies (CSIT), QUB). SRAVI is an application-based lip-reading system, and the application ('app') can be downloaded onto any device with a standard forward facing camera (e.g., smartphone, tablet). When the device is held in front of a patient, it will track lip movement and identify phrases being mouthed.
Cognitive Status
18 units on a scale
Interval 17.0 to 20.0

Adverse Events

Tracheostomy Patients

Serious events: 0 serious events
Other events: 0 other events
Deaths: 0 deaths

Serious adverse events

Adverse event data not reported

Other adverse events

Adverse event data not reported

Additional Information

Carla McClintock

Queen's University Belfast/Western Health & Social Care Trust

Phone: 07706482050

Results disclosure agreements

  • Principal investigator is a sponsor employee
  • Publication restrictions are in place