UK Validation of the Automated "AcceXible" Speech Analysis Software

Assessing the Diagnostic Accuracy of a Three One-minute Tests of Verbal Fluency, Using Artificial Intelligence, in Detecting Mild Cognitive Impairment and Early Dementia.

Dementia, especially dementia caused by Alzheimer's disease, is considered one of the most severe health problems of our time. It is currently known that the disease begins many years before clinical symptoms appear. The sooner the patient is diagnosed, the sooner the patient will be in a position to prevent further deterioration.

A recent orientation is the analysis of language in relation to the description of images with a high and varied semantic and emotional content. It can be studied that changes in the description of an image check if these changes are associated with the evolution of a person with probable impairment both in memory and cognitive as well as emotional, psychiatric, behavioral and even in their interaction with environmental factors especially those associated with socialization and loneliness.

The present study has the objective of validating a digital method for detection and follow-up of patients with mild cognitive impairment (MCI) or dementia in a memory clinic setting.

Study Overview

• Status: Completed
• Conditions: Mild Cognitive Impairment and Dementia
• Intervention / Treatment: Device: Accexible

• Study Type: Observational
• Enrollment (Actual): 221

Contacts and Locations

Study Locations

• United Kingdom
  • Cornwell, United Kingdom
    • Cornwall Partnership NHS Foundation Trust

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 55 years to 90 years (Adult, Older Adult)
• Accepts Healthy Volunteers: N/A

• Sampling Method: Probability Sample

Study Population

Sample:

Cases: 125 adult patients >55 years with suspected MCI or diagnosis of dementia referred to memory clinic.

Controls: 125 healthy adult patients >55 years without a diagnosis of MCI and without subjective cognitive complaints.

Description

Inclusion Criteria for patients:

• Adult patients 55+ years of age with suspected MCI or diagnosis of dementia referred into secondary care memory clinic by their General Practitioner.
• Have English as first language (able to speak and understand verbal messages).
• Patients must have agreed to participate in the study and have voluntarily signed the informed consent.

Inclusion Criteria for healthy volunteers:

• Healthy older adults (55+ years of age), without a diagnosis neurological, or psychiatric disorders or any clinical evidence of cognitive decline.
• Have English as first language (able to speak and understand verbal messages).
• Controls must have agreed to participate in the study and have voluntarily signed the informed consent.

Exclusion Criteria for patients:

• To have received a diagnosis of a significant psychiatric disorder or other cognitive impairment not due to neurodegeneration.
• To have significant vision problems that would affect the ability to perceive visual stimuli.
• To have significant hearing problems that would affect the ability to understand verbal cues.
• To be unable to give informed consent to participate in the study.

Exclusion Criteria for healthy volunteers:

• Objective evidence of significant cognitive decline in any one domain.
• Score of <88 on ACE-III cognitive testing.

Study Plan

How is the study designed?

Number of groups / cohorts

3

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Mild Cognitive Impairment	Device: Accexible; Speech Analysis
Healthy	Device: Accexible; Speech Analysis
Early Dementia	Device: Accexible; Speech Analysis

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic performance of Accexible's digital screening battery	Measure the odds that a patient has MCI or dementia measured by vocal biomarkers	An average of 1 year

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Correlation of Accexible's test battery with the ACE III	Comparison of Accexible's test battery with ACE III diagnostic predictive value at various cut-off points (e.g. 82 and 88 for ACE III)	An average of 1 year

Collaborators and Investigators

• Sponsor: Accexible
• Collaborators: Cornwall Partnership NHS Foundation Trust

Study record dates

Study Major Dates

• Study Start (Actual): November 18, 2022
• Primary Completion (Actual): November 12, 2024
• Study Completion (Actual): December 31, 2024

Study Registration Dates

• First Submitted: September 7, 2022
• First Submitted That Met QC Criteria: September 7, 2022
• First Posted (Actual): September 10, 2022

Study Record Updates

• Last Update Posted (Actual): April 23, 2026
• Last Update Submitted That Met QC Criteria: April 21, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Mental Disorders; Neurocognitive Disorders; Cognition Disorders; Cognitive Dysfunction; Dementia
• Other Study ID Numbers: 22/PR/0963

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No