Accexible Speech Analysis for MCI Detection and Monitoring in Colombia

Assessment of Sensitivity and Specificity of a Machine Learning System for Detection and Monitoring of Mild Cognitive Impairment (Accexible) Through Speech Analysis in a Colombian Population

Mild Cognitive Impairment (MCI) is frequently underdiagnosed due to its subtle clinical presentation. This study evaluates the diagnostic performance of AcceXible, a speech analysis-based machine learning platform, compared to the Montreal Cognitive Assessment (MoCA) for MCI detection and monitoring in Colombian patients.

A diagnostic test accuracy study will be conducted within a primary care setting (EPS Sanitas), including prior validation of the AcceXible protocol in the Colombian healthcare context.

The study pursues two primary aims: (1) to validate the AcceXible tool in a Colombian population, and (2) to demonstrate that AcceXible achieves high diagnostic accuracy for early MCI detection and longitudinal monitoring relative to the MoCA.

Study Overview

• Status: Completed
• Conditions: MCI
• Intervention / Treatment: Device: Accexible

• Study Type: Observational
• Enrollment (Actual): 114

Contacts and Locations

Study Locations

• Colombia
  • Bogotá, Colombia, 110911
    • Fundación Universitaria Sanitas

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

Adults aged >60 years attending in-person primary care consultations within the EPS Sanitas network (Bogotá, Colombia).

Description

Inclusion Criteria:

• Ability to independently operate a mobile or portable device with internet connectivity and integrated microphone
• Provision of voluntary written informed consent prior to study participation

Exclusion Criteria:

• Diagnosed psychiatric disorder or cognitive impairment not attributable to neurodegenerative etiology
• Visual impairment sufficient to preclude reading on-screen text or perceiving visual stimuli
• Illiteracy
• Hearing impairment sufficient to preclude comprehension of verbal instructions or detection of auditory test-onset cues

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy of acceXible compared to MoCA for MCI detection	Sensitivity and specificity of the acceXible speech-based platform relative to the MoCA (reference standard; cutoff <30 = abnormal) for detecting MCI in adults aged ≥55 years. Additional metrics: area under the ROC curve (AUC), positive and negative predictive values (PPV, NPV), and likelihood ratios.	Baseline

Collaborators and Investigators

• Sponsor: Accexible
• Collaborators: Fundación Universitaria Sanitas (UNISANITAS)

Study record dates

Study Major Dates

• Study Start (Actual): May 22, 2022
• Primary Completion (Actual): June 17, 2024
• Study Completion (Actual): June 17, 2024

Study Registration Dates

• First Submitted: April 21, 2026
• First Submitted That Met QC Criteria: April 21, 2026
• First Posted (Actual): April 27, 2026

Study Record Updates

• Last Update Posted (Actual): May 8, 2026
• Last Update Submitted That Met QC Criteria: May 5, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Keywords: machine learning; MCI; screening
• Other Study ID Numbers: 023-22-UNV

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

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