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.

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