Prediction of Cognitive Test Performance Using AI-Based Analysis of Narrative Speech

Chang Gung Memorial Hospital150 enrolled

Overview

This study aims to evaluate a new artificial intelligence (AI)-based method for measuring cognitive function using speech recordings. Participants will complete a short storytelling task in which they describe a story based on an image while their voice is recorded using a computer or mobile device. The speech recordings will be analyzed using AI technology to identify patterns in speech that may be related to cognitive function. The system will then estimate scores that correspond to commonly used cognitive tests. To evaluate the accuracy of this method, the AI-generated scores will be compared with results from standard cognitive assessments administered by trained researchers. These assessments may include tests commonly used to measure memory, attention, and other cognitive abilities. The goal of this study is to determine whether speech analysis using AI can provide a convenient and efficient approach for cognitive assessment. If successful, this technology may help support early detection of cognitive decline and provide a practical tool for large-scale or remote cognitive screening.

Study Type

INTERVENTIONAL

Allocation

Purpose

DIAGNOSTIC

Masking

NONE

Enrollment

150

Conditions

Cognitive Function Assessment Mild Cognitive Impairment

Interventions

AI-Based Storytelling Speech AssessmentBEHAVIORAL

Participants will be asked to describe a short story based on a randomly presented image while their speech is recorded using a web-based system on a computer or mobile device. The recorded speech will be analyzed using artificial intelligence algorithms to extract acoustic and linguistic features that may reflect cognitive function.

Eligibility

Sex: ALLMin age: 50 YearsHealthy volunteers:

Medical Language ↔ Plain English

Inclusion Criteria: 1. Age 50 years or older 2. Able to communicate verbally and understand study instructions 3. Able to hear and speak clearly 4. Willing and able to provide written informed consent Exclusion Criteria: 1. Severe speech or hearing impairment 2. History of major psychiatric disorders 3. History of stroke, traumatic brain injury, Parkinson's disease, epilepsy, or other neurodegenerative diseases 4. Current use of medications that may affect cognitive performance 5. Unable to complete the study procedures due to severe attention deficits or agitation

Outcomes

Primary Outcomes

Correlation Between AI-Predicted Cognitive Scores and Standard Cognitive Assessment Scores

The correlation between cognitive scores predicted by the AI-based speech analysis system and scores obtained from clinician-administered cognitive assessments, including the Mini-Mental State Examination (MMSE) and the Wechsler Adult Intelligence Scale (WAIS).

Time frame: Immediately after completion of the study session