Short-term Automated Longitudinal Analysis of Speech and Language in Cognitive Impairment

Dementia Clinical Trial

Official title:

"Análisis Longitudinal Del Habla y Seguimiento a Corto Plazo de Las Facultades Cognitivas de Personas Mediante Una Serie de Pruebas: Lista de Palabras CERAD, Repite Los dígitos en Orden Inverso, TMTA-B, Prueba Del Reloj, Fluidez fonémica, comprensión Verbal Relaciones semánticas, y semánticas Alternas".

Clinical Trial Details — Status: Active, not recruiting

Administrative data

• NCT number: NCT05340218
• Other study ID #: 18/475-E
• Status: Active, not recruiting
• Phase: N/A
• Start date: January 1, 2019
• Est. completion date: December 31, 2022

Study information

• Verified date: March 2022
• Source: Accexible
• Contact: n/a
• Is FDA regulated: No
• Study type: Interventional

Clinical Trial Summary

Validate speech analysis AI models:

• To contrast the accuracy of acceXible's platform as a screening tool in the detection of people with cognitive impairment and mild dementia.

• To evaluate the correlation between automatically analyzed linguistic variables and a combination of standard measures of cognition.

• To assess short-term variability in language ability among older adults, and to assess which aspects of language vary during the study period.

Recruitment information / eligibility

• Status: Active, not recruiting
• Enrollment: 300
• Est. completion date: December 31, 2022
• Est. primary completion date: December 1, 2019
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: All
• Age group: 55 Years to 90 Years

Eligibility

Inclusion Criteria:

• Adult patients 55+ years of age with suspected MCI or diagnosis of dementia and obtains a score greater than 20 on the MMSE.

• Patients must have agreed to participate in the study and have voluntarily signed the informed consent.

• (Healthy) Participants without a diagnosis neurological, or psychiatric disorders. Or taking medication that can affect cognitive abilities.

Exclusion Criteria

• 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.

Related Conditions & MeSH terms

• Cognitive Dysfunction
• Dementia
• Mild Cognitive Impairment

Intervention

Other:
• Speech analysis
Speech analysis to detect and monitor mild cognitive impairment

Locations

Country	Name	City	State
Spain	Centro de Prevención de Deterioro Cognitivo	Madrid

Sponsors (1)

Lead Sponsor	Collaborator
Accexible

Country where clinical trial is conducted

Spain, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Other	Accexible's model performance.	Percentage of patients classified correctly compared to the total number of sick patients, visualized at the ROC curve that allows to see the accuracy against the recall of the classifier. To contrast the accuracy of AcceXible's platform as a screening tool in the detection of people with cognitive impairment and mild dementia, a detection model has been developed from the analysis of the participants, acoustic, linguistic and semantic variables have been considered as well as audio characteristics.	Every 6 to 9 months
Primary	Pre-post variability of normal, MCI and dementia at both points of the study.	Through standard deviation of normal subjects, MCI and dementia, variations in language are measured by considering MMSE scores and the most significant variables of accexible's tests (image description test, phonetic verbal fluency test and semantic verbal fluency test).	Change from the baseline cognitive function at 9 months.
Secondary	Correlation between cognitive tests and language variables obtained by the platform.	Correlation between: Standard measures of cognition (e.g., MMSE score) + behavioral and psychiatric symptoms of mild cognitive impairment and language.	Every 6 to 9 months