Amyloid Prediction in Early Stage Alzheimer's Disease Through Speech Phenotyping - PAST Extension

• Conditions: Prodromal Alzheimer's Disease; Preclinical Alzheimer's Disease; Normal Cognition; Alzheimer Disease; Alzheimer's Disease (Incl Subtypes); Mild Cognitive Impairment

• Registration Number: NCT04937959
• Lead Sponsor: Novoic Limited

Brief Summary

The primary objective of the study is to evaluate whether a set of algorithms analysing acoustic and linguistic patterns of speech can detect amyloid-specific cognitive impairment in early stage Alzheimer's disease, based on archival spoken or written language samples, as measured by the area under the curve (AUC) of the receiver operating characteristic curve of the binary classifier distinguishing between amyloid positive and amyloid negative arms. Secondary objectives include (1) evaluating how many years before diagnosis of Mild Cognitive Impairment (MCI) such algorithms work, as measured on binary classifier performance of the classifiers trained to classify MCI vs cognitively normal (CN) arms using archival material from the following time bins before MCI diagnosis: 0-5 years, 5-10 years, 10-15 years, 15-20 years, 20-25 years; (2) evaluating at what age such algorithms can detect later amyloid positivity, as measured on binary classifier performance of the classifiers trained to classify amyloid positive vs amyloid negative arms using archival material from the following age bins: younger than 50, 50-55, 55-60, 65-70, 70-75 years old.

Detailed Description

Not available

Study Timeline

• Study Start: 2021-01-22
• Status Verified: 2021-06
• Study First Submitted: 2021-06-17
• Study First Submitted QC: 2021-06-23
• Study First Posted: 2021-06-24
• Last Update Submitted: 2022-04-06
• Last Update Posted: 2022-04-07
• Primary Completion: 2022-08-30
• Study Completion: 2022-08-30

Recruitment & Eligibility

• Status: UNKNOWN
• Sex: All
• Target Recruitment: 40

Inclusion Criteria

• Subjects are fully eligible for and have completed the AMYPRED-US (Amyloid Prediction in early stage Alzheimer's disease from acoustic and linguistic patterns of speech) study.

(See https://clinicaltrials.gov/ct2/show/NCT04928976)

• Subject has access to audio or written recordings created by them that are available for collection.
• Subject consents to take part in PAST extension study.

Exclusion Criteria

• Subject hasn't completed the full visit day in the AMYPRED-US study.

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
The area under the curve (AUC) of the receiver operating characteristic (ROC) curve of the binary classifier distinguishing between amyloid positive (Arms 1 and 3) and amyloid negative (Arms 2 and 4) arms.	Up to 85 years	Using archival spoken or written language samples as input.

Secondary Outcome Measures

Name	Time	Method
The sensitivity of the binary classifiers distinguishing between MCI and cognitively normal (CN) arms.	Up to 85 years	Using archival spoken or written language samples as input in the following bins: 0-5 years, 5-10 years, 10-15 years, 15-20 years, 20-25 years before MCI diagnosis.
The AUC of the binary classifier distinguishing between amyloid positive (Arms 1 and 3) and amyloid negative (Arms 2 and 4) arms.	Up to 85 years	Using archival spoken or written language samples as input in the following bins: younger than 50, 50-55, 55-60, 65-70, 70-75 years old.
The Cohen's kappa of the binary classifier distinguishing between amyloid positive (Arms 1 and 3) and amyloid negative (Arms 2 and 4) arms using archival spoken or written language samples as input.	Up to 85 years
The Cohen's kappa of the binary classifier distinguishing between amyloid positive (Arms 1 and 3) and amyloid negative (Arms 2 and 4) arms.	Up to 85 years	Using archival spoken or written language samples as input in the following bins: younger than 50, 50-55, 55-60, 65-70, 70-75 years old.
The sensitivity of the binary classifier distinguishing between amyloid positive (Arms 1 and 3) and amyloid negative (Arms 2 and 4) arms using archival spoken or written language samples as input.	Up to 85 years
The specificity of the binary classifier distinguishing between amyloid positive (Arms 1 and 3) and amyloid negative (Arms 2 and 4) arms using archival spoken or written language samples as input.	Up to 85 years
The AUC of the binary classifiers distinguishing between MCI and cognitively normal (CN) arms.	Up to 85 years	Using archival spoken or written language samples as input in the following bins: 0-5 years, 5-10 years, 10-15 years, 15-20 years, 20-25 years before MCI diagnosis.
The specificity of the binary classifiers distinguishing between MCI and cognitively normal (CN) arms.	Up to 85 years	Using archival spoken or written language samples as input in the following bins: 0-5 years, 5-10 years, 10-15 years, 15-20 years, 20-25 years before MCI diagnosis.
The Cohen's kappa of the binary classifiers distinguishing between MCI and cognitively normal (CN) arms.	Up to 85 years	Using archival spoken or written language samples as input in the following bins: 0-5 years, 5-10 years, 10-15 years, 15-20 years, 20-25 years before MCI diagnosis.
The specificity of the binary classifier distinguishing between amyloid positive (Arms 1 and 3) and amyloid negative (Arms 2 and 4) arms.	Up to 85 years	Using archival spoken or written language samples as input in the following bins: younger than 50, 50-55, 55-60, 65-70, 70-75 years old.
The sensitivity of the binary classifier distinguishing between amyloid positive (Arms 1 and 3) and amyloid negative (Arms 2 and 4) arms.	Up to 85 years	Using archival spoken or written language samples as input in the following bins: younger than 50, 50-55, 55-60, 65-70, 70-75 years old.

Trial Locations

Locations (1)

Syrentis Clinical Research; 🇺🇸 Santa Ana, California, United States