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 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 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.
See this in plain English?
AI-rewrites the medical criteria so a patient or caregiver can understand them. Always confirm with the trial site.
The primary outcome measure is 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.
Timeframe: Up to 85 years