Machine Learning Classifies Tau Status in Amyloid-Positive Cohorts
Personalized briefing
Discovery of the day · Neurology
Classification of tau status with machine learning models in amyloid‐positive cohorts
Dear Kelly M Leyden, this is your personalized scientific intelligence briefing — curated for your work in Neurology.
Key finding
Medicine · Alzheimer’s Disease
Discovery of the day
Machine learning models based on structural MRI, amyloid PET, and demographic features were developed to classify tau positivity in the Braak III/IV region, offering a surrogate for tau PET imaging. Logistic regression achieved the best performance with AUCs of 0.92 across internal and external validation, yielding combined accuracy, sensitivity, and specificity of 85%, 83%, and 85%, respectively. These results establish a clinically actionable framework for predicting tau burden and disease progression in amyloid-positive cohorts, directly relevant to multimodal biomarker integration and the development of accessible diagnostic assays for Alzheimer’s disease.
Novelty
82%
Rigor
91%
Significance
87%
Validity
89%
Clarity
94%
Advertisement
GroupRFQ — join group deals on lab & medical equipment. Pool orders, unlock volume pricing. See open deals →
Your briefing is personalized based on your selected fields, keywords, and research interests.
