MRI and amyloid PET features classify tau positivity with AUC 0.92 in external validation

A logistic regression model using MRI and amyloid PET features classified tau positivity in amyloid-positive cohorts with AUC 0.92, accuracy 85%, sensitivity 83%, specificity 85% on external validation. MCI subjects with predicted tau positivity progressed to AD faster (p<10^-6).

• Logistic regression model achieved AUC 0.92, accuracy 85%, sensitivity 83%, specificity 85% on combined external validation (OASIS-3 and SCAN).
• Subjects with mild cognitive impairment and predicted tau positivity progressed to Alzheimer's disease significantly faster (p < 10^-6).

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.