Brain metabolic imaging-based model identifies cognitive stability in prodromal Alzheimer's disease.
Authors
Affiliations (6)
Affiliations (6)
- Graduate Program in Biomedical Engineering, Price Faculty of Engineering, University of Manitoba, 75 Chancellor's Circle, Winnipeg, MB, R3T 5V6, Canada.
- PrairieNeuro Research Centre, Kleysen Institute for Advanced Medicine, Health Sciences Centre, 710 William Avenue, Winnipeg, MB, R3E 3J7, Canada.
- Section of Neurology, Department of Internal Medicine, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, MB, Canada.
- Graduate Program in Biomedical Engineering, Price Faculty of Engineering, University of Manitoba, 75 Chancellor's Circle, Winnipeg, MB, R3T 5V6, Canada. [email protected].
- PrairieNeuro Research Centre, Kleysen Institute for Advanced Medicine, Health Sciences Centre, 710 William Avenue, Winnipeg, MB, R3E 3J7, Canada. [email protected].
- Department of Human Anatomy and Cell Science, Rady Faculty of Health Sciences, University of Manitoba, 130-745 Bannatyne Avenue, Winnipeg, MB, R3E 0J9, Canada. [email protected].
Abstract
The recent approval of anti-amyloid pharmaceuticals for the treatment of Alzheimer's disease (AD) has created a pressing need for the ability to accurately identify optimal candidates for anti-amyloid therapy, specifically those with evidence for incipient cognitive decline, since patients with mild cognitive impairment (MCI) may remain stable for several years even with positive AD biomarkers. Using fluorodeoxyglucose PET and biomarker data from 594 ADNI patients, a neural network ensemble was trained to forecast cognition from MCI diagnostic baseline. Training data comprised PET studies of patients with biological AD. The ensemble discriminated between progressive and stable prodromal subjects (MCI with positive amyloid and tau) at baseline with 88.6% area-under-curve, 88.6% (39/44) accuracy, 73.7% (14/19) sensitivity and 100% (25/25) specificity in the test set. It also correctly classified all other test subjects (healthy or AD continuum subjects across the cognitive spectrum) with 86.4% accuracy (206/239), 77.4% sensitivity (33/42) and 88.23% (165/197) specificity. By identifying patients with prodromal AD who will not progress to dementia, our model could significantly reduce overall societal burden and cost if implemented as a screening tool. The model's high positive predictive value in the prodromal test set makes it a practical means for selecting candidates for anti-amyloid therapy and trials.