Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0610
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-08-01T06:07:07.034349Z
status: published
lens: g_space
sector: health
headline: Classification of tau status with machine learning models in amyloid-positive cohorts
dek: Although tau positron emission tomography (PET) imaging is effective for staging tau pathology, it is limited clinically by cost and availability. Machine learning models based on magnetic resonance imaging (MRI)- and amyloid PET-derived features may serve as useful screening tools for tau pathology. Multiple machine learning models were developed to classify tau positivity in the Braak III/IV region using structural MRI, amyloid PET, and demographic features. Alzheimer's Disease Neuroimaging Initiative (ADNI) (…
gain_title: Machine learning models using structural MRI, amyloid PET, and demographic features can classify tau positivity in the Braak III/IV region in amyloid-positive cohorts, achieving AUC 0.92 and 85% accuracy on external validation.
problem_title: (none)
trace_subject: (none)
gain_reading: Machine learning models using structural MRI, amyloid PET, and demographic features can classify tau positivity in the Braak III/IV region in amyloid-positive cohorts, achieving AUC 0.92 and 85% accuracy on external validation.
gain_evidence: Logistic regression achieved the best performance with areas under the curve (AUCs) of 0.92 for both internal and external validation. | Our model demonstrates the feasibility of classifying tau burden in amyloid-positive cohorts with MRI- and amyloid PET-derived features and may serve as a surrogate biomarker. | Combined external validation yielded accuracy/sensitivity/specificity of 85%/83%/85%.
problem_reading: (none)
problem_evidence: (none)
quick_read: By August 2026, researchers had trained machine learning models on ADNI data to predict tau PET positivity from more accessible MRI and amyloid PET features, then tested them on OASIS-3 and SCAN cohorts. Logistic regression reached AUCs of 0.92 in both internal and external validation, with combined external accuracy of 85%.

The result matters because tau PET is effective but limited clinically by cost and availability, so an MRI-based surrogate could expand screening in amyloid-positive populations. It remains uncertain how the model would perform outside research cohorts, across diverse clinical settings, and whether predicted tau status would change care decisions or outcomes.
limitation: 
tag: Evidence-backed gain
key_points: Model trained on ADNI n=410 and externally validated on OASIS-3 n=143 and SCAN n=154 using MRI, amyloid PET, and demographic features. | Logistic regression was best performing model with AUC 0.92 internally and externally and 85%/83%/85% accuracy/sensitivity/specificity combined. | Subjects with mild cognitive impairment and predicted tau positivity progressed to AD at significantly faster pace with p < 10-6.
rundown: Researchers developed multiple machine learning models to classify tau positivity in the Braak III/IV region using structural MRI, amyloid PET, and demographic features, training on Alzheimer's Disease Neuroimaging Initiative data with n=410.

External validation used Open Access Series of Imaging Studies n=143 and Standardized Centralized Alzheimer's Disease Neuroimaging n=154, where logistic regression outperformed other models and predicted tau positivity was associated with faster progression from mild cognitive impairment to AD.
sources:
- peer_reviewed | Alzheimer's &amp; Dementia | https://doi.org/10.1002/alz.71683 | 2026-08-01
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

d07c1adae65ff51a83d5b4f43f24c4a0ca4641f7b41b51e4f9cb5763b751e5ed

previous

0000000000000000000000000000000000000000000000000000000000000000