Diagnostic Performance of the AlzoSure Predict Assay and Its Association With Alzheimer's Disease Biomarkers and Imaging Findings

Beyond diagnosis: can fluid tau biomarkers stage Alzheimer’s disease? Lessons from down syndrome

The introduction of blood-based biomarkers (BBMs) for Alzheimer’s disease (AD) represents one of the most transformative advances in neurodegenerative disease research over the past decade. 1,2 For the first time, biological evidence of AD pathology can be obtained through a minimally invasive, scalable blood test, opening new opportunities for early diagnosis, patient triage, and implementation of disease-modifying therapies. 3 Among the available biomarkers, phosphorylated tau (p-tau) species, particularly plasma p-tau217, have consistently shown excellent diagnostic performance across the AD continuum, recently culminating in regulatory approval of plasma p-tau217-based assays in both the USA and Europe. 4–6 Despite this remarkable clinical success, a fundamental paradox remains. Plasma tau biomarkers work

Modernizing cognitive assessment in Alzheimer’s disease

Comment on “The Diagnostic Performance of the AlzoSure Predict Assay and Its Association With Alzheimer's Disease Biomarkers and Imaging Findings”

the diagnostic performance of the AlzoSure Predict assay and its link to established

Agreement between clinical diagnosis and blood biomarkers of Alzheimer's disease in a real-world peripheral memory clinic.

BackgroundBlood-based biomarkers (BBM) are promising to help diagnose Alzheimer's disease (AD) and are on the verge of implementation in diagnostic dementia workups. However, evaluating BBM performance in peripheral memory clinics is essential to establish their real-world clinical utility.ObjectiveTo evaluate the diagnostic concordance of BBMs with clinically established diagnoses in an unselected peripheral memory clinic population using predefined, validated thresholds.MethodsIn a peripheral memory clinic, plasma levels of phosphorylated Tau217 (pTau217), amyloid-β 42/40 ratio (Aβ42/Aβ40), glial fibrillary acidic protein, and neurofilament light (NfL) were measured in patients (mean age 75.2 ± 8.8 years, 48.3% female) clinically diagnosed with subjective cognitive decline (SCD; n = 108), mild cognitive impairment (MCI; n = 55), AD dementia (n = 132), or non-AD dementia (non-AD; n = 28). BBM levels were compared across diagnostic groups and concordance between clinical diagnoses and BBM test results, based on thresholds developed in an academic memory clinic, were analyzed.ResultsThe levels of all four BBMs differed between SCD and AD dementia (p < 0.001). Between AD dementia and non-AD dementia, only PTau217 levels differed (p = 0.03). In SCD participants, 50% (pTau217) to 79% (NfL) showed abnormality in at least one BBM. In AD dementia patients, this ranged from 83% (pTau217) to 97% (NfL); all had at least one abnormal BBM, and 68% had abnormalities in all four BBMs.ConclusionsIn a peripheral real-world memory clinic setting the BBMs demonstrated high concordance with clinically diagnosed dementia due to AD. Our findings suggest utility of BBMs in peripheral memory clinic practice, in patients with suspected dementia.

Development and validation of an amyloid PET dementia of the Alzheimer's type (DAT) score.

BackgroundAlzheimer's disease (AD) can be debilitating if left untreated, but its progression may be altered through early detection.ObjectiveTo develop and evaluate a convolutional neural network (CNN) for detecting AD from amyloid PET brain images and to investigate the regions contributing to model predictions.MethodsA 3D CNN with residual connections was developed to classify amyloid PET brain volumes. Amyloid PET data were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI), with approximately 600 images from cognitively normal control (NC) and dementia of the Alzheimer's type (DAT) participants used for training, validation, and testing. Performance was assessed using repeated 5-fold cross-validation (10 total folds). The model was also evaluated across the AD continuum, including unstable normal control (uNC), progressive normal control (pNC), stable mild cognitive impairment (sMCI), progressive mild cognitive impairment (pMCI), and early DAT (eDAT). Saliency and class activation maps were generated to identify regions contributing to predictions.ResultsThe model achieved a mean testing accuracy of 92% across the 10 folds. Across the disease continuum, accuracies were 76% for uNC, 78% for sMCI, 24% for pNC, 65% for pMCI, and 78% for eDAT. Saliency and class activation maps highlighted the putamen, thalamus, hippocampus, corpus callosum, and posterior cingulate cortex, regions previously implicated in AD pathology.ConclusionsThe proposed 3D CNN accurately distinguished DAT from cognitively normal controls using amyloid PET imaging and showed promising performance across the AD continuum. Model interpretation identified biologically relevant brain regions, supporting the potential of deep learning for early AD detection and clinical decision support.

Can the integration of blood-based biomarkers into Alzheimer’s disease diagnosis revolutionize the field?

The authors critically appraise the current evidence supporting plasma phosphorylated tau at threonine 217 (p-tau217) as the leading BBM for AD, and highlight current limitations, unresolved challenges, and future perspectives for the integration of plasma biomarkers into routine clinical practice.