Comparing machine learning‐derived MRI‐based and blood‐based neurodegeneration biomarkers in predicting syndromal conversion in early AD

Abstract

IntroductionWe compared the machine learning‐derived, MRI‐based Alzheimer's disease (AD) resemblance atrophy index (AD‐RAI) with plasma neurofilament light chain (NfL) level in predicting conversion of early AD among cognitively unimpaired (CU) and mild cognitive impairment (MCI) subjects.MethodsWe recruited participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had the following data: clinical features (age, gender, education, Montreal Cognitive Assessment [MoCA]), structural MRI, plasma biomarkers (p‐tau181, NfL), cerebrospinal fluid biomarkers (CSF) (Aβ42, p‐tau181), and apolipoprotein E (APOE) ε4 genotype. We defined AD using CSF Aβ42 (A+) and p‐tau181 (T+). We defined conversion (C+) if a subject progressed to the next syndromal stage within 4 years.ResultsOf 589 participants, 96 (16.3%) were A+T+C+. AD‐RAI performed better than plasma NfL when added on top of clinical features, plasma p‐tau181, and APOE ε4 genotype (area under the curve [AUC] = 0.832 vs. AUC = 0.650 among CU, AUC = 0.853 vs. AUC = 0.805 among MCI) in predicting A+T+C+.DiscussionAD‐RAI outperformed plasma NfL in predicting syndromal conversion of early AD.Highlights AD‐RAI outperformed plasma NfL in predicting syndromal conversion among early AD. AD‐RAI showed better metrics than volumetric hippocampal measures in predicting syndromal conversion. Combining clinical features, plasma p‐tau181 and apolipoprotein E (APOE) with AD‐RAI is the best model for predicting syndromal conversion.

Effect of increasing cognitive activity participation on default mode network in older adults with subjective cognitive decline: a randomised controlled trial

“…AD-RAI is superior to medial temporal lobe atrophy, hippocampal atrophy, or blood biomarkers alone in detecting early AD and predicting conversion of SCD to MCI. 25 , 26 The AD-RAI ranges from 0 to 1, with a higher value indicating more resemblance to atrophy.…”

MRI-informed machine learning-driven brain age models for classifying mild cognitive impairment converters

“…Over the last decades, MRI-based biomarkers have garnered substantial attention due to their great potential in guiding accurate diagnosis and brain-based interventions in clinical routine. 2 - 4 While the diagnostic performance of MRI biomarkers is well-studied in individuals with already present cognitive impairment, their clinical significance in identifying and predicting conversion from normal ageing adults to early-stage dementia remains controversial. 5 In the same line, given the dynamic relationships between ageing, neurodegeneration and brain morphometry may lead to further enhancements in the diagnostic, therapeutic and prognostic modelling of neurodegenerative diseases in real-world clinical practice.…”