Machine Learning Classification of Mild Cognitive Impairment using Advanced Multi-Shell Diffusion MRI and CSF Biomarkers
Guo, A. Y.; Laporte, J. P.; Singh, K.; Bae, J.; Bergeron, K.; de Rouen, A.; Fox, N. Y.; Zhang, N.; Faulkner, M. E.; Carino, I.; Benjamini, D.; Gong, Z.; Bouhrara, M.
Show abstract
INTRODUCTIONMachine learning applied to neuroimaging can help with medical diagnosis and early detection by identifying biomarkers of subtle changes in brain structure and function. The effectiveness of advanced diffusion MRI (dMRI) imaging methods for pre-dementia classification remains largely unexplored, particularly when combined with CSF biomarkers. METHODSWe implemented XGBoost machine learning models to evaluate the classification potential of dMRI parameters (derived using NODDI, C-NODDI, MAP, or SMI), CSF biomarkers of Alzheimers pathology (Tau, pTau, A{beta}42, A{beta}40), and pairwise dMRI + CSF combinations in distinguishing cognitive normality from mild cognitive impairment. RESULTSMAP-RTAP (AUC=0.78) and pTau/A{beta}42 (AUC=0.76) were the best performing individual biomarkers. Combining C-NODDI-C-NDI and A{beta}42/A{beta}40 achieved the highest performance (AUC=0.84) and accuracy (0.84), while other combinations optimized either sensitivity (0.93) or specificity (0.88). DISCUSSIONdMRI biomarkers demonstrate comparable performance to CSF biomarkers, with notable improvements achieved when combined. This study highlights dMRIs potential for enhancing early AD detection.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Comparison and aggregation of event sequences across ten cohorts to describe the consensus biomarker evolution in Alzheimer’s disease 97%
- White matter integrity is associated with cognition and amyloid burden in older adult Koreans along the Alzheimer’s disease continuum 96%
- Quantitative transport mapping of multi-delay arterial spin labeling MRI detects early blood perfusion alteration in Alzheimer’s disease 96%
Similar papers in this journal
- Topographical overlapping of the Aβ and Tau pathologies in the Default mode networks predicts Alzheimer’s Disease with higher specificity 97%
- Screening for early-stage Alzheimer's disease using optimized feature sets and machine learning 96%
- Disentangling the distal association between β-Amyloid and tau pathology at varying stages of tau deposition 96%
Similar papers in this journal
- Distinct and joint effects of low and high levels of Aβ and tau deposition on cortical thickness 96%
- Preliminary Validation of a Structural Magnetic Resonance Imaging Metric for Tracking Dementia-Related Neurodegeneration and Future Decline 96%
- Medial temporal atrophy in preclinical dementia: visual and automated assessment during six year follow-up 96%
Similar papers in this journal
- NODDI-derived measures of microstructural integrity in medial temporal lobe white matter pathways are associated with Alzheimer's disease pathology and cognitive outcomes 94%
- Sensitivity of unconstrained quantitative magnetization transfer MRI to Amyloid burden in preclinical Alzheimer’s disease 93%
- Automated quality control of T1-weighted brain MRI scans for clinical research: methods comparison and design of a quality prediction classifier 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.