Back

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.

2025-02-28 radiology and imaging
10.1101/2025.02.27.25322792 medRxiv
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.

50% of probability mass above

"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.