Table 1.
Demographic characteristics of the ADNI cohort.
Fig 1.
Heatmap of baseline CSF proteins that were significantly associated with regional MRI measures, SPARE-AD score or CSF biomarkers in AD patients and MCI subjects (n = 207).
Fig 2.
CSF proteins significantly associated with different ApoE gene polymorphisms (ε2 carriers, ε3 carriers, and ε4 carriers).
(A) CSF levels of ApoE protein between ApoE groups; (B) CSF levels of Interleukin-3 (IL-3) between ApoE groups and (C) CSF levels of Macrophage migration inhibitory factor (MIF) between ApoE groups. *These units refer to data before transformation.
Table 2.
CSF proteins significantly predicting a longitudinal decline on MMSE score in a sample of MCI subjects (n = 142).
Fig 3.
ROC curves from disease classification models for differentiating between AD and CN individuals.
Table 3.
CSF proteins selected in the CSF RFE subset using a built-in importance measure (SVM-RFE wrapper) for differentiating AD patients from CN individuals.
Table 4.
Accuracy, sensitivity, specificity and area under the curve of AD vs. CN models.
Table 5.
MCI to AD conversion prediction at a one year follow up using the AD vs. CN multivariate models.
Fig 4.
Predictive values from the combined CSF RFE subset CSF biomarker and regional MRI measures model for MCI to AD conversion prediction at several follow up timepoints.
(A) Predictive values of MCI-c progressing to AD at different follow up timepoints overlaid with predictive values of AD and CN individuals and (B) predictive values of MCI-nc at different follow up timepoints overlaid with predictive values of AD and CN individuals.