Table 1.
Feature distributions of the HCP subjects.
Fig 1.
Gender-specific age distribution of the HCP and ADNI subjects.
Table 2.
Age distribution of the ADNI subjects.
Fig 2.
Prediction results for the HCP dataset (age) for NICARA and the 1015 ROI dataset from braingraph.org.
The x-axis shows the actual age in years and the y-axis the predicted age in years during the cross-validation.
Table 3.
Prediction outcome using the correlation-based regression method for age.
Fig 3.
Prediction results for the ADNI dataset (age) for the total dataset (bottom) and the gender-specific subsets (top). The x-axis shows the actual age in years and the y-axis the predicted age in years during the cross-validation.
Table 4.
Prediction results for the ADNI dataset.
Table 5.
Prediction outcome using the correlation-based regression method for total intelligence.
Table 6.
Prediction outcome using the correlation-based regression method for crystallized intelligence.
Table 7.
Prediction outcome using the correlation-based regression method for fluid intelligence.
Fig 4.
Prediction results for the HCP dataset (total intelligence) for NICARA and the 1015 ROI dataset from braingraph.org.
The x-axis shows the actual values and the y-axis the predicted values during the cross-validation.
Fig 5.
Prediction results for the HCP dataset (fluid intelligence) for NICARA and the 1015 ROI dataset from braingraph.org.
The x-axis shows the actual values and the y-axis the predicted values during the cross-validation.
Fig 6.
Prediction results for the HCP dataset (crystallized intelligence) for NICARA and the 1015 ROI dataset from braingraph.org.
The x-axis shows the actual values and the y-axis the predicted values during the cross-validation.
Fig 7.
MAE of crystallized intelligence prediction.
Total dataset: green, Female subset: blue, Male subset: red. *: p < 0.05 without correction based on the Wilcoxon signed-rank test for paired absolute errors.
Fig 8.
MAE of fluid intelligence prediction.
Total dataset: green, Female subset: blue, Male subset: red. *: p < 0.05 without correction based on the Wilcoxon signed-rank test for paired absolute errors.
Table 8.
P-values from the comparison between crystallized and fluid intelligence.