Maximum accuracy was observed when the full post-stimulus epoch was utilized (900 ms).
As shown in Figure 3, the maximum accuracy was achieved when the value of K was equal to 3. Thus, when K was more than 3, the accuracy decreased as K increased.
The maximum accuracy was observed for trait (T 4 and the minimum for T1, across all methods.
Maximum accuracy was achieved with five of the twelve candidate stratification biomarkers: CCL3, HSPA1B, IL8, ELA2, and LCN2.
At the same time, possible cutoffs for p were surveyed and the maximum accuracy was recorded for each of the 1, 000 subsets.
When we used 320 × 320 matrices resulting from two principal components per node, the maximum accuracy was 62.5% when 19 functional connection feathers were used.
Maximum accuracy was achieved using a threshold of at least ten cancer cells to classify tumor cores as cancer cells present, which resulted in a sensitivity of 97%, a specificity of 77% and an overall accuracy 91%.
The updated decision tree is shown in Figure 2. Maximum accuracy was achieved with three of the same stratification biomarkers (CCL3, HSPA1B, and IL8), while the importance of ELA2 and LCN2 were superseded by GZMB and MMP8.
When extracting only one eigenvariate per region, the maximum accuracy was 62.5% for the 1st eigenvariate when 25 functional connection feathers were used and 54.69% for the 2nd eigenvariate when 36 functional connection feathers were used.
Extracting the PC using the training dataset of all lines instead of using only the line itself may lead to somewhat higher accuracies, as suggested by Figures 3, 4 and 5. Results showed that for lines B2 and W1, the maximum accuracy was reached when using only the first ~40% of the PC, which accounted for 95% of the variance in the genotype data.
