Skip to main content

Table 4 Prediction for chemoresistance in the proof-of-principle test set

From: miRNA signature associated with outcome of gastric cancer patients following chemotherapy

Sample ID Feature selection P < 0.05    Feature selection P < 0.01  
  Predictive
Index
Percentile1
Prediction
For
Pretreatment
Sample2
Overall
Prediction3
  Predictive
Index
Percentile
Prediction
for
Pretreatment
Sample
Overall
Prediction
1 pre 39% low incorrect   35% low incorrect
1 post 22%     24%   
2 pre 48% low correct   49% low correct
2 post 79%     77%   
3 pre 55% low correct   46% low correct
3 post 73%     77%   
4 pre 13% low correct   24% low correct
4 post 72%     73%   
5 pre 31% low correct   33% low correct
5 post 48%     46%   
6 pre 13% low correct   27% low correct
6 post 16%     66%   
7 pre 7% low correct   12% low correct
7 post 66%     57%   
8 pre 52% low incorrect   50% low incorrect
8 post 17%     24%   
  1. 1The predictive index was computed for each sample by this supervised principal component method, where a high value of the predictive index corresponds to a rapid progression after chemotherapy (i.e., short TTP). If the predictive index of a sample in the test set corresponded to the median predictive index of the training set, the sample was assigned a 50% predictive index.
  2. 2The risk was predicted low, if predictive index percentile of the pretreatment sample was less than 67%
  3. 3The prediction was considered correct if post-treatment samples were assigned a higher predictive index than pre-treatment samples.