Assessment of gene classifiers
Data set | Prediction rate | Sensitivity | Specificity | P* | OR | |||||
---|---|---|---|---|---|---|---|---|---|---|
22-gene New Zealand classifier tested on German data | ||||||||||
NZ data (training; SVM) | 0.77 (0.66-0.86) | 0.53 (0.33-0.73) | 0.88 (0.77-0.95) | 0.002 | 8.4 (3.5-21.4) | |||||
NZ data minus four genes not found in German data were removed from NZ data set (training; SVM) | 0.72 | 0.38 | 0.87 | 0.011 | ||||||
German data (test; SVM) | 0.71 (0.51-0.86) | 0.62 (0.32-0.86) | 0.79 (0.52-0.95) | 0.002 | 5.9 (1.6-24.5) | |||||
19-gene German classifier tested on NZ data | ||||||||||
German data (training; 3-NN) | 0.84 (0.65-0.95) | 0.85 | 0.83 | <0.0001 | 24.1 (5.3-144.7) | |||||
German data minus five genes not found in NZ data were removed from German data set (training; 3-NN) | 0.67 | 0.65 | 0.66 | 0.046 | ||||||
NZ data (test; 3-NN) | 0.67 (0.55-0.78) | 0.42 (0.22-0.64) | 0.78 (0.65-0.89) | 0.045 | 2.6 (1.2-6.0) |
NOTE: Value in parentheses are 95% confidence interval.
Abbreviation: NZ, New Zealand.
↵* P values were calculated from 2,000 permutation of class labels.