Table 4 |
||||||
| Performance evaluation in terms of sensitivity and specificity | ||||||
| Sensitivity | Specificity | |||||
| # of terms | SVM | Logistic | Ridge | SVM | Logistic | Ridge |
| 10 | 0.6211 ± 0.020 | 0.6267 ± 0.023 | 0.6307 ± 0.020 | 0.8520 ± 0.012 | 0.8460 ± 0.012 | 0.8323 ± 0.012 |
| 20 | 0.4633 ± 0.020 | 0.4483 ± 0.020 | 0.4441 ± 0.017 | 0.9252 ± 0.006 | 0.9354 ± 0.006 | 0.9309 ± 0.006 |
| 30 | 0.3306 ± 0.025 | 0.3154 ± 0.023 | 0.3038 ± 0.019 | 0.9523 ± 0.004 | 0.9566 ± 0.004 | 0.9573 ± 0.004 |
| 40 | 0.2549 ± 0.015 | 0.2424 ± 0.014 | 0.2320 ± 0.012 | 0.9628 ± 0.003 | 0.9677 ± 0.003 | 0.9668 ± 0.003 |
| 50 | 0.2032 ± 0.012 | 0.1974 ± 0.011 | 0.1910 ± 0.012 | 0.9724 ± 0.003 | 0.9732 ± 0.003 | 0.9723 ± 0.003 |
Sparse feature is used and the classification performance on stage range 11-12 is reported. Three different classifiers are applied for comparison, namely, SVM with linear kernel (SVM), logistic regression (Logistic) and ridge regression (Ridge).
Yuan et al. BMC Bioinformatics 2012 13:107 doi:10.1186/1471-2105-13-107
