Table 1.
The performance of predicting different time stages of hypoxia and normoxia in mixed samples.
| Training data (LOOCV b) | ||||
|---|---|---|---|---|
| SVM Model a | BAC c | Accuracy d | Specificity e | Sensitivity f |
| 4 h | 50.00% | 33.33% | 33.33% | 33.33% |
| 24 h | 72.86% | 66.67% | 60% | 71.43% |
| 48 h | 83.33% | 83.33% | 83.33% | 83.33% |
| Testing data | ||||
| 4 h | 66.67% | 66.67% | 66.67% | 66.67% |
| 24 h | 66.67% | 66.67% | 33.33% | 100% |
| 48 h | 100% | 100% | 100% | 100% |
a Models were trained by linear SVM classifier, and each model was trained using two-third of all samples (n = 12). b Leave-one-out cross validation (LOOCV) was performed on training sets. c BAC denotes the average of specificity and sensitivity. d Accuracy = [(TN + TP)/(TP + FP + FN + TN)]. e Specificity = [TN/(TN + FP)]. f Sensitivity = [TP/(TP + FN)].