Table 5.
Comparison of the prediction ability for HNHC patients between the model using single-year and consecutive 2-year data.
| c-statistics | P-valueb | ||
|---|---|---|---|
| Using single-year data | Using consecutive 2-year data | ||
| Reference modela | 0.824 (0.813–0.835) | 0.829 (0.818–0.840) | 0.56 |
| Logistic regression with Lasso regularization | 0.824 (0.813–0.835) | 0.830 (0.818–0.841) | 0.52 |
| Random forest | 0.837 (0.826–0.848) | 0.839 (0.828–0.850) | 0.80 |
| Gradient-boosted decision tree | 0.844 (0.833–0.855) | 0.845 (0.834–0.856) | 0.96 |
| Deep neural network | 0.842 (0.831–0.853) | 0.840 (0.828–0.851) | 0.81 |
aWe used a non-penalized logistic regression model as the reference model.
bWe compared the area under the curve between each machine-learning-based prediction model and the logistic regression model (the reference model) using the DeLong’s test.