Table 3.
AUC comparison of various demographic variable combinations for the training dataset: in reference to convolutional neural networks using I-CNN.
| Input Variables | AUC | p Value * |
|---|---|---|
| I-CNN | 0.9075 | - |
| I-CNN + Gender | 0.9107 | 0.657 |
| I-CNN + Age | 0.9111 | 0.602 |
| I-CNN + Weight | 0.9122 | 0.468 |
| I-CNN + Height | 0.9091 | 0.802 |
| I-CNN + Weight + Age | 0.9212 | 0.039 |
| I-CNN + Weight + Age + Gender | 0.9207 | 0.023 |
| I-CNN + Weight + Age + Gender + Height | 0.9213 | 0.049 |
* p value was calculated for the difference between the AUC based on I-CNN.