Research Article
Machine Learning Application of Transcranial Motor-Evoked Potential to Predict Positive Functional Outcomes of Patients
Table 2
Prediction performance of the models with 70 : 30 training samples and test samples ratio as the ability to identify the positive outcome.
| | | | | All features | Target and reference p2p amplitude and onset latency | Target and reference p2p amplitude, onset latency, and AUC |
| | | >200% method | >50% method | Fine KNN | Weighted KNN | Ensemble Subspace KNN | Fine KNN | Weighted KNN | Ensemble Bagged Trees | Ensemble Subspace KNN | Fine KNN | Weighted KNN | Ensemble Bagged Trees | Ensemble Subspace KNN | | True positive | 25.00% | 83.33% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 91.67% | | True negative | 75.00% | 75.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | | False positive | 25.00% | 25.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | | False negative | 75.00% | 16.67% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 8.33% |
|
|
