Research Article
Machine Learning Application of Transcranial Motor-Evoked Potential to Predict Positive Functional Outcomes of Patients
Table 3
Prediction performance of the models with 80 : 20 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 Bagged Trees | Ensemble Subspace KNN | SVM Fine Gaussian | Fine KNN | Weighted KNN | Ensemble Bagged Trees | Ensemble Subspace KNN | Fine KNN | Weighted KNN | Ensemble Bagged Trees | Ensemble Subspace KNN | | True positive | 25% | 75% | 75.00% | 100.00% | 100.00% | 87.50% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 87.50% | 100.00% | 87.50% | 87.50% | | True negative | 67% | 67% | 33.33% | 0.00% | 0.00% | 0.00% | 0.00% | 33.33% | 0.00% | 0.00% | 0.00% | 33.33% | 0.00% | 0.00% | 0.00% | | False positive | 33% | 33% | 66.67% | 100.00% | 100.00% | 100.00% | 100.00% | 66.67% | 100.00% | 100.00% | 100.00% | 66.67% | 100.00% | 100.00% | 100.00% | | False negative | 75% | 25% | 25.00% | 0.00% | 0.00% | 12.50% | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | 12.50% | 0.00% | 12.50% | 12.50% |
|
|
