Table 1.
Discrimination accuracy, cross-validation accuracy, and predictive power of different diagnostic models, based on all 91 atlas structures.
| Method | discrimination accuracy |
cross-validation accuracy |
predictive power |
structures included |
|---|---|---|---|---|
| BNCIT | 77.1 | 77.1 | 80.0 | RH |
| Naïve Bayes | 81.9 | 69.9 | 76.7 | All |
| Decision tree | 95.1 | 57.8 | 76.7 | RH, LPG, RSN, RNA, LC, LPG, RC |
| SVM | 94.0 | 79.5 | 80.0 | All |
| MLP | 100 | 68.7 | 76.7 | All |
| discriminant analysis | 83.1 | 75.9 | 73.3 | RH, LITG, RAG, RNA |
| Logistic regression | 79.5 | 75.9 | 73.3 | RH, LITG, RAG |
RH - right hippocampus; LPG - left parahippocampal gyrus; RSN - right subthalamic nucleus; RNA - right nucleus accumbens; LC - left cuneus; LPG -left precentral gyrus; RC - right cuneus; LITG - left inferior temporal gyrus; RAG - right angular gyrus.