Skip to main content

Table 2 Classification performances on the imputed dataset indicated by the area under the receiver operator curve (AUC)

From: Deep learning based low-cost high-accuracy diagnostic framework for dementia using comprehensive neuropsychological assessment profiles

 

Proposed DNNs

XGBoost

Logistic Regression

Random Forest

Adaboost

Bagging

Support Vector Machine

MinMax

0.9489

0.9506

0.9083

0.9405

0.9149

0.9334

0.8898

kNN

0.9603

0.9541

0.9356

0.9466

0.9444

0.9559

0.9321

MI

0.9586

0.9524

0.9312

0.9211

0.9184

0.9418

0.9347

LLS

0.9594

0.9471

0.9295

0.9343

0.9109

0.9339

0.9383

  1. MinMax: minimum-maximum imputation, kNN: k nearest neighbor imputation, MI: multiple imputation, LLS: local least square imputation