Table 2 Performance evaluation of prediction models.

From: Construction of disability risk prediction model for the elderly based on machine learning

 

Accuracy

Precision

Recall

F1

Haming

Jaccard

Kappa

AUC

LR

0.6640

0.6606

0.6646

0.6626

0.3360

0.4955

0.3279

0.6640

SVM

0.7467

0.7171

0.8089

0.7603

0.2533

0.6133

0.4939

0.7472

DNN

0.7134

0.6694

0.8354

0.7432

0.2866

0.5914

0.4278

0.7143

RF

0.9203

0.8889

0.9593

0.9228

0.0797

0.8566

0.8406

0.9206

Xgboost

0.8526

0.8014

0.9350

0.8630

0.1473

0.7591

0.7057

0.8533

  1. Accuracy, recall, precision, F1 score were all calculated with weighted metrics. Hamming, Jaccard, and Kappa refer to Hamming distance, Jaccard similarity coefficient, and Cohen’s kappa score.
Back to article page