Table 2 Precision of the machine learning algorithms and the BDCC.

From: Implementing machine learning in bipolar diagnosis in China

 

Random forest

SVR

LASSO

LDA

Logistic regression

BDCC

AUC

Features used

AUC

Features used

AUC

Features used

AUC

Features used

AUC

Features used

AUC

Features used

MDD

0.973

74/113

0.943

56/113

0.964

50/113

0.963

54/113

0.960

34/113

0.948

17/113

BPD

0.959

91/113

0.933

56/113

0.943

105/113

0.943

99/113

0.936

34/113

0.921

17/113

HC

0.927

111/113

0.905

91/113

0.918

21/113

0.923

99/113

0.925

18/113

0.923

17/113

  1. BDCC Bipolar Diagnosis Checklist in Chinese, SVR support vector regression, LASSO least absolute shrinkage and selection operator, LDA linear discriminant analysis, AUC area under curve, MDD major depressive disorder, BPD bipolar disorder, HCs healthy controls