Construction and validation of machine learning algorithm for predicting depression among home-quarantined individuals during the large-scale COVID-19 outbreak: based on Adaboost model

Table 2 Performance evaluation of each machine learning model with default parameters

model	Accuracy	AUC	Recall	Precision	F1-score	Kappa	MCC
Ada Boost Classifier	0.7894	0.7767	0.5484	0.7056	0.6049	0.4656	0.4799
Ridge Classifier	0.7895	0.0000	0.5110	0.7214	0.5891	0.4536	0.4712
CatBoost Classifier	0.7784	0.7672	0.4374	0.7160	0.5345	0.4023	0.4274
Light Gradient Boosting Machine	0.7764	0.7498	0.5352	0.6486	0.5852	0.4347	0.4390
Linear Discriminant Analysis	0.7813	0.5407	0.6580	0.6580	0.5878	0.4369	0.4445
Gradient Boosting Classifier	0.7716	0.7437	0.4956	0.6523	0.5618	0.4118	0.4196
Extra Trees Classifier	0.7627	0.7613	0.4143	0.6585	0.5048	0.3619	0.3797
Random Forest Classifier	0.7626	0.7652	0.3978	0.6753	0.4952	0.3554	0.3788
K Neighbors Classifier	0.7512	0.6783	0.3533	0.6517	0.4561	0.3138	0.3391
Extreme Gradient Boosting	0.7403	0.7378	0.4511	0.5901	0.5054	0.3350	0.3436
Naive Bayes	0.7266	0.7537	0.6297	0.5393	0.5785	0.3796	0.3833
Dummy Classifier	0.7018	0.5000	0.0000	0.0000	0.0000	0.0000	0.0000
SVM - Linear Kermel	0.6886	0.0000	0.5066	0.5422	0.4605	0.2624	0.2920
Decision Tree Classifier	0.6371	0.5849	0.4445	0.4032	0.4181	0.1582	0.1603
Quadratic Discriminant Analysis	0.5670	0.5271	0.4154	0.3138	0.3382	0.0406	0.0426

ISSN: 2050-7283