Table 2.

Summary of studies that developed MLa models to detect the accuracy of health-related information.

Study	ML approach	Results	Labeling type
Elhadad et al [19]	Deep learning multimodel, GRUb, LSTMc, and CNNd	99.99% (F1 score)	Ground truth data from websites
Ghenai et al [21]	Random forest	94.5% (weighted average for F1 score)	Crowdsource agreement but keywords are based on 4 WHOe website-identified rumors
Al-Rakhami and Al-Amri [18]	Ensemble learning and random forest+SVMf	97.8% (accuracy)	Single annotator only after confirming source
Zhao et al [10]	Random forest	84.4% (F1 score)	Annotator vote; in addition, consulted an expert to validate misleading information
Sicilia et al [9]	Random forest	69.9% (F1 score)	Agreement of a health expert
Saeed et al [8]	Random forest	83.5% (accuracy)	Agreement of a health expert

^aML: machine learning.

^bGRU: gated recurrent unit.

^cLSTM: long short-term memory.

^dCNN: convolutional neural network.

^eWHO: World Health Organization.

^fSVM: support vector machine.