Table 4.

The table shows the prediction of stroke by using AI.

SN	Citations	IC	DS	GT	FE	TOC	ML vs. DL	ACC %	AUC
1	Soun et al. [194] (2021)	LBBM (CT)	209	Stroke	NN	AlexNet	DL	96.09	0.96
2	Reva et al. [195] (2021)	OBBM, LBBM	200	Stroke, CT	NB	DT, RF, SVM	ML	85.32	NR
3	Murray et al. [9] (2020)	OBBM, LBBM	341	LVO, Stroke	RF	CNN	HDL	85.00	NR
4	Mouridsen et al. [196] (2020)	OBBM, LBBM, CUSIP	16	Stroke, MRI	NR	CNN	DL	74.00	0.74
5	Yu et al. [147] (2020)	OBBM, LBBM (EMG)	287	Stroke, EMG	SVM	RF, LSTM	ML	98.33	0.98
6	Ain et al. [197] (2020)	OBBM, LBBM	130	Stroke, non-stroke	NB	NB	ML	84.00	NR
7	Badriyah et al. [198] (2020)	OBBM (CT)	29	Stroke	NB	DT, RF, SVM	HDL	94.30	NR

SN: serial number, IC: input covariates, DS: data size, GT: Gground truth, OBBM: office-based biomarker, LBBM: laboratory based biomarkers, FE: feature extraction, TOC: type of classifier, ACC: percentage accuracy, CT: computer tomography, EMG: electromyography, MRI: magnetic resonance imagining, NR: not reported.