Table 2.

The performance of different models using T1 and SWI sequence in three-classification tasks (PD vs MSA vs HC)

Sequence	Models	Average
		Sen	Spec	ACC	AUC
SWI	LR	0.762	0.882	0.764	0.869
	SVM	0.787	0.896	0.789	0.914
	LGBM	0.792	0.897	0.794	0.917
T1	LR	0.736	0.872	0.744	0.839
	SVM	0.712	0.861	0.724	0.882
	LGBM	0.723	0.864	0.729	0.887
SWI + T1	LR	0.745	0.875	0.749	0.885
	SVM	0.798	0.903	0.804	0.914
	LGBM	0.812	0.907	0.814	0.905

Sen sensitive, Spec specificity, ACC accuracy, AUC area under the curve, SWI susceptibility weighted imaging, T1 T1 weighted imaging, LR logistic regression, SVM support vector machine, LGBM light gradient boosting machine