Table 7.

The 11 nonlinear trimodal regression analysis parameters from AGES-I were used to predict the presence of chronic heart failure in AGES-II through machine learning algorithms and evaluation metrics were computed.

	Algor.	Acc. Mean [%]	Acc. Max [%]	Sens. [%]	Spec. [%]	Recall [%]	Precision [%]	AUCROC
CHF	GB	88.3	90.3	85.5	91.2	85.5	90.7	0.959
	RF	95.5	97.0	93.7	97.3	93.7	97.2	0.993
	ADA-B	94.3	95.8	96.2	92.3	92.3	96.0	0.986