Machine-learning-based models to predict cardiovascular risk using oculomics and clinic variables in KNHANES

Zhang, Yuqi; Li, Sijin; Wu, Weijie; Zhao, Yanqing; Han, Jintao; Tong, Chao; Luo, Niansang; Zhang, Kun

doi:10.1186/s13040-024-00363-3

BioData Mining

Table 3 The model performance of 25 algorithms on the validation set and external validation set when AIP takes two different cut-off values

From: Machine-learning-based models to predict cardiovascular risk using oculomics and clinic variables in KNHANES

	AIP=0.318						AIP=0.34
Model	Acc	AUC	F1	E-AUC	E-Acc	E-F1	Acc	AUC	F1	E-AUC	E-Acc	E-F1
GradientBoosting	0.758	0.844	0.750	0.835	0.742	0.723	0.766	0.849	0.742	0.841	0.754	0.714
LGBM	0.757	0.842	0.746	0.836	0.744	0.724	0.766	0.848	0.739	0.842	0.754	0.713
AdaBoost	0.756	0.839	0.747	0.827	0.739	0.719	0.762	0.845	0.737	0.835	0.749	0.708
RandomForest	0.750	0.832	0.742	0.826	0.736	0.720	0.756	0.838	0.732	0.831	0.745	0.709
XGBoost	0.749	0.831	0.739	0.826	0.737	0.718	0.755	0.838	0.730	0.830	0.745	0.706
MLP	0.752	0.835	0.747	0.828	0.740	0.725	0.760	0.840	0.734	0.833	0.749	0.707
RidgeCV	0.751	0.831	0.746	0.823	0.736	0.720	0.756	0.835	0.734	0.829	0.745	0.709
RidgeRegression	0.751	0.830	0.746	0.823	0.735	0.720	0.755	0.835	0.734	0.828	0.744	0.709
LogisticRegression	0.751	0.830	0.744	0.823	0.734	0.716	0.756	0.835	0.734	0.828	0.746	0.709
LinearSVM	0.751	0.831	0.743	0.823	0.737	0.717	0.758	0.835	0.734	0.829	0.746	0.706
ExtraTrees	0.742	0.824	0.737	0.817	0.732	0.719	0.751	0.831	0.729	0.824	0.740	0.708
SGD	0.746	0.829	0.749	0.820	0.730	0.726	0.750	0.832	0.728	0.824	0.737	0.703
PassiveAggressive	0.744	0.822	0.734	0.812	0.731	0.706	0.750	0.828	0.725	0.820	0.739	0.700
SVM	0.745	0.827	0.726	0.820	0.735	0.709	0.749	0.830	0.707	0.825	0.742	0.685
Perceptron	0.737	0.813	0.729	0.799	0.719	0.703	0.752	0.826	0.726	0.818	0.740	0.698
Bagging	0.731	0.804	0.713	0.796	0.720	0.694	0.739	0.811	0.708	0.802	0.731	0.686
GaussianNB	0.675	0.789	0.723	0.778	0.661	0.708	0.666	0.793	0.710	0.783	0.652	0.694
QuadraticDiscriminant	0.652	0.786	0.533	0.783	0.660	0.522	0.661	0.790	0.520	0.786	0.670	0.512
LabelPropagation	0.687	0.759	0.693	0.758	0.685	0.696	0.690	0.764	0.680	0.762	0.686	0.678
LabelSpreading	0.683	0.756	0.691	0.755	0.682	0.695	0.686	0.761	0.679	0.759	0.682	0.678
KNeighbors	0.686	0.744	0.678	0.733	0.677	0.666	0.695	0.750	0.669	0.737	0.681	0.650
DecisionTree	0.675	0.675	0.680	0.669	0.669	0.669	0.685	0.685	0.675	0.674	0.675	0.6658
BernoulliNB	0.580	0.667	0.675	0.665	0.566	0.662	0.600	0.670	0.665	0.669	0.579	0.651
ExtraTree	0.669	0.669	0.674	0.655	0.655	0.652	0.674	0.673	0.664	0.663	0.663	0.645
Dummy	0.508	0.500	0.674	0.500	0.492	0.660	0.516	0.500	0.000	0.500	0.533	0.000

Back to article page

ISSN: 1756-0381

Contact us

General enquiries: journalsubmissions@springernature.com