Skip to main content

Table 4 Net reclassification improvement (NRI) in the test set

From: Comparing the performance of machine learning and conventional models for predicting atherosclerotic cardiovascular disease in a general Chinese population

Ref

PCE

China-PAR

RePCE

ReChina-PAR

ANN

0.089 *

(0.0104–0.1667)

0.355 ***

(0.249–0.462)

0.098 **

(0.033–0.162)

0.088 *

(0.017–0.158)

RF

0.005

(-0.094–0.104)

0.332 ***

(0.225–0.440)

0.036 *

(-0.07–0.138)

0.005

(-0.095 0.106)

GBM

0.003

(-0.083–0.089)

0.299 ***

(0.195–0.404)

0.093 *

(0.010–0.176)

0.042

(-0.048–0.133)

KNN

-0.150 **

(-0.259–0.041)

0.085 *

(0.008–0.162)

0.034 *

(-0.067–0.134)

-0.003

(-0.105–0.098)

Adaboost

-0.312 ***

(-0.414–0.211)

0.160 ***

(0.103–0.217)

-0.333 ***

(-0.395–0.271)

-0.327 ***

(-0.396–0.258)

SVM

-0.110

(-0.232–0.0120)

0.189 ***

(0.086–0.293)

-0.087

(-0.180–0.006)

-0.066

(-0.172–0.041)

Catboost

0.017

(-0.069–0.105)

0.264 ***

(0.159–0.369)

0.072

(-0.003–0.147)

0.072

(-0.012–0.157)

  1. Abbreviations: PCE Pooled Cohort Equations, China-PAR Prediction for ASCVD Risk in China, RePCE Recalibrated PCE, ReChina-PAR Recalibrated China-PAR, ANN Artificial Neural Network, RF Random Forest, GBM Gradient Boosting Machine, KNN K Nearest Neighbor, Adaboost Adaptive Boosting, SVM Support Vector Machine, Catboost Categorical Boosting; *P < 0.05; **P < 0.01; ***P < 0.001