Prediction model for the risk of osteoporosis incorporating factors of disease history and living habits in physical examination of population in Chongqing, Southwest China: based on artificial neural network

Table 3 The performance of four prediction models on training set and test set

Model	Data set	Accuracy	Sensitivity	Specificity	AUC (95% CI)
ANN	Training set	0.801	0.833	0.785	0.901 (0.882,0.920)
ANN	Test set	0.728	0.708	0.737	0.762 (0.714,0.810)
DBN	Training set	0.634	0.517	0.689	0.622 (0.585,0.659)
DBN	Test set	0.629	0.496	0.695	0.618 (0.561,0.675)
SVM	Training set	0.772	0.920	0.492	0.698 (0.661,0.758)
SVM	Test set	0.725	0.888	0.340	0.627 (0.588,0.625)
GA-DT	Training set	0.778	0.840	0.649	0.744 (0.710,0.779)
GA-DT	Test set	0.763	0.849	0.585	0.724 (0.689,0.760)

ISSN: 1471-2458