Predicting Increased Blood Pressure Using Machine Learning

Table 4

Logistic regression results of men’s training set.

	Coefficients	S.E	Wald 𝑍	𝑃	Pseudo 𝑅^2	AUC
Model 1
Intercept	3.27	1.41	2.32	0.02	0.05	0.597
BMI	−0.09	0.05	−1.74	0.08
Model 2
Intercept	3.28	1.73	1.89	0.05	0.03	0.591
WC	−0.02	0.01	−1.42	0.15
Model 3
Intercept	7.99	3.05	2.62	0.008	0.09	0.656
HC	−0.06	0.02	−2.36	0.0183
Model 4
Intercept	0.12	3.15	0.04	0.96	0.001	0.498
WHR	0.0089	0.03	0.24	0.8120
Model 5
Intercept	28.040	17.829	1.57	0.1158	0.05	0.596
BMI	−0.1416	0.1222	−1.16	0.2463
Wc	0.0193	0.0442	0.44	0.6628
Model 6
Intercept	106.641	42.606	2.50	0.0123	0.10	0.667
BMI	0.1117	0.1202	0.93	0.3528
HC	−0.1213	0.0645	−1.88	0.0601
Model 7
Intercept	−15.975	33.454	−0.48	0.6330	0.09	0.636
BMI	−0.1641	0.0710	−2.31	0.0207
WHR	0.0797	0.0499	1.60	0.1105
Model 8
Intercept	101.735	35.689	2.85	0.0044	0.12	0.672
WC	0.0532	0.0404	1.32	0.1883
HC	−0.1339	0.0587	−2.28	0.0226
Model 9
Intercept	−49.908	38.546	−1.29	0.1954	0.13	0.677
WC	−0.1085	0.0399	−2.72	0.0065
WHR	0.1836	0.0770	2.38	0.0172
Model 10
Intercept	49.970	36.852	1.36	0.1751	0.12	0.678
HC	−0.0904	0.0339	−2.67	0.0077
WHR	0.0633	0.0451	1.40	0.1602
Model 11
Intercept	106.368	42.926	2.48	0.0132	0.12	0.671
BMI	0.0284	0.1449	0.20	0.8447
WC	0.0479	0.0485	0.99	0.3234
HC	−0.1408	0.0686	−2.05	0.0400
Model 12
Intercept	−208.656	32.535	2−0.6	4 0.521	0.13	0.680
WC	−0.2790	0.350	1−0.8	0 0.425
HC	0.1460	0.296	7 0.4	9 0.622
WHR	0.3697	0.387	9 0.9	5 0.340
Model 13
Intercept	−55.980	41.837	−1.34	0.1809	0.13	0.681
BMI	0.0537	0.1476	0.36	0.7161
WC	−0.1345	0.0820	−1.64	0.1013
WHR	0.2015	0.0916	2.20	0.0279
Model 14
Intercept	57.797	60.170	0.96	0.3368	0.12	0.679
BMI	0.0234	0.1420	0.16	0.8691
HC	−0.0999	0.0671	−1.49	0.1364
WHR	0.0586	0.0530	1.11	0.2687
Model 15
Intercept	−22.9141	32.9873	−0.69	0.4873	0.139	0.688
BMI	0.0614	0.1482	0.41	0.6787
WC	−0.3231	0.3669	−0.88	0.3785
HC	0.1582	0.2985	0.53	0.5960
WHR	0.4062	0.3993	1.02	0.3089