Hospital-based prostate cancer screening in vietnamese men with lower urinary tract symptoms: a classification and regression tree model

Table 3 BMA prediction models using I-PSS, PSA, epidemiological, and behavioural characteristics for PCa

Model	Variable	OR (95% CI)	p	R² (%)	AUC	BIC	Posterior probability
1	IPSS	1.12 (1.06–1.18)	< 0.001	49.2	0.931	199.9	0.364
	PSA	1.06 (1.04–1.08)	< 0.001
	Intercept	0.03 (0.01–0.08)	< 0.001
2	IPSS	1.11 (1.05–1.17)	< 0.001	50.3	0.929	201.4	0.174
	PSA	1.06 (1.04–1.07)	< 0.001
	Age	1.06 (1.01–1.10)	0.047
	Intercept	0.01 (0.00–0.04)	< 0.001
3	IPSS	1.13 (1.07–1.19)	< 0.001	50.1	0.929	205.5	0.120
	PSA	1.06 (1.04–1.08)	< 0.001
	Fruits (≥ 3 times/week)	0.50 (0.23–1.06)	0.069
	Intercept	0.05 (0.02–0.12)	< 0.001
4	IPSS	1.12 (1.06–1.19)	< 0.001	49.7	0.931	203.6	0.057
	PSA	1.06 (1.04–1.08)	< 0.001
	Overweight or Obesity	1.68 (0.80–3.53)	0.174
	Intercept	0.03 (0.01–0.07)	< 0.001
5	IPSS	1.12 (1.06–1.18)	< 0.001	49.7	0.931	203.7	0.056
	PSA	1.06 (1.04–1.08)	< 0.001
	Vegetable oil (≥ 3 times/week)	1.84 (0.75–4.52)	0.186
	Intercept	0.02 (0.01–0.07)	< 0.001

ISSN: 1471-2490