Use of machine learning models to predict prognosis of combined pulmonary fibrosis and emphysema in a Chinese population

Table 2 Univariate and multivariate Cox analyses for overall mortality in CPFE

Variables	Univariable COX regression analysis		Multivariable COX regression analysis
Variables	Hazard ratio (95% CI)	P value	Hazard ratio (95% CI)	P value
Age, years	1.053 (1.031–1.076)	< 0.001	1.040 (1.017–1.063)	< 0.001
DLCO, %Predicted	0.965 (0.952–0.978)	< 0.001	0.973 (0.958–0.989)	0.001
RVD, mm	1.115 (1.074–1.158)	< 0.001	1.111 (1.064–1.161)	< 0.001
CRP, mg/L	1.009 (1.005–1.013)	< 0.001	1.005 (1.001–1.010)	0.023
Globulin, g/L	1.066 (1.038–1.094)	< 0.001	1.038 (1.005–1.072)	0.023
ALB, g/L	0.906 (0.867–0.948)	< 0.001
ILD-GAP model	1.652 (1.391–1.962)	< 0.001

CPFE combined pulmonary fibrosis and emphysema; DLCO diffusing lung capacity for carbon monoxide; RVD right ventricular diameter; CRP C-reactive protein; ALB albumin

ISSN: 1471-2466