Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content
Fig. 3 | European Journal of Medical Research

Fig. 3

From: Nomogram model using serum Club cell secretory protein 16 to predict prognosis and acute exacerbation in patients with idiopathic pulmonary fibrosis

Fig. 3

Construction of the CC16-based prognostic signature. A Univariate Cox regression analysis of CC16 expression and clinical characteristics in the training set. B LASSO regression analysis, an upper abscissa indicated how many variables in this model have non-zero coefficients, with each curve representing a change in the coefficient of each variable. C Ten-fold cross-validation for parameter selection in the LASSO model. D In the training set, patients at high-risk have shorter OS than those at low-risk, based on a Kaplan–Meier curve (P < 0.001). E Time-dependent ROC curves of 1-year and 2-year. F Based on the risk score, AUCs for 0.5- to 2.5-year ROC curves were calculated. G A nomogram for prediction of one-, two-, and three-year survival probability in the training set. H Graphs showing the calibration curves for the nomogram prediction of survival rates at 1, 2, and 3 years. I 1-year DCA curve comparison between this nomogram model and GAP index. J 2-year DCA curve comparison. K 3-year DCA curve comparison

Back to article page

European Journal of Medical Research

ISSN: 2047-783X

Contact us