A nomogram for predicting lung-related diseases among construction workers in Wuhan, China

Abstract

Objective: To develop a prediction nomogram for the risk of lung-related diseases (LRD) in construction workers. Methods: Seven hundred and fifty-two construction workers were recruited. A self- designed questionnaire was performed to collected relevant information. Chest X-ray was taken to judge builders' lung health. The potential predictors subsets of the risk of LRD were screened by the least absolute shrinkage and selection operator regression and univariate analysis, and determined by using multivariate logistic regression analysis, then were used for developing a prediction nomogram for the risk of LRD. C-index, calibration curve, receiver operating characteristic curve, decision curve analysis (DCA) and clinical impact curve analysis (CICA) were used to evaluation the identification, calibration, predictive ability and clinical effectiveness of the nomogram. Results: Five hundred and twenty-six construction workers were allocated to training group and 226 to validation group. The predictors included in the nomogram were symptoms, years of dust exposure, work in shifts and labor intensity. Our model showed good discrimination ability, with a bootstrap-corrected C index of 0.931 (95% CI = 0.906–0.956), and had well-fitted calibration curves. The area under the curve (AUC) of the nomogram were (95% CI = 0.906–0.956) and 0.945 (95% CI = 0.891–0.999) in the training and validation groups, respectively. The results of DCA and CICA indicated that the nomogram may have clinical usefulness. Conclusion: We established and validated a novel nomogram that can provide individual prediction of LRD for construction workers. This practical prediction model may help occupational physicians in decision making and design of occupational health examination.