Prediction models and risk assessment for silicosis using a retrospective cohort study among workers exposed to silica in China.

ABSTRACT: This study aims to develop a prognostic risk prediction model for the development of silicosis among workers exposed to silica dust in China. The prediction model was performed by using retrospective cohort of 3,492 workers exposed to silica in an iron ore, with 33 years of follow-up. We developed a risk score system using a linear combination of the predictors weighted by the LASSO penalized Cox regression coefficients. The model's predictive accuracy was evaluated using time-dependent ROC curves. Six predictors were selected into the final prediction model (age at entry of the cohort, mean concentration of respirable silica, net years of dust exposure, smoking, illiteracy, and no. of jobs). We classified workers into three risk groups according to the quartile (Q1, Q3) of risk score; 203

SUBMITTER: Tse LA 

PROVIDER: S-EPMC4473532 | biostudies-literature | 2015 Jun

REPOSITORIES: biostudies-literature