A Random Forest Model for Daily PM2.5 Personal Exposure Assessment for a Chinese Cohort

Errors in air pollution exposure assessment are often considered as a major limitation in epidemiological studies. However, it is difficult to obtain accurate personal level exposure on cohort populations due to the often prohibitive expense. Personal exposure estimation models are used in lieu of direct personal exposure measures but still suffer from issues of availability and accuracy. We aim to establish a personal PM2.5 exposure assessment model for a cohort population and assess its performance by applying our model on cohort subjects. We analyzed data from representative sites selected from the subclinical outcomes of polluted air in China (SCOPA-China) cohort study and established a random forest model for estimating daily PM2.5 personal exposure. We also applied the model among subjects recruited in the project mentioned above within the same area and study period to estimate the reliability of the model. The established model showed a good fit with an R-2 of 0.81. The model application results showed similar patterns with empirically measured data. Our pilot study provided a validated and feasible modeling approach for assessing daily personal PM2.5 exposure for large cohort populations. The promising model framework can improve PM2.5 exposure assessment accuracy for future environmental health studies of large populations.