Search

Due to the wealth of exposome data from longitudinal cohort studies that is currently available, the need for methods to adequately analyze these data is growing. We propose an approach in which machine learning is used to identify longitudinal exposome-related predictors of health, and illustrate its potential through an application. Our application involves studying the relation between exposome and self-perceived health based on the 30-year running Doetinchem Cohort Study. Random Forest (RF) was used to identify the strongest predictors due to its favorable prediction performance in prior research. The relation between predictors and outcome was visualized with partial dependence and accumulated local effects plots. To facilitate interpretation, exposures were summarized by expressing them as the average exposure and average trend over time. The RF model's ability to discriminate poor from good self-perceived health was acceptable (Area-Under-the-Curve = 0.707). Nine exposures from different exposome-related domains were largely responsible for the model's performance, while 87 exposures seemed to contribute little to the performance. Our approach demonstrates that ML can be interpreted more than widely believed, and can be applied to identify important longitudinal predictors of health over the life course in studies with repeated measures of exposure. The approach is context-independent and broadly applicable., (© 2022. The Author(s).)

Night shift work is associated with increased health risks. Here we examined the association of metabolic risk factors and immune cell counts, with both night shift work and particular characteristics thereof: frequency, duration and consecutive night shifts. We performed a cross-sectional study using data from 10,201 non-shift workers and 1062 night shift workers of the Lifelines Cohort study. Linear regression analyses, adjusted for demographic, lifestyle and occupational factors, were used to study associations of night shift work characteristics with metabolic risk factors and immune cell counts. Night shift workers had an increased BMI, waist circumference and immune cell counts compared to non-shift workers. This was especially seen in night shift workers who had a higher frequency of night shifts per month (≥ 5: BMI: B = 0.81 kg/m 2 (95%-CI = 0.43-1.10); waist circumference: B = 1.58 cm (95%-Cl = 0.34-1.71; leukocytes: B = 0.19 × 10 9 cells/L (95%-CI = 0.04-0.34 × 10 9 )) and worked more consecutive night shifts (> 3: BMI: B = 0.92 kg/m 2 (95%-CI = 0.41-1.43); waist circumference: B = 1.85 cm (95%-Cl = 0.45-3.24); leukocytes: B = 0.32 × 10 9 cells/L (95%-CI = 0.09-0.55 × 10 9 )). This association was less pronounced in long-term night shift workers (≥ 20 years). Our findings provide evidence for the association between night shift work characteristics and BMI, waist circumference and leukocytes (including, monocytes, lymphocytes, and basophil granulocytes)., (© 2022. The Author(s).)

The immune system potentially plays an important mechanistic role in the relation between shift work and adverse health effects. To better understand the immunological effects of shift work, we compared numbers and functionality of immune cells between night-shift and non-shift workers. Blood samples were collected from 254 night-shift and 57 non-shift workers employed in hospitals. Absolute numbers of monocytes, granulocytes, lymphocytes, and T cell subsets were assessed. As read out of immune function, monocyte cytokine production and proliferative capacity of CD4 and CD8 T cells in response to various stimuli were analysed. The mean number of monocytes was 1.15 (95%-CI = 1.05-1.26) times higher in night-shift than in non-shift workers. Furthermore, night-shift workers who worked night shifts in the past three days had a higher mean number of lymphocytes (B = 1.12 (95%-CI = 1.01-1.26)), T cells (B = 1.16 (95%-CI = 1.03-1.31)), and CD8 T cells (B = 1.23 (95%-CI = 1.05-1.45)) compared to non-shift workers. No differences in functional parameters of monocytes and lymphocytes were observed. The differences in numbers of monocytes and T cells suggest that chronic exposure to night-shift work as well as recent night-shift work may influence the immune status of healthcare workers. This knowledge could be relevant for preventive initiatives in night-shift workers, such as timing of vaccination.