Estimating air pollution exposure has long been a challenge for environmental health researchers. Technological advances and novel machine learning methods have allowed us to increase the geographic range and accuracy of exposure models, making them a valuable tool in conducting health studies and identifying hotspots of pollution. Here, we have created a prediction model for daily PM_2.5 levels in the Greater London area from 1st January 2005 to 31st December 2013 using an ensemble machine learning approach incorporating satellite aerosol optical depth (AOD), land use, and meteorological data. The predictions were made on a 1 km × 1 km scale over 3960 grid cells. The ensemble included predictions from three different machine learners: a random forest (RF), a gradient boosting machine (GBM), and a k-nearest neighbor (KNN) approach. Our ensemble model performed very well, with a ten-fold cross-validated R² of 0.828. Of the three machine learners, the random forest outperformed the GBM and KNN. Our model was particularly adept at predicting day-to-day changes in PM_2.5 levels with an out-of-sample temporal R² of 0.882. However, its ability to predict spatial variability was weaker, with a R² of 0.396. We believe this to be due to the smaller spatial variation in pollutant levels in this area.

Background: Urban air pollution is involved in the progress of idiopathic pulmonary fibrosis (IPF). Its potential role on the devastating event of Acute Exacerbation of IPF (AE-IPF) needs to be clarified. This study examined the association between long-term personal air pollution exposure and AE- IPF risk taking into consideration inflammatory mediators and telomere length (TL). Methods: All consecutive IPF-patients referred to our Hospital from October 2013-June 2019 were included. AE-IPF events were recorded and inflammatory mediators and TL measured. Long-term personal air pollution exposures were assigned to each patient retrospectively, for O₃, NO₂, PM_2.5 [and PM₁₀, based on geo-coded residential addresses. Logistic regression models assessed the association of air pollutants’ levels with AE-IPF and inflammatory mediators adjusting for potential confounders. Results: 118 IPF patients (mean age 72 ± 8.3 years) were analyzed. We detected positive significant associations between AE-IPF and a 10 μg/m³ increase in previous-year mean level of NO₂ (OR = 1.52, 95%CI:1.15–2.0, p = 0.003), PM_2.5 (OR = 2.21, 95%CI:1.16–4.20, p = 0.016) and PM₁₀ (OR = 2.18, 95%CI:1.15–4.15, p = 0.017) independent of age, gender, smoking, lung function and antifibrotic treatment. Introduction of TL in all models of a subgroup of 36 patients did not change the direction of the observed associations. Finally, O₃ was positively associated with %change of IL-4 (p = 0.014) whilst PM_2.5, PM₁₀ and NO₂ were inversely associated with %changes of IL-4 (p = 0.003, p = 0.003, p = 0.032) and osteopontin (p = 0.013, p = 0.013, p = 0.085) respectively. Conclusions: Long-term personal exposure to increased concentrations of air pollutants is an independent risk factor of AE-IPF. Inflammatory mediators implicated in lung repair mechanisms are involved.

Land use regression (LUR) and dispersion/chemical transport models (D/CTMs) are frequently applied to predict exposure to air pollution concentrations at a fine scale for use in epidemiological studies. Moreover, the use of satellite aerosol optical depth data has been a key predictor especially for particulate matter pollution and when studying large populations. Within the STEAM project we present a hybrid spatio-temporal modeling framework by (a) incorporating predictions from dispersion modeling of nitrogen dioxide (NO₂), ozone (O₃) and particulate matter with an aerodynamic diameter equal or less than 10 μm (PM10) and less than 2.5 μm (PM2.5) into a spatio-temporal LUR model; and (b) combining the predictions LUR and dispersion modeling and additionally, only for PM2.5, from an ensemble machine learning approach using a generalized additive model (GAM). We used air pollution measurements from 2009 to 2013 from 62 fixed monitoring sites for O3, 115 for particles and up to 130 for NO₂, obtained from the dense network in the Greater London Area, UK. We assessed all models following a 10-fold cross validation (10-fold CV) procedure. The hybrid models performed better compared to separate LUR models. Incorporation of the dispersion estimates in the LUR models as a predictor, improved the LUR model fit: CV-R² increased to 0.76 from 0.71 for NO₂, to 0.79 from 0.57 for PM10, to 0.81 to 0.66 for PM2.5 and to 0.75 from 0.62 for O₃. The CV-R² obtained from the hybrid GAM framework was also increased compared to separate LUR models (CV-R² = 0.80 for NO₂, 0.76 for PM10, 0.79 for PM2.5 and 0.75 for O₃). Our study supports the combined use of different air pollution exposure assessment methods in a single modeling framework to improve the accuracy of spatio-temporal predictions for subsequent use in epidemiological studies.

Background: Although the associations of outdoor air pollution exposure with mortality and hospital admissions are well established, few previous studies have reported on primary care clinical and prescribing data. We assessed the associations of short and long-term pollutant exposures with General Practitioner respiratory consultations and inhaler prescriptions. Methods: Daily primary care data, for 2009–2013, were obtained from Lambeth DataNet (LDN), an anonymised dataset containing coded data from all patients (1.2 million) registered at general practices in Lambeth, an inner-city south London borough. Counts of respiratory consultations and inhaler prescriptions by day and Lower Super Output Area (LSOA) of residence were constructed. We developed models for predicting daily PM_2.5, PM₁₀, NO₂ and O₃ per LSOA. We used spatio-temporal mixed effects zero inflated negative binomial models to investigate the simultaneous short- and long-term effects of exposure to pollutants on the number of events. Results: The mean concentrations of NO₂, PM₁₀, PM_2.5 and O₃ over the study period were 50.7, 21.2, 15.6, and 49.9 μg/m³ respectively, with all pollutants except NO₂ having much larger temporal rather than spatial variability. Following short-term exposure increases to PM₁₀, NO₂ and PM_2.5 the number of consultations and inhaler prescriptions were found to increase, especially for PM₁₀ exposure in children which was associated with increases in daily respiratory consultations of 3.4% and inhaler prescriptions of 0.8%, per PM₁₀ interquartile range (IQR) increase. Associations further increased after adjustment for weekly average exposures, rising to 6.1 and 1.2%, respectively, for weekly average PM₁₀ exposure. In contrast, a short-term increase in O₃ exposure was associated with decreased number of respiratory consultations. No association was found between long-term exposures to PM₁₀, PM_2.5 and NO₂ and number of respiratory consultations. Long-term exposure to NO₂ was associated with an increase (8%) in preventer inhaler prescriptions only. Conclusions: We found increases in the daily number of GP respiratory consultations and inhaler prescriptions following short-term increases in exposure to NO₂, PM₁₀ and PM_2.5. These associations are more pronounced in children and persist for at least a week. The association with long term exposure to NO₂ and preventer inhaler prescriptions indicates likely increased chronic respiratory morbidity.

Background: The coronavirus disease (COVID-19) pandemic has posed an unprecedented challenge to health systems, and has significantly affected the healthcare of lung cancer patients. The aim of our study was to assess the impact of COVID-19 on early lung cancer patients’ surgical treatment. Methods: All consecutive patients with early-stage non-small cell lung cancer eligible for surgical treatment stage I/II and resectable stage III, referred to our department during the first wave of COVID-19 between February to May 2020, were included and compared with those on the exact corresponding quarter in 2019, one year before the pandemic. Waiting time to surgical treatment, increase of tumor’s size and increase on lung cancer stage were recorded and compared. All subjects were followed up for 12 months. Multiple linear and logistic regression models were applied to assess the differences in the management of the studied groups adjusting for potential confounders. Results: Sixty-one patients with early-stage lung cancer were included in the study; 28 (median age 67 years, SD: 7.1) during the pandemic and 33 (median age 67.1 years, SD: 7.5) one year earlier. A significantly longer period of waiting for treatment and an increase in tumor size were observed during the pandemic compared to before the pandemic [median time 47 days, interquartile rate (IQR): 23–100] vs. [median time 18 days, IQR: 11–23], p < 0.001. No significant differences were detected in the increase of the stage of lung cancer between the subgroups. Conclusion: The COVID-19 pandemic had a significant impact on surgical and oncological care, leading to significant delays on treatment and an increase in tumor size in early-stage lung cancer patients.