Staying Ahead of the Epidemiologic Curve

Background: The modular British Columbia Asthma Prediction System (BCAPS) is designed to reduce information burden during wildfire smoke events by automatically gathering, integrating, generating, and visualizing data for public health users. The BCAPS framework comprises five flexible and geographically scalable modules: (1) historic data on fine particulate matter (PM 2.5 ) concentrations; (2) historic data on relevant health indicator counts; (3) PM 2.5 forecasts for the upcoming days; (4) a health forecasting model that uses the relationship between (1) and (2) to predict the impacts of (3); and (5) a reporting mechanism. Methods: The 2018 wildfire season was the most extreme in British Columbia history. Every morning BCAPS generated forecasts of salbutamol sulfate (e.g., Ventolin) inhaler dispensations for the upcoming days in 16 Health Service Delivery Areas (HSDAs) using random forest machine learning. These forecasts were compared with observations over a 63-day study period using different methods including the index of agreement (IOA), which ranges from 0 (no agreement) to 1 (perfect agreement). Some observations were compared with the same period in the milder wildfire season of 2016 for context. Results: The mean province-wide population-weighted PM 2.5 concentration over the study period was 22.0 μg/m 3 , compared with 4.2 μg/m 3 during the milder wildfire season of 2016. The PM 2.5 forecasts underpredicted the severe smoke impacts, but the IOA was relatively strong with a population-weighted average of 0.85, ranging from 0.65 to 0.95 among the HSDAs. Inhaler dispensations increased by 30% over 2016 values. Forecasted dispensations were within 20% of the observed value in 71% of cases, and the IOA was strong with a population-weighted average of 0.95, ranging from 0.92 to 0.98. All measures of agreement were correlated with HSDA population, where BCAPS performance was better in the larger populations with more moderate smoke impacts. The accuracy of the health forecasts was partially dependent on the accuracy of the PM 2.5 forecasts, but they were robust to over- and underpredictions of PM 2.5 exposure. Conclusions: Daily reports from the BCAPS framework provided timely and reasonable insight into the population health impacts of predicted smoke exposures, though more work is necessary to improve the PM 2.5 and health indicator forecasts

Asthma · Environmental health · Geography · Meteorology · Air Quality and Health Impacts · Climate Change and Health Impacts · Computer Science · Demography · Fire effects on ecosystems · Medicine · Internal Medicine

• An Integrated Risk Function for Estimating the Global Burden of Disease Attributable to Ambient Fine Particulate Matter Exposure

  Open Access•Richard T Burnett, C Arden Pope et al.•Environmental Health Perspectives•2014

  Añadir item

• Wildland fire smoke and human health

  Open Access•Wayne E Cascio•The Science of The Total…•2018

  Añadir item

• A systematic review of the physical health impacts from non-occupational exposure to wildfire smoke

  Open Access•Jia C Liu, Gavin Pereira et al.•Environmental Research•2015

  Añadir item

• Critical Review of Health Impacts of Wildfire Smoke Exposure

  Open Access•Colleen E Reid, Michael Brauer et al.•Environmental Health Perspectives•2016

  Añadir item

• Random Forests

  Open Access•Leo Breiman•Machine Learning•2001

  Añadir item

• Machine Learning-Based Integration of High-Resolution Wildfire Smoke Simulations and Observations for Regional Health Impact Assessment

  Open Access•Yufei Zou, Susan O’neill et al.•International Journal of…•2019

  Añadir item

• Success and failure in narrowing the disability employment gap

  Open Access•Ben Baumberg Geiger, Kjetil A Van Der Wel et al.•BMC Public Health•2017

  Añadir item