Extreme weather events and emergency care: investigating and predicting patient emergency department outcomes in times of extreme weather
1
School of Public Health Sciences, University of Waterloo, Waterloo, Canada
2
Division of Clinical Sciences, Northern Ontario School of Medicine University, Thunder Bay, Canada
3
Thunder Bay Regional Health Sciences Centre, Thunder Bay, Canada
Popul. Med. 2026;8(Supplement Supplement 1):A1846
ABSTRACT
INTRODUCTION:
Climate change is increasing the number of extreme weather events (EWEs) in Canada1,2. These events place strain on emergency departments (EDs), disrupting acute care patterns3-5. Existing research focuses on forecasting ED operational metrics6,7, but the patient-level effects of EWEs across different demographic and presentation groups are much less explored. This research analyzes how EWEs, including heatwaves, wildfires, and cold spells, affect ED utilization and patient outcomes in Ontario. Specifically, we assess EWE impacts on patient-level metrics (e.g., length of stay, time to physician initial assessment), examine how these effects vary across strata, and develop machine learning (ML) models to forecast EWE impacts within strata.
METHODS:
Eleven years of daily ED data spanning 2013 to 2024 from Thunder Bay Regional Health Science Centre have been linked to provincial climate and wildfire data sources. EWE days are defined using established percentile thresholds. Generalized Linear Models are used to associate the presence of an EWE and its intensity/duration with ED outcomes across distinct demographic and clinical presentations. Time-series ML models, such as XGBoost, Random Forest, and LSTM, are used to forecast ED outcomes and identify high-risk periods for these groups.
RESULTS:
This study examines the granular effects of EWEs on distinct patient groupings in the ED. Through this, the study identifies underlying patterns regarding how EWEs affect admissions and outcomes for these groupings. These findings are then integrated into the creation of high-accuracy ML models that forecast patient outcomes during EWEs.
CONCLUSIONS:
This project provides fine-grained, actionable insights into how EWEs affect distinct patient groupings in Ontario. By detecting condition-specific vulnerabilities, identifying demographic differences, and forecasting patient outcomes, this work will empower hospital administrators, ED managers, public health planners, and provincial decision-makers to develop proactive, equitable climate change adaptation plans.
Climate change is increasing the number of extreme weather events (EWEs) in Canada1,2. These events place strain on emergency departments (EDs), disrupting acute care patterns3-5. Existing research focuses on forecasting ED operational metrics6,7, but the patient-level effects of EWEs across different demographic and presentation groups are much less explored. This research analyzes how EWEs, including heatwaves, wildfires, and cold spells, affect ED utilization and patient outcomes in Ontario. Specifically, we assess EWE impacts on patient-level metrics (e.g., length of stay, time to physician initial assessment), examine how these effects vary across strata, and develop machine learning (ML) models to forecast EWE impacts within strata.
METHODS:
Eleven years of daily ED data spanning 2013 to 2024 from Thunder Bay Regional Health Science Centre have been linked to provincial climate and wildfire data sources. EWE days are defined using established percentile thresholds. Generalized Linear Models are used to associate the presence of an EWE and its intensity/duration with ED outcomes across distinct demographic and clinical presentations. Time-series ML models, such as XGBoost, Random Forest, and LSTM, are used to forecast ED outcomes and identify high-risk periods for these groups.
RESULTS:
This study examines the granular effects of EWEs on distinct patient groupings in the ED. Through this, the study identifies underlying patterns regarding how EWEs affect admissions and outcomes for these groupings. These findings are then integrated into the creation of high-accuracy ML models that forecast patient outcomes during EWEs.
CONCLUSIONS:
This project provides fine-grained, actionable insights into how EWEs affect distinct patient groupings in Ontario. By detecting condition-specific vulnerabilities, identifying demographic differences, and forecasting patient outcomes, this work will empower hospital administrators, ED managers, public health planners, and provincial decision-makers to develop proactive, equitable climate change adaptation plans.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
