Background CDC uses the National Electronic Injury Surveillance System-All Injuries Program (NEISS-AIP) to track injury-related emergency department (ED) visits. Although data are received weekly, previously data were annually processed with 12+ month delay.
Aims Improve timeliness of NEISS-AIP and determine national estimates of injury-related ED visits in the United States before and during the COVID-19 pandemic.
Methods We used CDC’s Enterprise Data and Visualization Platform, an Azure cloud-based platform, for analysis. We integrated a Tableau server for creating a interactive data visualization dashboard. We compared injury ED visits before the COVID-19 pandemic (January 1 through December 31, 2019) to the year of the pandemic declaration (January 1 through December 31, 2020).
Results We improved timeliness of NEISS-AIP data from 12+ months to six weeks by developing a cloud-based data pipeline and significantly reduced manual processing efforts by nearly fully automating the data management process. There was an estimated 1.7 million (25%) decrease in nonfatal injury-related ED visits during April-June 2020 compared to the same time frame in 2019. Similar decreases were observed for ED visits due to motor vehicle-related injuries (199,329; 23.3%) and falls-related injuries (497,971; 25.1%). Monthly 2020 estimates remained relatively similar with 2019 estimates for self-harm-, assault-, and poisoning-related ED visits.
Conclusion The use of data science significantly improved the timeliness of data analysis. Timely access to data is crucial to monitor emerging trends to prevent future injuries.
Learning Outcomes Recognize benefits of applying data science to monitoring injury trends. Knowledge of methods to improve data timeliness.
Statistics from Altmetric.com
If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.