i
Data science strategy for injury and violence prevention
-
August 2020
Details:
-
Corporate Authors:
-
Description:Injuries and violence are the leading causes of death in the United States for children, adolescents, and adults ages 18 to 44 years and rank in the top 10 causes of death for persons 45 years or older. In recent years, rates of deaths due to many forms of injury and violence—drug overdose, suicide, homicide, road traffic crashes, and falls—have increased, leading to recent declines in life expectancy in the United States. Beyond rising mortality, injuries and violence contribute to substantial morbidity as well as social and economic costs each year.
Preventing injury and violence is a public health imperative given the significant impact on individuals, families, and communities across the United States. However, primary challenges to rapidly addressing these public health problems include limitations of both public health data as well as prevention and response capabilities. Lack of timely information, inability to identify emerging health threats, limited capacity to target services, increasingly prevalent health misinformation, declining participation in and lack of representativeness of traditional data systems, and fragmentation of electronic health records and clinical data systems are examples of the challenges facing contemporary public health efforts.
A growing body of research now indicates that application of novel data and data science tools, methods, and techniques can help address critical public health needs, including injury and violence prevention and related issues such as social determinants of health and health equity. Academic research has focused, for example, on the use of novel data sources such as internet search queries to assess disease-related trends in real-time, natural language processing to study electronic health records and other systems with unstructured text, machine learning to improve prevention programming, network analysis to better understand mortality risk, online surveys to improve data timeliness and response rates, and interactive data visualization to improve communication and dissemination of scientific findings.
Although data science is an emerging field, academic, industry, and governmental organizations have typically defined it by two consistent features: 1) a multidisciplinary approach that blends methodological techniques from computer science, statistics, and various subject matter domains and 2) a focus on large, complex, or otherwise novel data sources.
For the purposes of public health and injury and violence prevention, the National Center for Injury Prevention and Control (Injury Center) defines population-health data science as a multidisciplinary approach combining traditional epidemiologic methods and contemporary computer science techniques, with a particular focus on large and complex data sources, to improve the measurement and prevention of injury and violence in communities.
Suggested Citation: Centers for Disease Control and Prevention. Data Science Strategy for Injury and Violence Prevention. Atlanta, GA: National Center for Injury Prevention and Control, Centers for Disease Control and Prevention, 2020.
Data-Science-Strategy_FINAL_508.pdf
-
Subjects:
-
Document Type:
-
Place as Subject:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type: