Back to Annual Meeting

Back to Annual Meeting

APHA Scientific Session and Event Listing

Recorded presentation

Ikuho Yamada, PhD, Department of Geography, University of Utah, 260 S. Central Campus Drive, Room 270, Salt Lake City, UT 84112, 801-585-3177, ikuho.yamada@geog.utah.edu and Karen Frederickson Comer, The Polis Center, Indiana University Purdue University Indianapolis, 1200 Waterway Boulevard, Suite 100, Indianapolis, IN 46219.

The major objective of this research is to enhance our understanding of teen pregnancy prevalence in a spatial context using data mining techniques and GIS. Teen pregnancy is considered to be one of the most serious public health concerns in local communities in the U.S. According to the National Campaign to Prevent Teen Pregnancy (www.teenpregnancy.org), the U.S. has the highest teen pregnancy rate among the fully industrialized counties in the western world. This research attempts to identify environmental factors, both physical and social, that would affect teenage girls' risk of pregnancy. The goal is to increase understanding of the risk structure and allow more targeted and effective prevention programs to be developed. Data mining techniques, in particular, decision tree induction algorithms and feed-forward neural networks, are utilized to construct exploratory models that explain teen pregnancy prevalence in relation to environmental factors. The teen pregnancy data used in this research are provided by the Marion County Health and Hospital Corporation in Indiana, while the geographic and environmental data are obtained from SAVI, one of the nation's oldest and largest GIS-based community information systems. SAVI regularly collects and makes accessible a wide variety of detailed information for the Indianapolis Metropolitan Statistical Area, including census, criminal justice, health, vital statistics, education, welfare, and community asset data. A secondary objective of this research is to assess whether and how the growing number of community information systems in the US can contribute to meaningful spatial analysis and an improved understanding of community-based health issues.

Learning Objectives:

• Recognize promising potential of GIS and data mining techniques in public health research
• Identify environmental factors that are strongly related to teen pregnancy prevalence

Keywords: Geographic Information Systems, Teen Pregnancy

Related Web page: www.savi.org/

Presenting author's disclosure statement:

Any relevant financial relationships? No

Recorded presentation