Spatially-Constrained Community Detection for Health Professional Shortage Area Delineation with Human Mobility Data
Topics: Health and Medical
, Geographic Information Science and Systems
, Spatial Analysis & Modeling
Keywords: community detection, spatial constraints, health geography
Session Type: Virtual Paper Abstract
Day: Sunday
Session Start / End Time: 2/27/2022 03:40 PM (Eastern Time (US & Canada)) - 2/27/2022 05:00 PM (Eastern Time (US & Canada))
Room: Virtual 40
Authors:
Yunlei Liang, University of Wisconsin - Madison
Wen Ye, University of Wisconsin - Madison
Song Gao, University of Wisconsin - Madison
,
,
,
,
,
,
,
Abstract
Health Professional Shortage Area (HPSA) designation identifies areas with a shortage of health care services, including primary, dental, and mental health care providers. The first step of a HPSA designation is to identify rational service areas, which are usually subdivisions of one state. Existing rational service areas are usually developed based on the local knowledge of health needs and are created through time-intensive manual work by health service officials. A data-driven and spatial-constrained community detection method based on the anonymous human mobility flow data collected from mobile phones is proposed in this research to establish the statewide rational service areas.
Based on the inter-census tract mobility flows, the graph-based Walktrap community detection method is applied to detect clusters of census tracts that are strongly connected with each other. Then, the spatial adjacency matrix of census tracts is used to enforce spatial contiguity by cutting disconnected clusters and merging small clusters with their neighbor clusters.
After delineating rational service areas, a scoring process is conducted to select HPSA based on criteria including population-to-provider ratio, poverty ratio, infant health index and travel time/distance to the nearest non-designated provider. The final HPSA score map is generated and a new python toolbox is developed for automatic scoring in ArcGIS. Finally, the resulted HPSAs are compared with existing HPSAs. Measurements include the area comparison, travel flows within-HPSAs are calculated to quantify the change between two HPSAs. Furthermore, demographic information is analyzed to discover the relationship between HPSA scores and local socio-economic characteristics.
Spatially-Constrained Community Detection for Health Professional Shortage Area Delineation with Human Mobility Data
Category
Virtual Paper Abstract
Description
This abstract is part of a session. Click here to view the session.
| Slides