Limits...
Identifying the Uncertainty in Physician Practice Location through Spatial Analytics and Text Mining

View Article: PubMed Central - PubMed

ABSTRACT

In response to the widespread concern about the adequacy, distribution, and disparity of access to a health care workforce, the correct identification of physicians’ practice locations is critical to access public health services. In prior literature, little effort has been made to detect and resolve the uncertainty about whether the address provided by a physician in the survey is a practice address or a home address. This paper introduces how to identify the uncertainty in a physician’s practice location through spatial analytics, text mining, and visual examination. While land use and zoning code, embedded within the parcel datasets, help to differentiate resident areas from other types, spatial analytics may have certain limitations in matching and comparing physician and parcel datasets with different uncertainty issues, which may lead to unforeseen results. Handling and matching the string components between physicians’ addresses and the addresses of the parcels could identify the spatial uncertainty and instability to derive a more reasonable relationship between different datasets. Visual analytics and examination further help to clarify the undetectable patterns. This research will have a broader impact over federal and state initiatives and policies to address both insufficiency and maldistribution of a health care workforce to improve the accessibility to public health services.

No MeSH data available.


More errors in the geocoding results.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5036762&req=5

ijerph-13-00930-f005: More errors in the geocoding results.

Mentions: Such a conclusion could help to find other errors generated from the geocoding process, such as the other case displayed in Figure 5. The highlighted point location is not positioned along the road centerline, but is within a community block. By checking the addresses in the attributed table, it could be found that two different addresses are recorded in the table, which has proved to be another mistake in the geocoded result. By visually examining the nearby address location, one other error could be identified since two different addresses are labeled at the same location, although the geocoded location is along a road or in the street centerline. Through a further examination, it can be found that those two addresses (“740 FERST DR” and “1360 PIERCE DR”) are geocoded at the wrong location. “740 FERST DR” is located at the upper left corner of Figure 5, while actually “PIERCE DR” can be found in Figure 4, highlighted in the blue rectangle. As a result, a new rule can be derived as if a cluster of the geocoded location is positioned at the same x and y coordinates but the street addresses are not the same, such a cluster of physicians’ addresses may contain errors. Such a rule, however, is not valid to the parcel dataset, in which duplicated parcel polygons may have exactly the same geometric boundary or location but have different addresses. By applying such rules, it can be found that each of the 13 unique locations has multiple addresses, indicating potential geocoding errors.


Identifying the Uncertainty in Physician Practice Location through Spatial Analytics and Text Mining
More errors in the geocoding results.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5036762&req=5

ijerph-13-00930-f005: More errors in the geocoding results.
Mentions: Such a conclusion could help to find other errors generated from the geocoding process, such as the other case displayed in Figure 5. The highlighted point location is not positioned along the road centerline, but is within a community block. By checking the addresses in the attributed table, it could be found that two different addresses are recorded in the table, which has proved to be another mistake in the geocoded result. By visually examining the nearby address location, one other error could be identified since two different addresses are labeled at the same location, although the geocoded location is along a road or in the street centerline. Through a further examination, it can be found that those two addresses (“740 FERST DR” and “1360 PIERCE DR”) are geocoded at the wrong location. “740 FERST DR” is located at the upper left corner of Figure 5, while actually “PIERCE DR” can be found in Figure 4, highlighted in the blue rectangle. As a result, a new rule can be derived as if a cluster of the geocoded location is positioned at the same x and y coordinates but the street addresses are not the same, such a cluster of physicians’ addresses may contain errors. Such a rule, however, is not valid to the parcel dataset, in which duplicated parcel polygons may have exactly the same geometric boundary or location but have different addresses. By applying such rules, it can be found that each of the 13 unique locations has multiple addresses, indicating potential geocoding errors.

View Article: PubMed Central - PubMed

ABSTRACT

In response to the widespread concern about the adequacy, distribution, and disparity of access to a health care workforce, the correct identification of physicians’ practice locations is critical to access public health services. In prior literature, little effort has been made to detect and resolve the uncertainty about whether the address provided by a physician in the survey is a practice address or a home address. This paper introduces how to identify the uncertainty in a physician’s practice location through spatial analytics, text mining, and visual examination. While land use and zoning code, embedded within the parcel datasets, help to differentiate resident areas from other types, spatial analytics may have certain limitations in matching and comparing physician and parcel datasets with different uncertainty issues, which may lead to unforeseen results. Handling and matching the string components between physicians’ addresses and the addresses of the parcels could identify the spatial uncertainty and instability to derive a more reasonable relationship between different datasets. Visual analytics and examination further help to clarify the undetectable patterns. This research will have a broader impact over federal and state initiatives and policies to address both insufficiency and maldistribution of a health care workforce to improve the accessibility to public health services.

No MeSH data available.