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.


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

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

ijerph-13-00930-f004: Errors in the geocoding results.

Mentions: Figure 4 displays a typical geocoding error that was ignored until it could be identified through visual examination. After some initial operations in address matching were performed, it was noticed that some physicians’ addresses could not be matched to any surrounding parcels. The highlighted point in Figure 4 is actually a cluster of 161 physicians whose addresses are geocoded to the same location. For this reason, when we zoom to the targeted area on the map, it can be found that this cluster of physicians is close to Emory University Hospital. By examining the addresses in the attribute table, a combination of problems can be found since some of the physicians’ addresses are empty or not valid, while some of them do have the valid addresses but they were geocoded to the wrong location due to the maximization of location matching in the geocoding process. By examining this point location to the other points on the map in Figure 4, it can be found that all other geocoded locations are along the road centerlines, while this problematic location is not close to any road. For this reason, visual reasoning helps to derive a conclusion as a geocoded location could be wrong if it is not along the street centerline. In general, a hybrid method was applied in the geocoding process to increase matches. For example, in case that the address information in the physician profile was not complete, when the zip codes were available in the profile, then such zip codes from the preferred mailing addresses were utilized to accomplish the geocoding process. Such locations would most likely fail to be geocoded at street level. Particularly since the text mining and string matching approach could generate a matching result to a higher degree, we can find the differences in the results derived from two different approaches.


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

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

ijerph-13-00930-f004: Errors in the geocoding results.
Mentions: Figure 4 displays a typical geocoding error that was ignored until it could be identified through visual examination. After some initial operations in address matching were performed, it was noticed that some physicians’ addresses could not be matched to any surrounding parcels. The highlighted point in Figure 4 is actually a cluster of 161 physicians whose addresses are geocoded to the same location. For this reason, when we zoom to the targeted area on the map, it can be found that this cluster of physicians is close to Emory University Hospital. By examining the addresses in the attribute table, a combination of problems can be found since some of the physicians’ addresses are empty or not valid, while some of them do have the valid addresses but they were geocoded to the wrong location due to the maximization of location matching in the geocoding process. By examining this point location to the other points on the map in Figure 4, it can be found that all other geocoded locations are along the road centerlines, while this problematic location is not close to any road. For this reason, visual reasoning helps to derive a conclusion as a geocoded location could be wrong if it is not along the street centerline. In general, a hybrid method was applied in the geocoding process to increase matches. For example, in case that the address information in the physician profile was not complete, when the zip codes were available in the profile, then such zip codes from the preferred mailing addresses were utilized to accomplish the geocoding process. Such locations would most likely fail to be geocoded at street level. Particularly since the text mining and string matching approach could generate a matching result to a higher degree, we can find the differences in the results derived from two different approaches.

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.