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

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.

Physician Multisite Practicing: Impact on Access to Care

“…The collection and geocoding of health workforce data reveal 3 uncertainty issues of particular concern in the derivation of correct physician practice locations: (1) uncertainty in survey results, such as the accuracy of address information collected 6–8 ; (2) uncertainty in the road network data, which are the source for geocoding and deriving latitude and longitude from address information 9,10 ; and (3) uncertainty about whether the addresses are practice addresses or home addresses. 11–13 However, an additional layer of spatial uncertainty exists in physician practice locations: multisite practicing. Most of the literature has focused on the first 3 issues and largely ignored multisite practicing; there is a general lack of study on multisite practicing, largely because of the dearth of workforce data capturing such practice patterns.…”

Effective Scalable and Integrative Geocoding for Massive Address Datasets

“…Recently, design of application specific geocoding system has attracted much interest [17,19,33]. Geocoding is considered as an initial process to generate input data to support other studies such as public health research [20,21,36,37]. Different methods for linking and binding geocoding data to records are discussed in [35] and impact of geocoding error and its propagation through final results is analyzed in [40].…”

“…Linear interpolation is the most common interpolation method to apply on these reference datasets. Using street network maps along with linear interpolation is known as traditional geocoding which is widely used in geocoding systems [18,36,42].…”

“…Such definition does not provide sufficient information on how close the results are to the "ground truth" points. Another important concept in geocoding is Spatial accuracy, positional accuracy or positional error which is used in literatures with the same meaning of average distance between results from geocoding process and ground truth geolocation [31,32,35,36,39,41,42]. Although, match rate and positional accuracy have been studied in many literatures, fewer of them report exact numbers for positional accuracy and there was less attention to this measurement till recently [32].…”

Understanding the clustering patterns in physician distribution through Affinity Propagation

“…In our pilot research, we successfully differentiate the home addresses from non-home addresses through spatial analytics, text mining, and visual examination [13] by parsing and comparing the physicians’ addresses to the addresses documented in the parcel datasets that contain the zoning code of the land use types. When the physician’s address can be matched to a parcel, it can be clarified whether it is home address or not as the zoning code of the parcel specifies its usage as single family or multi-family resident community, for commercial or industrial development, or as tax exempted areas including governmental properties, churches, hospitals, non-profit organizations, and so on.…”