GIS Application of Healthcare Data for Advancing Epidemiological Studies

Healthcare practices increasingly rely on advanced technologies to improve analysis capabilities for decision making. In particular, spatial epidemiological approach to healthcare studies provides significant insight in evaluating health intervention and decisions through Geographic Information Systems (GIS) applications. This chapter illustrates a space-time cluster analysis using Kulldorff’s Scan Statistics (1999), local indicators of spatial autocorrelation, and local G-statistics involving routine clinical service data as part of a limited data set collected by a Northeast Ohio healthcare organization over a period 1994 – 2006. The objective is to find excess space and space-time variations of lung cancer and to identify potential monitoring and healthcare management capabilities. The results were compared with earlier research (Tyczynski & Berkel, 2005); similarities were noted in patient demographics for the targeted study area. The findings also provide evidence that diagnosis data collected as a result of rendered health services can be used in detecting potential disease patterns and/or utilization patterns, with the overall objective of improving health outcomes.

Physician Characteristics Associated with Early Adoption of Electronic Medical Records in Smaller Group Practices

To examine physician characteristics and practice patterns associated with the adoption of electronic medical records (EMRs) in smaller group practices. Primary care physicians in Kentucky were surveyed regarding their use of EMRs. Respondents were asked if their practice had fully implemented, partially implemented, or not implemented EMRs. Of the 482 physicians surveyed, the rate of EMR adoption was 28%, with 14% full implementation and 14% partial implementation. Younger physicians were significantly more likely to use EMRs (p = 0.00). For those in their thirties, 45% had fully or partially implemented EMRs compared with 15% of physicians aged 60 and above. In logistic regression analyses that controlled for practice characteristics, age, male gender, and rural location predicted EMR adoption. Younger physicians in smaller group practices are more likely to adopt EMRs than older physicians. EMRs were also associated with an increased use of chronic disease management.

Issues and Techniques to Mitigate the Performance Gap in Content-Based Image Retrieval Systems

This chapter discusses key aspects concerning the performance of Content-based Image Retrieval (CBIR) systems. The so-called performance gap plays an important role regarding the acceptability of CBIR systems by the users. It provides a timely answer to the actual demand for computational support from CBIR systems that provide similarity queries processing. Focusing on the performance gap, this chapter explains and discusses the main problems currently under investigation: the use of many features to represent images, the lack of appropriate indexing structures to retrieve images and features, deficient query plans employed to execute similarity queries, and the poor quality of results obtained by the CBIR system. We discuss how to overcome these problems, introducing techniques such as how to employ feature selection techniques to beat the “dimensionality curse” and how to use proper access methods to support fast and effective indexing and retrieval of images, stressing the importance of using query optimization approaches.

The Impact of Information Technology across Small, Medium, and Large Hospitals

Hospitals invest in Information Technology to lower costs and to improve quality of care. However, it is unclear whether these expectations for Information Technology are being met. This study explores Information Technology (IT) in a hospital environment and investigates its relationship to mortality, patient safety, and financial performance across small, medium, and large hospitals. Breaking down IT into functional, technical, and integration components permits the assessment of different types of technologies’ impact on financial and operational outcomes. Findings indicate that both IT sophistication (access to IT applications) and IT sophistication’s relationship to hospital performance varies significantly between small, medium, and large hospitals. In addition, empirical investigation of quality, safety, and financial performance outcomes demonstrates that the observed impact of IT is contingent upon the category of IT employed.

Perceptions of an Organizing Vision for Electronic Medical Records by Independent Physician Practices

Actual adoption and usage rates of healthcare Information Technology (HIT) in general and electronic medical records (EMR) in particular are well below expectations, even though both show potential to help solve some of the more pressing problems plaguing the U.S. healthcare system. This research explores the role that a community-wide organizing vision (OV) (Ramiller & Swanson, 2003) plays in shaping independent physician practices’ perceptions of EMR technology, and hence, their interest in adopting and using the technology. This chapter reports on an OV for EMRs by analyzing data collected using a mail survey of independent physician practices and uses factor analysis to examine structural properties and content of the OV among the practices sampled. Contributions to theory include exploring the applicability of Ramiller and Swanson’s (Ramiller & Swanson, 2003; Swanson & Ramiller, 2004, 1997) OV on HIT innovations in healthcare research. Contributions to practice include empowering HIT decision makers with a model for addressing the introduction of a technology innovation (EMR) into an independent physician practice.

Alerts in Healthcare Applications

Urgent requests and critical messages in healthcare applications must be delivered and handled timely instead of in an ad-hoc manner for most current systems. Therefore, we extend a sophisticated alert management system (AMS) to handle process and data integration in healthcare chain workflow management under urgency constraints. Alerts are associated with healthcare tasks to capture the parameters for their routing and urgency requirements in order to match them with the specialties of healthcare personnel or the functionalities of Web Services providers. Monitoring is essential to ensure the timeliness and availability of services as well as to ensure the identification of exceptions. We outline our implementation framework with Web Services for the communications among healthcare service providers together with mobile devices for medical professionals. We demonstrate the applicability of our approach with a prototype medical house-call system (MHCS) and evaluate our approach with medical professionals and various stakeholders.

Decision Making by Emergency Room Physicians and Residents

Clinical Decision Support Systems (CDSS) are typically constructed from expert knowledge and are often reliant on inputs that are difficult to obtain and on tacit knowledge that only experienced clinicians possess. Research described in this article uses empirical results from a clinical trial of a CDSS with a decision model based on expert knowledge to show that there are differences in how clinician groups of the same specialty, but different level of expertise, elicit necessary CDSS input variables and use said variables in their clinical decisions. This article reports that novice clinicians have difficulty eliciting CDSS input variables that require physical examination, yet they still use these incorrectly elicited variables in making their clinical decisions. Implications for the design of CDSS are discussed.

Multi-Modal Content Based Image Retrieval in Healthcare

Multi-modal imaging requires innovations in algorithms and methodologies in all areas of CBIR, including feature extraction and representation, indexing, similarity measurement, grouping of similar retrieval results, as well as user interaction. In this chapter, we will discuss the rise of multi-modal imaging in clinical practice. We will summarize some of our pioneering CBIR achievements working with these data, exemplified by a specific application domain of PET-CT. We will also discuss the future challenges in this significantly important emerging area.

Evaluation Challenges for Computer-Aided Diagnostic Characterization

Evaluating the success of computer-aided decision support systems depends upon a reliable reference standard, a ground truth. The ideal gold standard is expected to result from the marking, labeling, and rating by domain experts of the image of interest. However experts often disagree, and this lack of agreement challenges the development and evaluation of image-based feature prediction of expert-defined “truth.” The following discussion addresses the success and limitation of developing computer-aided models to characterize suspicious pulmonary nodules based upon ratings provided by multiple expert radiologists. These prediction models attempt to bridge the semantic gap between images and medically-meaningful, descriptive opinions about visual characteristics of nodules. The resultant computer-aided diagnostic characterizations (CADc) are directly usable for indexing and retrieving in content-based medical image retrieval and supporting computer-aided diagnosis. The predictive performance of CADc models are directly related to the extent of agreement between radiologists; the models better predict radiologists’ opinions when radiologists agree more with each other about the characteristics of nodules.

Internet as a Source of Health Information and its Perceived Influence on Personal Empowerment

The primary aim of this study is twofold. First, the authors seek to identify the factors that influence members of the general public to conduct Internet searches for health information. Their second intent is to explore the influence such Internet use has on three types of personal empowerment. In the summer of 2007 the authors conducted a household sample survey of a population of Canadian adults. A total of 261 self-administered questionnaires were returned to the researchers. Our findings indicate that use of the Internet as a source of health information is directly realted to three main factors: sex, age and the individual’s perceived ability to understand, interpret and use the medical information available online. Further, their results lend support to the notion that using the Internet to search for information about health issues represents a more consumer-based and participative approach to health care. This study is one of the first to relate Internet use to various forms of personal empowerment. This area appears to have great potential as a means by which consumers can become more empowered in managing personal health issues.