Search

Decision context, knowledge management, decision makers, and decision strategy are fundamental components for understanding decision support systems (DSSs). This paper describes the specific case of designing a framework for an intelligent DSS in the context of pathology test ordering by general practitioners (GPs). In doing so it illustrates the processes of discovering practical and relevant knowledge from pathology request data generated and stored in a professional pathology company, investigates and understands the decision makers (GPs) through a survey about their current practices in test ordering and their requirements for decision support, and finally proposes an intelligent decision support framework as the decision strategy to support GPs in ordering pathology tests more effectively and appropriately. The process and framework developed through this case contributes effective guidance for practitioners and theoretical understanding concerning intelligent decision support in a complex environment.

Pathology ordering by general practitioners (GPs) is a significant contributor to rising health care costs both in Australia and worldwide. A thorough understanding of the nature and patterns of pathology utilization is an essential requirement for effective decision support for pathology ordering. In this paper a novel methodology for integrating data mining and case-based reasoning for decision support for pathology ordering is proposed. It is demonstrated how this methodology can facilitate intelligent decision support that is both patient-oriented and deeply rooted in practical peer-group evidence. Comprehensive data collected by professional pathology companies provide a system-wide profile of patient-specific pathology requests by various GPs as opposed to that limited to an individual GP practice. Using the real data provided by XYZ Pathology Company in Australia that contain more than 1.5 million records of pathology requests by general practitioners (GPs), we illustrate how knowledge extracted from these data through data mining with Kohonen’s self-organizing maps constitutes the base that, with further assistance of modern data visualization tools and on-line processing interfaces, can provide “peer-group consensus” evidence support for solving new cases of pathology test ordering problem. The conclusion is that the formal methodology that integrates case-based reasoning principles which are inherently close to GPs’ daily practice, and data-driven computationally intensive knowledge discovery mechanisms which can be applied to massive amounts of the pathology requests data routinely available at professional pathology companies, can facilitate more informed evidential decision making by doctors in the area of pathology ordering.

This paper identifies four approaches to resource allocation decisions in public services from the literature: a rational approach using devices such as budgets, cost-benefit analysis, statistical techniques, etc.; non-rational approaches such as satisficing, muddling through, and garbage can models of decision making; expectations analysis based on what managers believe is expected of them; and heuristics based on experience and values.Our research question was to understand, at the micro or operational level in public sector settings, how managers faced with finite resources and uncertain demand actually make resource allocation decisions and which of the approaches (or combinations of approaches) were used.A multimethods approach is adopted, comprising qualitative data collection and the analysis of timesheet data using statistical techniques and self-organising maps to identify how resource allocation decisions are made where resources are limited but demand is unpredictable and uncontrollable.The research findings are that rational devices, heuristics (informed by norms and values) and expectations (incorporating the non-rational approach) can be seen as complementary and mutually reinforcing, and are difficult to separate. Individual approaches (rational, non-rational, expectations, or heuristics) to resource allocation decisions provide an inadequate explanation for complex resource allocation decisions in a public sector setting.This is a model of resource allocation decision making that is useful both theoretically and practically, and is particularly pertinent to public sector settings where finite resources must be allocated to uncontrollable demand.

A massive rise in the number and expenditure of pathology ordering by general practitioners (GPs) concerns the government and attracts various studies with the aim to understand and improve the ordering behavior. In this paper we attempt to understand the reasons for and implications of pathology ordering by general practitioners by applying an unsupervised text mining technique on the clinical notes of the pathology requests obtained from a pathology company in Australia. Pathology requests are clustered into different groups based on the information that is included by the doctors in clinical notes accompanying the requests. Features and patterns of the groups are investigated and analyzed. The novelty of the paper is in using text mining techniques to extract knowledge from unstructured text data in the area of pathology ordering and to understand the reasons for pathology ordering from a doctors' perspective

Pathology ordering by General Practitioners (GPs) is a significant contributor to rising health care costs both in Australia and worldwide. A thorough understanding of the nature and patterns of pathology utilization is an essential requirement for addressing the issues of appropriate pathology orderings and possible over-utilization. This paper describes how Kohonen’s Self-Organizing Maps are used to discover the most typical patterns in pathology orderings for different patient groups. Test ordering data from a pathology company in Australia is analyzed; homogenous clusters of patients with similar ordering patterns are discovered and investigated, and possible management implications are discussed. The novelty of this approach is in using data mining techniques on pathology ordering data in order to provide a patient oriented perspective for understanding the nature of ordering patterns.