Using dependency/association rules to find indications for computed tomography in a head trauma dataset

Imberman, Susan P.; Domanski, Bernard; Thompson, Hilary W.

doi:10.1016/s0933-3657(02)00052-0

Cited by 20 publications

(17 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It does not attempt to modify the data mining process as the algorithms and statistical methods available currently are generally applicable and effective for the medical domain and have been used successfully by many medical teams. However these projects are often undertaken by specialists who understand the tools and technologies or they have required manual post mining translation or interpretation of outputs by domain specialists (Imberman & Domanski 2002;Moser et al, 1999). The results presented here show that ADAPT is able to facilitate the ordering and presentation of complex outputs in a more intuitive language and provide the knowledge items required for decision making as described earlier.…”

Section: Nonementioning

confidence: 67%

“…As an integrated unit, the hypothesis engine and ADAPT are able to facilitate greater access to mining technologies, and the ability to apply some of the more complex mining technologies by all medical users without the risk of producing irrelevant or incomprehensible outputs. The health domain is a myriad of complexity and standardised data mining techniques are often not applicable (Cios, 2002, Imberman & Domanski 2002Hagland, 2004) hence the need for a deeper analysis of the potential for data mining in the medical domain which in turn requires knowledge of the process of medical knowledge acquisition and how the data mining technologies can facilitate this process. The remainder of this chapter aims to reduce this knowledge gap through a discussion of the processes of knowledge acquisition and diagnostic decision making in the medical domain and of the potential for novel data pattern evaluation methods to augment and automate these processes.…”

Section: Clinical Data Mining Contextmentioning

confidence: 99%

“…Whilst this was a satisfactory representation for results which had to absolutely comply with the stated thresholds and are hence critical to acceptance, it provided no indication of where results were outside of, but close enough to, the required thresholds as determined again by a user measure of acceptable flexibility. There are numerous statistical measures and methods available to test a pattern (Imberman & Domanski, 2002;Beals et al, 1999), however they may not be critical measures of pattern interest strength to a particular user.…”

Section: Concept Formalisationmentioning

confidence: 99%

See 2 more Smart Citations

Building Clinical Trust in Automated Knowledge Acquisition

Shillabeer¹

2008

Data Mining in Medical and Biological Research

View full text Add to dashboard Cite

The aim of this chapter is to describe the process of medical knowledge acquisition from a historical context and to define the requirements for producing knowledge which is able to be trusted and applied in a clinical setting. This is related to modern data mining approaches which do not yet adequately address these requirements. This is believed to be the most critical issue in the acceptance of data mining in the medical domain. The chapter will discuss how data mining can address these needs and will provide discussion of a technical solution to the stated issues. Overall this chapter aims to demonstrate that the individual needs of all medical professionals can be addressed and that data mining can be a valuable tool in the diagnostic and decision making toolkit. It will also empower medical professionals to take a greater role in the development of such systems by providing a checklist of features to include and pitfalls to avoid, thus ensuring greater success in future systems. Introduction Clinical data mining contextWhile acceptance of data mining technologies is growing, progress has been slow and it is not yet an integrated part of the medical data analysis toolkit. Many reasons have been documented for this but the primary issues are two fold; the decision making and knowledge acquisition processes of the medical domain are not adequately reflected in the technologies available and the systems are too often built to suit the specific analytical needs of an individual user. Whilst this has enabled the application of the technology in specific scenarios, it has resulted in the development of tools which cannot be utilised outside of the specific purpose for which they were built. These issues serve to limit the exposure, applicability and trust of data mining systems to the medical domain. Data mining researchers have long been concerned with the application of tools to facilitate and improve data analysis on large, complex data sets for the purpose of knowledge acquisition. The current challenge is to make data mining and knowledge discovery systems applicable to a wider range of domains, among them medicine. Early work was performed over transactional, retail based data sets, but the attraction of finding previously unknown knowledge from the increasing volume of data collected from the medical domain is an emerging area of interest and specialisation. This chapter is primarily concerned with Open Access Database www.intechweb.org There is a growing body of work which aims to qualify and define a process for the discovery of new knowledge accross a range of domains, however this work has not focused on the unique needs of the medical domain and hence the domain has remained relatively untouched by the advances in data mining and knowledge discovery technology. The primary challenge presented by medicine is to develop a technology that can apply a trusted knowledge acquisition process to reveal data patterns in the form of hypotheses which are based on measures that can be relied upon in medical healt...

show abstract

Section: Nonementioning

confidence: 67%

Section: Clinical Data Mining Contextmentioning

confidence: 99%

Section: Concept Formalisationmentioning

confidence: 99%

See 1 more Smart Citation

Building Clinical Trust in Automated Knowledge Acquisition

Shillabeer¹

2008

Data Mining in Medical and Biological Research

View full text Add to dashboard Cite

show abstract

“…It is a popular and well researched method for discovering interesting relations between variables and data. With the in-depth research of related work, association rule has been widely used in many areas including commerce, computer science, medicine, etc (Imberman, Domanski, and Thompson, 2002). At present, the application of association rule learning in the field of education and learning is at the early stage.…”

Section: Association Rule Miningmentioning

confidence: 99%

Members’ Behavior in Virtual Learning Community: A Study Using Data Mining Approach

Li¹,

Nie²,

Chen³

et al. 2014

CIS

View full text Add to dashboard Cite

Purpose: With the development of information technology, online virtual learning community is on its way to become an important approach for people to construction and sharing of knowledge. Researches on virtual learning community are not only important to the establishment and management of virtual learning community itself, but are helpful for people's quest for the future development of online learning. However, current researches related to the virtual learning community are in inadequacy, and especially the application of quantitative analysis method for research is rarely seen. Using quantitative analysis method of data mining to study members' behavior in online learning communities. Method: In this article, the discussion data (posts) from five online English virtual learning communities in China are sampled and colleted. These data were processed according to a series of guidelines to obtain proper data documents, and these data documents were opened under Waikato Environment for Knowledge Analysis and then carried out preprocessing. Next, the module of association rule learning in Waikato Environment Knowledge Analysis were used to perform mining on these processed data, and obtained a series of potential behavior rules in these communities. The partial rules have been listed in the article with their meaning analyzed. Findings: The result shows that in this setting it is feasible to apply the association rule learning to virtual learning community. Value: It provides approaches and lays the foundation for future relevant studies.

show abstract

“…There has been research on graph mining (see [7] for an overview); however, none of it analyzes the process of graph construction. There has also been research on determining when a relationship between two variables is interesting, usually in the context of association rule mining ( [20,11,10,12,13,6]). However, some of this work still assumes the typical support and confidence measures; since support excludes small sets, such work does not cover the same ground as ours.…”

Section: Related Workmentioning

confidence: 99%

Graph building as a mining activity

Badia

Kantardzic

2005

Proceedings of the 3rd International Workshop on Link Discovery

View full text Add to dashboard Cite

Many analysis of data proceed by building a graph out of the data set and then using social network theory and similar tools on the result. However, there is no theory concerning the construction of the graph itself, even though this is a very important process. In this paper, we attempt to provide a framework in which the graph building process is formalized and studied. We show the parameters (choices) involved in constructing a graph from raw data, and propose some new ways to combine and analyze the data. We also argue the importance of this approach in several domain applications, including criminal/terrorist investigations.

show abstract

Using dependency/association rules to find indications for computed tomography in a head trauma dataset

Cited by 20 publications

References 7 publications

Building Clinical Trust in Automated Knowledge Acquisition

Building Clinical Trust in Automated Knowledge Acquisition

Members’ Behavior in Virtual Learning Community: A Study Using Data Mining Approach

Graph building as a mining activity

Contact Info

Product

Resources

About