data mining: opportunities and challenges
Chapter XV - Data Mining in Health Care Applications
Data Mining: Opportunities and Challenges
by John Wang (ed) 
Idea Group Publishing 2003
Brought to you by Team-Fly


A close examination of Table 2 suggests the primary determinants in attaining a successful CHIN implementation are overcoming Competition, Economic, Organizational Autonomy and Control and Political Issues thereby indicating that the technical or technology implementation is not the deterrent. Rather, the above issues relate to the broader social and political dynamics of the health care industry. Of the thirty interviews with members of these projects, there was consistent concern about two issues: 1) what is the purpose of warehousing community data?, and 2) how should the data be used?

To address the first question, numerous writings have offered rationale for warehousing health care data. For instance, the 2001 American Medical Informatics Association Conference ( hosted several panels and paper sessions to address the needs of warehousing medical data; these assessments included:

  1. the critical integration of clinical and administrative data from a myriad of source systems;

  2. determination of cost efficiency measures between the general population and individual patient; and

  3. retrospective and prospective studies of medical history, prescriptions and laboratory results among patient medical records.

The warehousing of patient data, particularly in a CHIN domain, offers the industry the capability to more efficiency identify risk factors associated with disease episodes and prevention-focused public health requirements, and to electronically link the diverse players (e.g., providers and payors insurance companies) along the health care continuum. Moreover, such applications lend themselves to intelligent data analysis that require accurate data quality technologies in the mining of health care data.

To determine how warehoused health care data can be best utilized, one can return to the outcomes of the CHIN cases. One recurring theme from each of the cases was the need to access data for resource utilization and determination of medical outcomes within a broader population, in general, and single patient, in particular. Other uses of these data include pattern identification by sample groups by statistically slicing the data by demographic, socio-economic and other characteristics. All of these uses of warehoused health care data stimulate more effective and efficient deployment resources and knowledge bases among communities - thereby influencing public policy implications.

While data-mining applications offer the industry these and other advantages, the social challenges abound. The erosion of personal privacy and the security of the data remain formidable issues. These are particularly of issue regarding existing health care Web sites (e.g.,, that enable consumers to track data (e.g., on AIDS/HIV, diabetes, cancer, sickle cell anemia, etc.) and can provide marketing and medical leads for drug manufacturers and health care insurers. According to the Association of Computing Machinery (ACM) U.S. Public Policy Committee ( and other industry groups, horror stories about unauthorized disclosure of patient information are numerous; consumers continue to battle the losses and costs associated with privacy invasion. As pointed out by Barbara Simons, chair of the ACM Public Policy Committee, ( drafts from the National Information Infrastructure Task Force stated:

"medical information is routinely shared with and viewed by third parties who are not involved in patient care. The American Medical Records Association has identified twelve categories of information seekers outside the health care industry who have access to health care files, including employers, government agencies, credit bureaus, insures, educational institutions and the media."

Further, and in the context of data mining and CHINs, several questions remain unanswered with regard to the warehousing and mining of health care information:

  1. Who owns the data?

  2. What are the costs associated with the "inability" to mine community data?

  3. What security policies and procedures should be implemented in a CHIN (data-mining) application?

  4. How do CHINs improve public health?

  5. How should organizational practices be re-engineered to ensure that security policies and procedures are practiced within the organization?

Brought to you by Team-Fly

Data Mining(c) Opportunities and Challenges
Data Mining: Opportunities and Challenges
ISBN: 1591400511
EAN: 2147483647
Year: 2003
Pages: 194
Authors: John Wang © 2008-2017.
If you may any questions please contact us: