Uses data mining techniques to discover unsuspected, useful patterns of infections and antimicrobial resistance from the analysis of hospital laboratory data.
Published in Chapter:
Applications of Data Mining in the Healthcare Industry
John Wang (Montclair State University, USA), Xiaohua Hu (Drexel University, USA), and Dan Zhu (Iowa State University, USA)
Copyright: © 2008
|Pages: 6
DOI: 10.4018/978-1-59904-889-5.ch010
Abstract
The workflow of health care organizations involves the generation and collection of various kinds of data relating to clinical practices, clinical trials, patient information, resource administration, policies, and research. Traditionally, statistical techniques are used to derive some operational information from the data. Data mining, a new method, provides the opportunity to derive, in an exploratory and interactive manner, valuable health care knowledge in terms of associations, sequential patterns, classifications, predictions, and symbolic rules. Such inductively-derived health care knowledge can provide strategic insights into the practice delivery of health care. As the medical field expands, it is the duty of each physician to evaluate and protect each patient from diseases, side effects, and medical mishaps. Armed with a scalpel, stethoscope, and other accruements, physicians are now armed with data mining as a tool for expanding their knowledge base. Data mining is available to every aspect within the health care industry. It is multifaceted and used in areas like insurance to detect fraud, the pharmaceutical industry to evaluate side effects of drugs, and even detection of certain diseases based on genetics.