Citation

Tepas JJ. J. Trauma 2009; 67(2): S108-10.

Affiliation

Department of Surgery, University of Florida, College of Medicine/Jacksonville, Jacksonville, FL 32209, USA. jjt@jax.ufl.edu

Copyright

(Copyright © 2009, Lippincott Williams and Wilkins)

DOI

10.1097/TA.0b013e3181af0ad7

PMID

19667841

Abstract

Data mining is defined as the automatic extraction of useful, often previously unknown information from large databases or data sets. It has become a major part of modern life and is extensively used in industry, banking, government, and health care delivery. The process requires a data collection system that integrates input from multiple sources containing critical elements that define outcomes of interest. Appropriately designed data mining processes identify and adjust for confounding variables. The statistical modeling used to manipulate accumulated data may involve any number of techniques. As predicted results are periodically analyzed against those observed, the model is consistently refined to optimize precision and accuracy. Whether applying integrated sources of clinical data to inferential probabilistic prediction of risk of ventilator-associated pneumonia or population surveillance for signs of bioterrorism, it is essential that modern health care providers have at least a rudimentary understanding of what the concept means, how it basically works, and what it means to current and future health care.

Language: en