Text Mining Applied to Electronic Medical Records: A Literature Review

Data Mining Background

Text mining is a variation of data mining (Navathe, B., & Ramez, 2000). Thus, this section introduces the concept of data mining, its conception, techniques, learning methods, and processes that can be used and its automation.

Data mining is the process of understanding and discovering patterns in large data sets to retrieve useful knowledge (Fayyad, Piatetsky-Shapiro, & Smyth, 1996). Regarding healthcare, this knowledge can be useful to improve the quality of treatments, increasing revenues or lower costs of healthcare organization such as a hospital. Data mining is widely used in the fields of computer science, economics, communication and marketing, allowing finding important patterns on information that are, otherwise, difficult to analyse.

It is hard to say when this concept appeared. Data mining use several of Bayes algorithms created in the XVIII century (Pawlak, 2002), but only in 1989-1991 was the term introduced by researcher Gregory Piatetsky-Shapiro (Piatetsky-Shapiro, 1990).