Particularities of data mining in medicine: lessons learned from patient medical time series data analysis

Abstract

Nowadays, large amounts of data are generated in the medical domain. Various physiological signals generatedfrom different organs can be recorded to extract interesting information about patients’health. The analysis ofphysiological signals is a hard task that requires the use of specific approaches such as the Knowledge Discovery inDatabases process. The application of such process in the domain of medicine has a series of implications anddifficulties, especially regarding the application of data mining techniques to data, mainly time series, gatheredfrom medical examinations of patients. The goal of this paper is to describe the lessons learned and the experiencegathered by the authors applying data mining techniques to real medical patient data including time series. In thisresearch, we carried out an exhaustive case study working on data from two medical fields: stabilometry (15professional basketball players, 18 elite ice skaters) and electroencephalography (100 healthy patients, 100 epilepticpatients). We applied a previously proposed knowledge discovery framework for classification purpose obtaininggood results in terms of classification accuracy (greater than 99% in both fields). The good results obtained in ourresearch are the groundwork for the lessons learned and recommendations made in this position paper thatintends to be a guide for experts who have to face similar medical data mining projects.