Data mining is a technique for analyzing large amounts of data, in various formats, often called Big Data, in order to gain knowledge about it. The healthcare industry is the next Big Data area of interest as its large variability in patients, their health status and their records which can include image scans, graphical test results, and hand-written physician notes, has been untapped for analysis. In addition to data mining, there is a newer analysis method called process mining. Process mining is similar to data mining in that large data files are reviewed and analyzed, but in this case, event logs specific to a particular process or series of processes, are analyzed. Process mining allows one to understand the initial baseline, determine any bottlenecks or resource constraints, and evaluate a recently implemented change. Process mining was conducted on a hospital event log of patients entering the emergency room with sepsis, to better understand this newer analysis method, to highlight the information discovered, and to determine its role with data mining. Not only did the analysis of the event logs provide process mapping and process analysis, but it also highlighted areas in the clinical operations in need of further investigation, including a possible relationship with patient re-admission and their release method. In addition, the data mining method of creating a histogram, of the process data, was applied, allowing data mining and process mining to be utilized complimentary.
Keywords: Data mining; process mining; sepsis.
This is an Open Access article. Authors own copyright of their articles appearing in the Journal of Public Health Informatics. Readers may copy articles without permission of the copyright owner(s), as long as the author and OJPHI are acknowledged in the copy and the copy is used for educational, not-for-profit purposes.