Discovering possible patterns associations among drug prescriptions

Abstract

Nowadays, the use of electronic records in clinical practice can be used to help decision making processes and give an entire view of all health services provided from all points of view. The constant grow of data storage associated to medication prescriptions allow people to get powerful and useful information by applying data mining techniques. Association rules, which are normally used in transactions databases, can be applied on this kind of data and produce relevant rules from existing patterns. The information retrieved by the patterns found in medica- tion prescriptions data can lead to a wide range of new management solutions and possible services optimization. In this work we present a study about medication prescriptions in north region of Portugal. The main goal is to find possible relations among medication prescriptions themselves, and between the medication prescribed by a doctor and the lab associated with those medication. Since this kind of stud- ies lack in Portugal, our results provide valuable information for those working in the area that need to make decisions in order to optimize resources within health institutions.