Assistant Visiting Professor
This presentation highlights a research project that analyzed historical data related to medication administration errors at a Regional Medical Center. The objective of this analysis was to determine if data mining techniques could identify relationships within the error data that point to processes and circumstances that enable medication administration errors.
This research project utilized the Cross Industry Standard Process for Data Mining (CRISP-DM) to determine if data mining techniques applied to a medication administration error data could yield information that could improve the systems and processes supporting medication administration at a regional medical center.
Data sources from the point of medication dispensing to the patient's response covering a one year period were queried to obtain all available information relating to an acknowledge medication administration error. These data were analyzed using Microsoft SQL Server 2005 - Clustering Algorithm. The clustering algorithm results confirm the limitations of self reporting as means of medication administration error measurement.
However, this research identifies many cultural, process, and policy inconsistencies that drive self reporting behavior and subsequently lead to marginalized error event knowledge capture. These findings contributed to the development of design improvements for medication error reporting systems. Additionally, we demonstrate the difficulty of deriving information from multiple Healthcare IT systems that are not integrated. Our experience provides practical guidance for organizations evaluating Clinical Decisions Support Systems designed to support the medication use process. Furthermore the lessons learned from this research could aid the evaluation process of commercially available data warehouse/data mining solutions for Healthcare organizations that are relying on multiple systems that are not fully interoperable.