Programmatic Theme: Translational Bioinformatics

Abstract: In this work, we aim to enhance the reliability of health information technology (HIT) systems by detection of plausible HIT hazards in clinical order transactions. In the absence of well-defined event logs in corporate data warehouses, our proposed approach identifies relevant timestamped data fields that could indicate transactions in the clinical order life cycle generating raw event sequences. Subsequently, we adopt state transitions of the OASIS Human Task standard to map the raw event sequences and simplify the complex process that clinical radiology orders go through. We describe how the current approach provides the potential to investigate areas of improvement and potential hazards in HIT systems using process mining. The discussion concludes with a use case and opportunities for future applications.

Learning Objective: In this paper, we describe an approach to EHR data that reverse engineers raw event sequences per clinical order (Feature Engineering). We also make use of OASIS Human-Task standard in Healthcare setting (for radiology orders) and generate simplified event logs. Leveraging process mining we reveal rare and irregular patterns in order state transitions that are indicative of potential HIT hazards (adverse events and interruptions in care delivery).

Authors:

Ozgur Ozmen, Oak Ridge National Laboratory
Hilda Klasky (Presenter)
Oak Ridge National Laboratory

Olufemi Omitaomu, Oak Ridge National Laboratory
Mohammed Olama, Oak Ridge National Laboratory
Teja Kuruganti, Oak Ridge National Laboratory
Laura Pullum, Oak Ridge National Laboratory
Merry Ward, US Department of Veterans Affairs
Jean Scott, US Department of Veterans Affairs
Angela Laurio, US Department of Veterans Affairs
Frank Drews, US Department of Veterans Affairs
Jonathan Nebeker, US Department of Veterans Affairs