Paper Number



Hospitals have a keen interest to root out unauthorized access of Electronic Health Records (EHRs). The retrospective analysis of suspicious EHR views may help to take preventive measures against such access. However, investigating EHR access manually is labor-intensive and only allows for checking a small sample of cases. We explore how process mining techniques can be used to support the detection of unauthorized views. In the context of EHR access, it is easier to define authorized views with certainty than to detect unauthorized views. Therefore, we propose DEUCE: a methodology that focuses on identifying authorized behavior, such that unauthorized views are distinguished, and can be investigated more in-depth. We evaluate the methodology in the form of a case study at a Dutch hospital. As a result of this study, the hospital has adopted the approach in favor of their traditional approach and unauthorized EHR access is now more efficiently detected.



When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.