Towards a Comparative Assessment of Data-Driven Process Models in Health Information Technology

Conference · 01 December 2023

DOI:https://doi.org/10.1109/ICHI57859.2023.00052· OSTI ID:2282971

Klasky, Hilda  ^[1]; Ozmen, Ozgur  ^[1]; Omitaomu, Femi  ^[1]; Olama, Mohammed M.  ^[1]; Ward, Merry ^[2]; Laurio, Angela ^[2]; Nebeker, Jonathan R. ^[2]

---

1. ORNL
2. Department of Veterans Affairs

Process mining for conformance analysis focuses on comparing a reference process model against a data-driven process model that is generated via log files from information technology systems. While this approach is helpful when there is an existing process model in an organization, it leaves the question of what to do in the absence of a complete reference process model unanswered. In this paper, we present a comparative assessment approach that combines process mining, process mapping for dimensionality reduction, and statistical analysis. Our goal is to find similarities and dissimilarities in data-driven process models among U.S. Veterans Health Administration (VHA) facilities to assess process conformance among different healthcare facilities, which can help assess the standardization of care. We illustrate our approach by applying it to two clinical radiology order process models generated by two similar facilities. Our results demonstrate statistical similarities in the standardization of care among those two facilities.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 2282971
• Resource Relation: Conference: IEEE ICHI 2023: International Conference on Healthcare Informatics - Houston, Texas, United States of America - 6/26/2023 11:00:00 AM-6/29/2023 11:00:00 AM
• Country of Publication: United States
• Language: English