Signal from the noise: A mixed graphical and quantitative process mining approach to evaluate care pathways applied to emergency stroke care

Abstract

Objective: Mapping real-world practice patterns vs. deviations from intended guidelines and protocols is necessary to identify and improve the quality of care for emergent medical conditions like acute ischemic stroke. Most status-quo process identification relies on expert opinion or direct observation, which can be biased or limited in scalability. We propose a mixed graphical and quantitative process mining approach to Electronic Health Record (EHR) event log data as a unique opportunity not only to more easily identify practice patterns, but also to compare real-world care processes and measure their conformance or variability.

Materials: Data was obtained from the event log of a major EHR vendor (Epic) for Stanford Health Care Hospital patients aged 18 years and older presenting to the ED from January 1, 2010 through December 31, 2018 and receiving tPA (tissue plasminogen activator) within 4.5 h of presentation.

Methods: We developed an unsupervised process-mining algorithm to create a process map from clinical event logs. The method first identifies the most common events across the cohort. Then, all possible ordered events are recorded, and a summarized vector of nodes (events) and edges (events occurring in series) are mapped by their timing and probability. The highest probability ordered pairs are used to identify the most common path. We define measures for individual pathways conformity and average conformity across all encounters.

Results: Automatically generated process mining graphs, and specifically it's the most common path, mimicked our institutions recommended "code stroke" clinical pathway. The average conformity score for our cohort was 0.36 (i.e. paths had an average of 36% overlap with all possible paths), with a range from high of 0.64 and low of 0.20.

Discussion: This method allows for unsupervised visualization of the current state of common processes as well as their most common path, which can then be used to calculate the conformity of individual pathways through this process. These results may be used to evaluate the consistency of quality care at a given institution. It may also be extended to other common processes like sepsis or myocardial infarction care or even those which currently lack standardized clinical pathways.

Conclusion: Our mixed graphical and quantitative process mining approach represents an essential data analysis step to improve complex care processes by automatically generating qualitative and quantitative process measures from existing event log data which can then be used to target quality improvement initiatives.

Keywords: Big data; Process mining; Quality improvement (QI); Stroke; Unsupervised machine learning.