Adaptive Identification and Modeling of Clinical Pathways with Process Mining

TL;DR

Clinical pathways vary across patients and diseases, challenging manual guideline-based modeling. The authors propose a two-phase process mining framework, with training on historical data to build a baseline knowledge base and online adaptation via conformance checking to discover and incorporate new pathways. Using the Synthea COVID-19 dataset, the method achieves high AUC values (up to 95.62%) while maintaining interpretable, simple representations and progressively more tailored pathway variants. This work offers a data-driven, adaptive approach to clinical pathway modeling that can improve personalization and resource planning in healthcare.

Abstract

Clinical pathways are specialized healthcare plans that model patient treatment procedures. They are developed to provide criteria-based progression and standardize patient treatment, thereby improving care, reducing resource use, and accelerating patient recovery. However, manual modeling of these pathways based on clinical guidelines and domain expertise is difficult and may not reflect the actual best practices for different variations or combinations of diseases. We propose a two-phase modeling method using process mining, which extends the knowledge base of clinical pathways by leveraging conformance checking diagnostics. In the first phase, historical data of a given disease is collected to capture treatment in the form of a process model. In the second phase, new data is compared against the reference model to verify conformance. Based on the conformance checking results, the knowledge base can be expanded with more specific models tailored to new variants or disease combinations. We demonstrate our approach using Synthea, a benchmark dataset simulating patient treatments for SARS-CoV-2 infections with varying COVID-19 complications. The results show that our method enables expanding the knowledge base of clinical pathways with sufficient precision, peaking to 95.62% AUC while maintaining an arc-degree simplicity of 67.11%.

Figures (4)

• Figure 1: The proposed two-phase method for adaptive identification and modeling of clinical pathways in healthcare.
• Figure 2: A BPMN model describing different procedures in a clinical pathway mined through our method.
• Figure 3: The fitness values per process discovery algorithm and clustering technique for each iteration, in comparison with the baseline.
• Figure 4: The time required for batch processing of the event logs during online adaptation at each iteration for all the methods.