From Data Lifting to Continuous Risk Estimation: A Process-Aware Pipeline for Predictive Monitoring of Clinical Pathways

2026-05-05

AI Summary

Traditional retrospective process mining struggles to enable real-time risk prediction for partially observed patient trajectories. This work proposes a process-aware predictive monitoring pipeline that frames risk prediction as a dynamic, continuous process. By integrating data augmentation, temporal reconstruction, event log construction, and prefix-based trajectory representations, the approach facilitates early and progressive risk assessment along clinical pathways. Evaluated on data from 4,479 COVID-19 patients, the method achieves an AUC of 0.906 and an F1-score of 0.835 using logistic regression alone. Moreover, as event sequences lengthen, predictive performance steadily improves from an AUC of 0.642 to 0.942, demonstrating the framework’s effectiveness and reproducibility in dynamic clinical settings.

Abstract

This paper presents a reproducible and process-aware pipeline for predictive monitoring of clinical pathways. The approach integrates data lifting, temporal reconstruction, event log construction, prefix-based representations, and predictive modeling to support continuous reasoning on partially observed patient trajectories, overcoming the limitations of traditional retrospective process mining. The framework is evaluated on COVID-19 clinical pathways using ICU admission as the prediction target, considering 4,479 patient cases and 46,804 prefixes. Predictive models are trained and evaluated using a case-level split, with 896 patients in the test set. Logistic Regression achieves the best performance (AUC 0.906, F1-score 0.835). A detailed prefix-based analysis shows that predictive performance improves progressively as new clinical events become available, with AUC increasing from 0.642 at early stages to 0.942 at later stages of the pathway. The results highlight two key findings: predictive signals emerge progressively along clinical pathways, and process-aware representations enable effective early risk estimation from evolving patient trajectories. Overall, the findings suggest that predictive monitoring in healthcare is best conceived as a continuous, dynamically aware process, in which risk estimates are progressively refined as the patient journey evolves.

Problem

• predictive monitoring
• clinical pathways
• continuous risk estimation
• patient trajectories
• process-aware

Innovation

• process-aware predictive monitoring
• data lifting
• prefix-based representation
• continuous risk estimation
• clinical pathway prediction