Related Experiment Video
Updated: May 26, 2025
Development and Implementation of a Multi-Disciplinary Technology Enhanced Care Pathway for Youth and Adults with Concussion
Published on: January 20, 2019
A Markov Chain methodology for care pathway mapping using health insurance data, a study case on pediatric TBI
Viktor-Jan De Deken1, Wilfried Cools1, Helena Van Deynse1
1REDM (Research Center on Digital Medicine), Vrije Universiteit Brussel, Brussels 1090, Belgium.
Background:
Care pathways are increasingly used in healthcare systems globally to guide patient care and improve outcomes. These pathways offer a structured approach to managing patient care processes, potentially reducing costs and enhancing efficiency. However, the dynamic and complex nature of healthcare presents challenges in analyzing and improving these pathways, particularly due to the unique and varied patient journeys. This study focuses on the use of administrative data to map care pathways for pediatric Traumatic Brain Injury (TBI) patients, a population significantly impacted by high mortality and disability rates.
Objective:
The objective of this research is to map and analyze care pathways using a novel methodology inspired by Hidden Markov chains. The study aims to overcome challenges in analyzing the dynamic and complex nature of the healthcare processes, particularly in a heterogeneous patient population. By using administrative data, the goal is to provide valuable insights into care pathways of these patients.
Methods:
The study utilizes a study case dataset comprising of 4074 children admitted to Belgian hospitals for TBI in 2016, with administrative data encompassing healthcare services up to one-year post-TBI. The proposed methodology involves representing care pathways as Hidden Markov chains, where the transition between states is determined by the current medical treatment. Hierarchical clustering based on similarity of care paths, volume, and median timepoint is applied to identify subpopulations.
Results:
Hierarchical clustering reveals distinct clusters, each characterized by unique care pathways. The clusters show variations in the length of care pathways, proportion of mild to severe cases, and vary with unique treatment events. Visualization of these pathways provides a comprehensive understanding of the treatment patterns within each cluster.
Conclusion:
The study introduces a novel methodology for mapping care pathways. Uncovering these different care pathways enhances the understanding of the variation in care and might lead to improving the quality of care received by patients.
