Discovering Clinical Pathways of an Adaptive Integrated Care Environment

Abstract

The overall demographic trend of an increasingly aging population leads to more complex chronic patients resulting in rising healthcare costs. Integrated care systems can reduce these costs and increase patients’ quality of life by replacing part of the necessary hospital visits with home hospitalization and automated monitoring. However, classical hospital information systems are not flexible enough to support these types of uncertain, human-driven treatment processes, also called clinical pathways. Therefore, adaptive case management systems have been developed. They are highly configurable, offer additional runtime flexibility and are currently being advanced in multiple large research projects. One such project is called Personalised Connected Care for Complex Chronic Patients or CONNECARE and is currently being tested at three sites across Europe in two clinical case studies each.

The goal of this work is to evaluate the usage patterns observed during the course of the CONNECARE project in order to assert the degree of executional flexibility that was employed while treating the patients. To achieve this, the web access logs of the underlying Smart Adaptive Case Management (SACM) component, CONNECARE’s case execution engine, will be analyzed using process mining techniques. Afterward, the generated visual process maps for the different case studies will be compared and evaluated regarding their contained execution flexibility. The expected high complexity of the maps is mitigated by means of manual data clustering, the provision of models at different abstraction levels, the use of the fuzzy mining algorithm and the employment of interactive visualization techniques.

Results show that while professionals in both studies and at all sites made use of the provided flexibility measures, the degree of flexibility that was used depends on the exact site. However, the degree of employed flexibility correlates with the overall system activity during each study. Additional features for collaboration and communication that are provided by the SACM component were used at a varying degree, also depending on the site. One site made extensive use of the user and role modeling capabilities but all sites showed an accumulation of performed work for individual users. At the site with the highest system activity, clinicians were shown to react to alarms based on automated measurement threshold violations by contacting colleagues or the affected patient. As the case studies are still being executed at the time of writing this work, the evaluation was designed to be re-executable once the study period has passed.

Keywords: Integrated Care, Clinical Pathway, Adaptive Case Management, ACM, Process
Mining, Process Discovery, REST, Healthcare, CONNECARE

Core literature

• Eloisa Vargiu, Juan Manuel Fernandez, Felip Miralles, Isaac Cano, Elena Gimeno-Santos, Carme Hernandez, Gerard Torres, Jordi Colomina, Jordi de Batlle, Rachelle Kaye, Bella Azaria, Shauli Nakar, M. H. Lahr, Esther Metting, Margot Jager, Hille Meetsma, Stefano Mariani, Marco Mamei, Franco Zambonelli, Felix Michel, Florian Matthes, Jo Goulden, John Eaglesham, and Charles Lowe. Integrated Care for Complex Chronic Patients. International Journal of Integrated Care, 17(5):302, October 2017. doi: 10.5334/ijic.3619.
• Felix Michel and Florian Matthes. A Holistic Model-Based Adaptive Case Management Approach for Healthcare. In 2018 IEEE 22nd International Enterprise Distributed Object Computing Workshop (EDOCW). IEEE, oct 2018. doi: 10.1109/edocw. 2018.00014.
• Wil van der Aalst. Process Mining. ACM Transactions on Management Information Systems, 3(2):1–17, jul 2012. doi: 10.1145/2229156.2229157.
• R. S. Mans, W. M. P. Aalst, van der, and R. J. B. Vanwersch. Process mining in healthcare: opportunities beyond the ordinary. BPM reports. BPMcenter.org, January 2013.
• Andrew Partington, Moe Wynn, Suriadi Suriadi, Chun Ouyang, and Jonathan Karnon. Process Mining for Clinical Processes – A Comparative Analysis of Four Australian Hospitals. ACM Transactions on Management Information Systems, 5(4):1–18, jan 2015. doi: 10.1145/2629446.
• Nik Farid, Marc De Kamps, and Owen Johnson. Process Mining in Frail Elderly Care: A Literature Review. In Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies. SCITEPRESS - Science and Technology Publications, 2019. doi: 10.5220/0007392903320339.
• Claudio Di Ciccio, Andrea Marrella, and Alessandro Russo. Knowledge-Intensive Processes: Characteristics, Requirements and Analysis of Contemporary Approaches. Journal on Data Semantics, 4(1):29–57, apr 2014. doi: 10.1007/s13740-014-0038-4.
• Tugba Gurgen Erdogan and Ayca Tarhan. A Goal-Driven Evaluation Method Based on Process Mining for Healthcare Processes. Applied Sciences, 8(6):894, may 2018. doi: 10.3390/app8060894.