Call for Papers

Innovative informatics methods for process mining in health care

https://www.journals.elsevier.com/journal-of-biomedical-informatics/call-for-papers/innovative-informatics-methods-for-process-mining-in-health

The world’s most valuable resource is no longer oil, but data. The biomedical and health domains are no exception. The ultimate goal of biomedical informatics techniques is not to collect more data, but to extract valuable knowledge and insights from existing data. Regarding the execution of clinical processes, more and more data are being captured in the form of event data by, for instance, electronic health record systems. Event data constitutes a key source of information to analyze and improve clinical processes. In recent years, a new discipline has emerged which combines traditional process analysis and datacentric analysis: process mining. Research interest, focusing on the development of innovative methods, has experienced a remarkable growth in recent years. In 2016, the review paper “Process mining in health care: a literature review” [1], published in JBI, identified 74 articles on this topic. By mid 2020, the number of articles citing this same review reached more than 285. Within the biomedical informatics context, process mining contributions have dealt with various challenges in recent years. These include, for instance, the extraction of typical treatment processes from electronic medical records [2], the automatic detection of process deviations in trauma resuscitation [3], the discovery of collaboration patterns between health care professionals in the emergency room [4], and the suitable abstraction of medical event data to discover processes and compare traces [5].

This special issue provides a high-quality forum for interdisciplinary researchers to propose novel informatics methods for process mining in health care. The submitted papers should center around relevant problems experienced in the medical domain and propose innovative process mining methods to deal with them. Hence, submissions should move beyond using a brief health care application simply to illustrate a highly generic process mining method. The special issue welcomes high-quality and innovative submissions on a wide range of topics, including (but not limited to):

• Data extraction, integration and preparation for process mining in health care
• Data-driven modeling, analysis and improvement of health care processes
• Data-driven compliance analysis for health care processes
• Data-driven monitoring of health care processes
• Multi-perspective approaches for process mining in health care
• Root-cause analysis for health care processes
• Predictive analytics for health care processes
• Data-driven process recommendations in health care
• Data-driven simulation and optimization of health care processes
• Human-in-the-loop approaches to process mining in health care
• Privacy-preserving approaches for process mining in health care

For all topics, the focus should be on the development of novel methods and techniques for process mining in a biomedical informatics context.

Questions regarding the special issue

Please direct any questions regarding the special issue to Dr. Jorge Munoz-Gama (jmun@uc.cl).

References

• [1] E. Rojas, J. Munoz-Gama, M. Sepúlveda, D. Capurro, Process mining in health care: A literature review, J. Biomed. Inform. 61 (2016) 224–236.
• [2] J. Chen, L. Sun, C. Guo, W. Wei, Y. Xie, A data-driven framework of typical treatment process extraction and evaluation, J. Biomed. Inform. 83 (2018) 178–195.
• [3] S. Yang, A. Sarcevic, R.A. Farneth, S. Chen, O.Z. Ahmed, I. Marsic, R.S. Burd, An approach to automatic process deviation detection in a time-critical clinical process, J. Biomed. Inform. 85 (2018) 155–167.
• [4] C. Alvarez, E. Rojas, M. Arias, J. Munoz-Gama, M. Sepúlveda, V. Herskovic, D. Capurro, Discovering role interaction models in the emergency room using process mining, J. Biomed. Inform. 78 (2018) 60–77.
• [5] G. Leonardi, M. Striani, S. Quaglini, A. Cavallini, S. Montani, Leveraging semantic labels for multi-level abstraction in medical process mining and trace comparison, J. Biomed. Inform. 83 (2018) 10–24.