Data Requirements for Process Learning

Data Requirements for Process Learning

Johny Ghattas (University of Haifa, Haifa, Israel, & Smart Path Ltd, Jaffa-Tel-Aviv, Israel), Mor Peleg (Department of Information Systems, University of Haifa, Haifa, Israel), Pnina Soffer (Department of Information Systems, University of Haifa, Haifa, Israel) and Yaron Denekamp (Faculty of Medicine, Galil Center for Medicial Informatics, Technion Institute of Technology, Haifa, Israel)
Copyright: © 2013 |Pages: 18
DOI: 10.4018/ijkbo.2013010101
OnDemand PDF Download:
No Current Special Offers


Process flexibility and adaptability is essential in environments where the processes are prompt to changes and variations. Process learning is a possible approach for automatically discovering from process log data those process paths that yielded good outcomes and suggesting appropriate process model modifications to enhance future process performance in such environments. The authors discuss and establish the data requirements for process learning, applicable to clinical process management. Their discussion extends a previously established learning process model (LPM) by providing a formal set of data requirements which enables the authors to accomplish effective learning. Learning data requirements are illustrated by walking through the application of the LPM framework to a clinical process.
Article Preview

The Learning Process Model (Lpm)

Let us consider a clinical process; while diagnosing a patient, the clinical expert needs to consider the available data about the patient, including his current state, medical history, and any inputs that may be important for making decisions throughout the clinical process, including diagnosis and treatment.

The data required for the clinical expert to accomplish this task is provided in two different time periods: (a) initially available data from the patient records and from the initial examination of the patient; (b) data generated by external events during process execution, such as sudden changes in the state of the patient. External events, which are out of the clinical team’s control, may provide additional inputs, which may require some change to the patient treatment decided up to that moment. Together, the initial inputs and the external events data determine the overall path to be adopted and constitute what we call the process context.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 12: 4 Issues (2022): Forthcoming, Available for Pre-Order
Volume 11: 4 Issues (2021): 2 Released, 2 Forthcoming
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing