Efficient pathology case distribution leveraging workflow and domain modeling, and flexible definition of policies
The value of digital pathology and its potential to improve the current pathology practice are increasingly recognized, with a growing number of examples of successful implementation in a variety of use cases. While current widely-spread uses relate to research, consultation, second opinion and education, success stories are emerging demonstrating outcome and cost benefits of leveraging digital pathology for standard diagnosis as well. In all these cases optimization of pathology workflows, standardization and seamless integration in the environment are emphasized as prerequisites to reaching the desired improvements.
We develop workflow-driven applications to enable clinical users to efficiently and effectively leverage deployed digital pathology solutions for faster diagnosis and better patient outcomes. The work addresses information integration requirements, and aims to identify and propose solutions for performance bottlenecks in existing processes. A process with potential for improvement is the case distribution to pathologists for diagnosis.
Materials and Methods
We propose an approach to workflow modeling and implementation that is open and flexible, and leverages existing standards (BPMN2.0) developed in the context of business process modeling and widely adopted in other domains. This enables efficient implementation and give us access to an existing platform (KIE) that delivers a workflow-engine (jBPM), a rule-engine (Drools), and a constraint satisfaction solver (OptaPlanner). By externalizing the definitions and implementations of tasks within the workflows, we build workflows that are adaptive to the environment and that can incorporate decision models and applications of the desired complexity. We selected case distribution for diagnosis as the first process to optimize and built an application that can be efficiently customized to the needs of each lab with respect to dispatching rules, operational domain model, optimization goals and visual elements.
We implemented a case distribution application that can be deployed within an integrated workflow implementation to optimize the distribution of cases to pathologists for diagnosis. To automatically assign cases to pathologists according to defined policies, the optimization component applies the defined policy model (scoring rules within the domain model). The schedules are generated according to the desired optimization goals, e.g. to improve throughput or turnaround. This application seamlessly connects with relevant systems in the environment, the LIMS and the IMS, in a loosely-coupled standard way through the integration engine to retrieve all needed data about the cases to be visualized and used in the dispatching decisions, and to provide the case assignation information to the IMS.
The optimization of the case distribution to pathologists for diagnosis has been identified in the literature as an important area when aiming at workflow improvements and automation of the processes in the pathology labs. A common theme emphasized by previous research identifying user needs and requirements for efficient digital pathology implementation is the use of standards to support adoption and the seamless integration with all relevant systems in the environment. Within a standards-based workflow-driven approach, we implement a case distribution application that optimizes the case assignation for diagnosis by modeling the local workflows and the requirements of each deployment site. The optimization component applies the local policy models (i.e. business rules, domain models with roles and characteristics, and optimization goals) to propose the most suitable solution for distributing the incoming case load among the available pathologists for diagnosis.
2. Jara-Lazaro A.R., Thamboo T.P., Teh M., Tan P.H., Digital pathology: exploring its applications in diagnostic surgical pathology practice., Pathology 2010, 42(6):512-8.
3. Stathonikos N., Veta M., Huisman A., van Diest P.J., Going fully digital: Perspective of a Dutch academic pathology lab., J Pathol Inform 2013, 4:15.
4. Vodovnik A., Diagnostic time in digital pathology: A comparative study on 400 cases., J Pathol Inform. 2016; 7:4.
5. Rojo M.G., Castro A.M., Gonçalves L., COST Action "EuroTelepath": digital pathology integration in electronic health record, including primary care centres., Diagn Pathol. 2011, 6(Suppl 1):S6.
6. Park S., Pantanowitz L., Parwani A.V., Wells A., Oltvai Z.N., Workflow organization in pathology., Clin Lab Med. 2012, 32(4):601-22.
7. Ho J., Aridor O., Parwani A.V., Use of contextual inquiry to understand anatomic pathology workflow: Implications for digital pathology adoption, J Pathol Inform. 2012; 3:35.
8. Ho J., Aridor O., Glinski D. W., Saylor C. D., Pelletier J. P., Selby D. M., Parwani A. V., Needs and workflow assessment prior to implementation of a digital pathology infrastructure for the US Air Force Medical Service. J Pathol Inform. 2013; 4:32.
9. Ho J., Ahlers S.M., Stratman C., Aridor O., Pantanowitz L., Fine J.L., Kuzmishin J.A., Montalto M.C., Parwani A.V., Can digital pathology result in cost savings? A financial projection for digital pathology implementation at a large integrated health care organization., J Pathol Inform. 2014, 5(1):33.
10. JBoss, (2015), jBPM Business Process Management Suite. Available from: www.jbpm.org [Accessed: 2016-01-01]
11. BPMN Standard, Available from: http://www.bpmn.org.
12. Rojo M.G., Rolón E., Calahorra L., García F.O., Sánchez R.P., Ruiz F., Ballester N., Armenteros M., Rodríguez T., Espartero R.M., Implementation of the Business Process Modelling Notation (BPMN) in the modelling of anatomic pathology processes., Diagn Pathol. 2008, 3(Suppl 1):S22.
13. JBoss (2015), KIE (Knowledge Is Everything) group. Open source projects for business systems automation and management. Available from : http://www.kiegroup.org/.
14. JBoss (2015), Drools Business Rules Management System. Available from: www.drools.org.
15. JBoss, (2015), OptaPlanner constraint satisfaction solver. Available from: www.optaplanner.org [Accessed: 2016-01-01]
16. Juby Joseph Ninan, (2014), Integrating rules and automated planning in business processes, Eindhoven University of Technology, Master Tesis, Available from: http://alexandria.tue.nl/extra1/afstversl/wsk-i/ninan2014.pdf, [Accessed: 2016-01-01].
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
4. In case of virtual slide publication the authors agree to copy the article in a structural modified version to the journal's VS archive.