Variance analysis in Task-Time matrix clinical pathways
- Resource Type
- Conference
- Authors
- Yan, Hui; Van Gorp, Pieter; Kaymak, Uzay; Ji, Lei; Lu, Xudong; Chiau, Choo Chiap; Korsten, Hendrikus H. M.; Duan, Huilong
- Source
- 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI) Biomedical & Health Informatics (BHI), 2017 IEEE EMBS International Conference on. :253-256 2017
- Subject
- Bioengineering
Engineering Profession
Logic gates
Electrocardiography
Hospitals
Hidden Markov models
Surgery
Computational modeling
Databases
- Language
Clinical pathways are popular healthcare management tools to standardise care and ensure quality. Measuring pathway conformance and analysing variances gives valuable feedback in the context of care improvement trajectories. The Business Process Model and Notation (BPMN) language and Task-Time matrices are popular ways to model clinical pathways. A key step in variance analysis involves the computation of optimal alignments between the pathway model and patient-specific traces. This paper presents for this step a new algorithm which reduces the time for finding deviations from hours to minutes. A case study on variance analysis is undertaken, where a clinical pathway from the practice and a large set of patients data from an EMR database are used. The results demonstrate that automated variance analysis between BPMN Task-Time models and real-life EMR data is feasible. We also provide meaningful insights for further improvement.