Researcher: Prof. Mor Peleg
Background
Clinical practice guidelines provide evidence-based recommendations on how to manage disease. They aim to increase the quality of care, reduce unjustified practice variation, and save costs. In order for them to be effective, clinical guidelines need to be integrated with the care flow and provide patient-specific advice when and where needed. As such, representing the guidelines in a computer-interpretable format enables use of a decision-support system that is based on guideline knowledge paired with electronic patient data. Such a system can provide patient-specific and personalized recommendations to clinicians and patients anytime, anywhere.
Computer-interpretable clinical guidelines (CIGs)
Prof. Mor Peleg, associate professor at the University of Haifa’s Department of Information Systems, uses task-network models to represent the logic of clinical guidelines. The computer-interpretable clinical guidelines (CIGs) use arguments for and against decision candidates (e.g., possible interventions or tests); and an informed decision about indicated candidates is assisted by instantiating the models for particular patients (against their electronic health records). Data is supplemented with ontologies that define relationships between classes of diseases and drugs, which may suggest ways to augment guideline knowledge.
Prof. Peleg is applying these models to develop mobile applications for patients that link CIGs to various data sources, such as hospital health records and wearable sensors.
More about this work can be found at: Mor Peleg. Computer-interpretable Clinical Guidelines: a Methodological Review. Journal of Biomedical Informatics Vol. 46 No. 4, pp. 744–763, 2013.
For more recent work please see: http://mis.hevra.haifa.ac.il/~morpeleg/
Research Status
Currently, Prof. Peleg is working on CIG-related research:
• Integrating recommendations derived from different CIGs that apply to patients with multi-morbidities, to detect and mitigate interactions using a goal-based approach
• Increasing patient compliance for behavioral change, using psychological interventions and behavioral economics incentives
• Personalization of CIGs for patients
• Mobile health applications of CIGs designed to involve and empower patients to self-manage their health
• Mining evidence from patient-reported outcomes
• Learning how to evolve guideline recommendations by mining data on patient treatments and outcomes
• Combining argumentation-based reasoning with OWL-based inference
Related pages
Mor Peleg, Prof. - researcher page
