[0]A Guideline Engine For Knowledge Management (original) (raw)
Related papers
Semantic web framework for knowledge-centric clinical decision support systems
Artificial intelligence in medicine, 2007
Lately, there have been considerable efforts to computerize Clinical Practice Guidelines (CPG) so that they can be executed via Clinical Decision Support Systems (CDSS) at the point of care. We present a Semantic Web framework to both model and execute the knowledge within a CPG to develop knowledge-centric CDSS. Our approach entails knowledge modeling through a synergy between multiple ontologies-i.e. a domain ontology, CPG ontology and patient ontology. We develop decision-rules based on the ontologies, and execute them with a proof engine to derive CPG-based patient specific recommendations. We present a prototype of our CPG-based CDSS to execute the CPG for Follow-up after Treatment for Breast Cancer.
Studies in health …, 2007
Breast cancer follow-up care can be provided by family physicians after specialists complete the primary treatment. Cancer Care Nova Scotia has developed a breast cancer followup Clinical Practice Guideline (CPG) targeting family physicians. In this paper we present a project to computerize and deploy the said CPG in a Breast Cancer Follow-up Decision Support System (BCF-DSS) for use by family physicians in a primary care setting. We present a semantic web approach to model the CPG knowledge and employ a logic-based proof engine to execute the CPG in order to infer patient-specific recommendations. We present the three stages of the development of BCF-DSS-i.e. (a) Computerization of the paperbased CPG for Breast Cancer follow-up; (b) Development of three ontologies-i.e. the Breast Cancer Ontology, the CPG ontology based on the Guideline Element Model (GEM) and a Patient Ontology; and (c) Execution of the Breast Cancer follow-up CPG through a logic-based CPG execution engine.
An ontology-driven agent-based clinical guideline execution engine
Artificial Intelligence in Medicine, 2007
One of the hardest tasks in any healthcare application is the management of knowledge. Organisational information as well as medical concepts should be represented in an appropriate way in order to improve interoperability among existing systems, to allow the implementation of knowledge-based intelligent systems, or to provide high level support to healthcare professionals. This paper proposes the inclusion of an especially designed ontology into an agent-based medical platform called HeCaSe2. The ontology has been constructed as an external resource, allowing agents to coordinate complex activities defined in any clinical guideline.
Ontology-driven execution of clinical guidelines
2011
Clinical guidelines (CG) contain general descriptions, defined by health care organisations, of the way in which a particular pathology should be treated. Their adoption in daily care offers several benefits to both patients and practitioners, such as the standardisation of the delivered care and the reduction of errors, but, at the same time, there are several issues that limit their application.
AVICENA, ontology for the design of executable clinical practice guidelines
2006
Clinical practice guidelines (CPG) are increasingly more demanded as a necessary tool in the supply of health care. In spite of their continuous evolution and spreading, their usage in the context of the new information technologies is still not enough developed. There is much work to be done in the area of execution of CPG, and, consequently, it is difficult to find repositories of formal and executable CPG. The project AVICENA is a new proposal of an ontology for the modelling of executable guidelines, that (1) creates new ways for the representation of clinical knowledge and (2) allows the management of the dynamics of health-related processes.
An Ontology-Driven Approach to Clinical Evidence Modelling Implementing Clinical Prediction Rules
IGI Global eBooks, 2013
Diagnostic error is a major threat to patient safety in the context of the primary care setting. Evidencebased medicine has been advocated as one part of a solution. The ability to effectively apply evidence-based medicine implies the use of information systems by providing efficient access to the latest peer-reviewed evidence-based information sources. A fundamental challenge in applying information technology to a diagnostic clinical domain is how to formally represent known clinical knowledge as part of an underlying evidence repository. Clinical prediction rules (CPRs) can provide the basis for a formal representation of knowledge. The TRANSFoRm project defines the architectural components required to deliver a solution by providing an ontology driven clinical evidence service to support provision of diagnostic tools, designed to be maintained and updated from electronic sources of research data, to assist primary care clinicians during the patient consultation through delivery of up to date evidence based diagnostic rules. www.igi-global.com/chapter/informatics-and-socio-technical-challenges-when-designingsolutions-for-integrated-ecare/111378?camid=4v1a
medRxiv (Cold Spring Harbor Laboratory), 2022
Objective: Clinical decision support systems (CDSS) have a critical role in improving the quality and safety of health care delivery. CDSS rules direct the behavior of CDSS. However, the CDSS rules have not been routinely shared and reused, and ontology can promote the reusing of CDSS rules. We systematically screened literature to elaborate on the current status of ontology applied in CDSS rule management. Methods: We searched PubMed, the Association for Computing Machinery (ACM) Digital Library, and the Nursing & Allied Health Database for publications focusing on ontology, clinical decision support, and rules. Grounded theory and PRISMA 2020 guidelines were followed. One author started the screening and literature analysis, and two authors validated the processes and results. Inclusion and exclusion criteria were developed and refined iteratively. Results: Among 81 included publications, the identified CDSS were mainly applied to managing chronic conditions, alerts for medication prescriptions, reminders for immunizations and preventive services, diagnoses, and treatment recommendations. The CDSS rules were presented in Semantic Web Rule Language, Jess, or Jena formats. Despite ontology was used to supply medical knowledge, CDSS rules, and terminologies to CDSS, ontology has not been used in CDSS rule management. Conclusions: Although ontology can facilitate the reuse, management, and maintenance of CDSS rules, CDSS ontology remains unavailable indicating that more efforts are needed to improve the reusability and interoperability of CDSS rules. .
AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, 2006
We present an approach and architecture for implementing scalable and maintainable clinical decision support at the Partners HealthCare System. The architecture integrates a business rules engine that executes declarative if-then rules stored in a rule-base referencing objects and methods in a business object model. The rules engine executes object methods by invoking services implemented on the clinical data repository. Specialized inferences that support classification of data and instances into classes are identified and an approach to implement these inferences using an OWL based ontology engine is presented. Alternative representations of these specialized inferences as if-then rules or OWL axioms are explored and their impact on the scalability and maintenance of the system is presented. Architectural alternatives for integration of clinical decision support functionality with the invoking application and the underlying clinical data repository; and their associated trade-offs...
Guideline formalization and knowledge representation for clinical decision support
The prevalence of situations of medical error and defensive medicine in healthcare institutions is a great concern of the medical community. Clinical Practice Guidelines are regarded by most researchers as a way to mitigate these occurrences; however, there is a need to make them interactive, easier to update and to deploy. This paper provides a