PHR Ontology and Knowledge Modeling
James Fleck: Anticancerweb 23(12), 2020
The Personal Health Record (PHR) consists of translating all the patient's clinical data into an electronic medical record, fully available for universal patient use. The data will be recovered on different devices, such as laptops, tablets and cell phones, using a personal username (ONU) and a strong password (PW). Other security strategies used today would be introduced to provide additional confidentiality. The development of a specific PHR ontology will be based on Ontology Web Language (OWL), previously described 1. The PHR ontology provides specific and explicit concept definitions and the relationship between concepts. PHR ontology, using formal semantics, will support knowledge modeling of all patient clinical data in well-designed software. Data will be uploaded only by the attending physician and made available to the patient, on real time. With the patient's consent, the data can be shared with other doctors and healthcare institutions. PHR ontology is an abstract representation of the domain of health knowledge, capable of reasoning and useful not only for clinical practice, but also for clinical research. The representation of electronic clinical date will result from the combination of one standardized information model with Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT) 2. The BMC Medical Informatics and Decision Making recently published a proposed clinical data encoding methodology3, which could be easily translated into a PHR ontology.
Fortunately, a background has already been built for the development of ontologies4. Before the turn of the century, Mariano Fernández, Asunción Gómez-Pérez and Natalia Juristo from the Laboratorio de Inteligencia Artificial, Facultad de Informática, Universidad Politécnica de Madrid have described an elegant methodology do build ontologies from the scratch. The first steps are specification and knowledge acquisition. A detailed explanation of PHR ontology specification is available in the Global e-PHR website ( www.ephr.org )11. The website describes its domain, purpose, scope and level of formality. Knowledge acquisition is supported by formal medical literature and level of evidence. A Unified Medical Language System (UMLS)5 was introduced by the US National Library of Medicine, labeling biomedical domain and creating a semantic network, where permission for use can be obtained. Global e-PHR problem-oriented medical record methodology will assist in uploading well-structured data. At the conceptualization step, the domain knowledge will be structured, based on a well-defined glossary terms, their relationship and conceptual hierarchy. The use of UMLS source vocabularies to build the PHR ontology is represented below in association with the proposed Global e-PHR model. A platform must be used to integrate well-recognized meta-ontologies. At the implementation phase, PHR ontology should provide a lexical and syntactic analyzer, a translator, an editor, a browser, a searcher, an evaluator and an automatic maintainer. Finally, a formal language capable of being understood by humans and machines is created, being applicable for clinical assistance and research.
1. Bechhofer S. (2009) OWL: Web Ontology Language. In: LIU L., ÖZSU M.T. (eds) Encyclopedia of Database Systems. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-39940-9_1073
2. Systematized Nomenclature of Medicine – Clinical Terms (SNOMED-CT): https://www.snomed.org
3. Shaker El-Sappagh, Francesco Franda, Farman Ali and Kyung-Sup Kwak: SNOMED CT standard ontology based on the ontology for general medical science, BMC Medical Informatics and Decision Making 18:76, 2018(https://doi.org/10.1186/s12911-018-0651-5)
4. Mariano Fernández, Asunción Gómez-López and Natalia Juristo: Methontology: from ontological art towards ontological engineering. 1997.
5. Unified Medical Language System (UMLS): https://www.nlm.nih.gov/research/umls/
6. International Statistical Classification of Diseases and Related Health Problems (ICD): https://www.who.int/standards/classifications/classification-of-diseases
7. Current Procedural Terminology (CPT®) International: https://www.ama-assn.org/practice-management/cpt/current-procedural-terminology-cpt-international
8. Stuart J Nelson, Kelly Zeng, John Kilbourne, Tammy Powell, Robin Moore: Normalized names for clinical drugs: Rx Norm at 6 years, J Am Med Inform Ass 18:441-448, 2011. doi:10.1136/amiajnl-2011-000116
9. National Drug File Reference Terminology (NDF-RT) https://healthdata.gov/dataset/national-drug-file-reference-terminology-api
10. Logical Observation Identifier Names and Codes (LOINC): https://loinc.org
11. James Fleck: Global e-PHR – Personal Health Record (www.ephr.org)
12. Photo by Greg Rakozy on Unsplash