Integration of Clinical Guidelines into Digital Healthcare Tools: Ontological Modeling

Modern clinical guidelines (CGs), serving as the foundation of evidence-based medicine, predominantly exist in text document formats (PDF, DOC). It makes them difficult to automatically process and integrate into Medical Information Systems (MIS) and Clinical Decision Support Systems (CDSS). Physicians are forced to manually search for, analyze, and apply these recommendations, which is time-consuming process and increases the risk of missing important details. To solve this problem, the authors present a practical methodology for converting text-based CGs into machine-readable clinical guidelines through the application of ontological modeling. The key idea consists of a two-level model for their representation. The external level (for physicians) is a hierarchically structured text, familiar and convenient for reading and analysis. Key elements of this structure are “data containers,” which clearly describe observations, interventions, and the conditions for their application. The internal level (for computer systems) is a formalized knowledge graph into which the content of the “containers” is transformed. This graph, built upon medical ontologies and classifiers, can be automatically processed by a CDSS to generate personalized prompts directly during a physician's work with the Electronic Health Record (EHR). The proposed approach, based on ontological modeling, allows for: Firstly, integrating CGs into the physician's workflow (the CDSS can automatically analyze patient data and suggest relevant recommendations). Secondly, enhancing treatment personalization through the automatic analysis of multiple individual patient parameters during decision-making. Thirdly, facilitating navigation through CGs, as the structured format simplifies the search for needed information and understanding of the relationships between different recommendations. Fourthly, ensuring knowledge relevance (the process of updating machinereadable CGs when new guideline versions appear can be largely automated). The proposed methodology has been successfully tested on relevant CGs in cardiology, and a CDSS prototype was implemented on the IACPaaS cloud platform. Converting CGs into a machine-readable format is a strategic step from a digital document archive to intelligent assistants that save physician time, reduce error rates, and promote strict adherence to the principles of evidence-based medicine at each patient's bedside. Despite their importance, modern clinical guidelines do not contribute to the automation of clinical activities. They are presented in text formats, such as PDF and DOC, which limits their use in digital healthcare. This lecture presents a methodology for creating machinereadable clinical guidelines (MCG) to integrate them into medical decision support systems and medical information systems. The authors propose a two-level ontological model that includes an external-level ontology, which is a representation of MCGs in the form of hierarchically templated texts for doctors, and an internal-level ontology, which is a formalized knowledge graph for machine processing. The authors use a hybrid approach to create MCGs, combining the creation of structured MCGs by specialists with the use of large language models for formalization.