A Health eLearning Ontology and Procedural Reasoning Approach for Developing Personalized Courses to Teach Patients...

Area of Science:

• Medical Education
• Health Informatics
• Artificial Intelligence in Healthcare

Background:

• Patient education is crucial for treatment adherence and health outcomes.
• Current educational materials often lack personalization, leading to suboptimal patient understanding.
• Intelligent Tutoring Systems (ITSs) offer a model for adaptive learning but require adaptation for healthcare.

Purpose of the Study:

• To propose a methodological framework for developing personalized patient education courses.
• To improve patient comprehension of medical conditions and prescribed treatments.
• To enhance patient preparedness for medical consultations and adherence to care plans.

Main Methods:

• Development of a methodological framework integrating an eLearning ontology with procedural reasoning.
• Personalization of courses across four patient axes: condition/treatment, comprehension level, VARK learning style, and Bloom's taxonomy level.
• Operationalization of the framework using precompiled plans for diverse disease conditions.
• Validation through two use cases: anticoagulation therapy and lower back pain management.

Main Results:

• The framework effectively represents content and derives personalized courses for specific medical conditions.
• Personalized courses demonstrated potential to improve patient understanding and engagement.
• Qualitative and quantitative data indicated acceptability of the framework among patients and practitioners.

Conclusions:

• The proposed framework provides a robust method for creating personalized patient education.
• Tailored educational content can significantly improve patient understanding, potentially leading to better health outcomes.
• The framework is adaptable and validated for practical application in clinical settings.