Analyzing interactions on combining multiple clinical guidelines

Area of Science:

• Health Informatics
• Clinical Decision Support
• Multimorbidity Management

Background:

• Managing patients with multiple health conditions (multimorbidity) presents challenges in coordinating care and avoiding conflicting recommendations.
• Existing approaches for identifying interactions among clinical recommendations often lack reusability and scalability.
• Investigating these features is crucial for effective multimorbidity management.

Purpose of the Study:

• To present a novel approach for detecting interactions among clinical recommendations from various guidelines.
• To enhance the detection of interactions by extending a knowledge representation model (TMR).
• To provide a systematic analysis of relevant interactions in the context of multimorbidity.

Main Methods:

• Development of a rule-based system for identifying potential interactions between clinical recommendations.
• Extension of the Temporal Medical Record (TMR) knowledge representation model to improve interaction detection.
• Evaluation of the approach through a case study involving breast cancer patient rehabilitation.

Main Results:

• The proposed approach successfully identifies potential interactions among clinical recommendations.
• The extended TMR model enhances the accuracy and scope of interaction detection.
• The case study demonstrated the approach's promise in supporting expert decision-making.

Conclusions:

• The developed approach offers a reusable and scalable solution for detecting recommendation interactions in multimorbidity.
• This method can significantly aid healthcare professionals in managing complex patient cases.
• Further research and expert collaboration are essential for refining and implementing this approach in clinical practice.