Comprehensive mitigation framework for concurrent application of multiple clinical practice guidelines.

Area of Science:

• Artificial Intelligence in Medicine
• Clinical Decision Support Systems
• Medical Informatics

Background:

• Managing multiple clinical practice guidelines (CPGs) for patients with multiple conditions presents challenges.
• Integrating patient preferences into clinical decision-making is complex.
• Existing clinical decision support systems often struggle with concurrent guideline application.

Purpose of the Study:

• To propose a comprehensive framework for mitigating interactions between multiple CPGs.
• To incorporate patient preferences into the clinical decision-making process.
• To address challenges in concurrent CPG application and preference integration.

Main Methods:

• Developed a first-order logic (FOL) based framework for CPG mitigation.
• Introduced revised, mitigation-oriented representations for CPGs and secondary medical knowledge.
• Implemented a novel mitigation algorithm using actionable graphs, revision operators, and FOL-based patient information.
• Utilized depth-first search, theorem proving, and model finding techniques.

Main Results:

• The framework successfully identifies and addresses interactions between multiple CPGs.
• A management scenario, defining safe and preferred activities, can be established for patients.
• Demonstrated feasibility through a clinical case study involving chronic kidney disease, hypertension, and atrial fibrillation.
• A proof-of-concept clinical decision support system (CDSS) was developed.

Conclusions:

• The proposed framework offers a robust solution for mitigating CPG interactions in multi-morbid patients.
• Incorporating patient preferences leads to more personalized and safer treatment plans.
• The mitigation CDSS simplifies complex logic for clinicians, providing meaningful summaries.