Expanding a First-Order Logic Mitigation Framework to Handle Multimorbid Patient Preferences

Area of Science:

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

Background:

• Multimorbidity presents significant challenges in healthcare delivery.
• Integrating patient preferences into care is crucial for personalized medicine.
• Existing frameworks for managing multiple clinical practice guidelines (CPGs) need enhancement.

Purpose of the Study:

• To extend a first-order logic framework for representing and applying CPGs to multimorbid patients.
• To incorporate required and desired revision types from secondary knowledge sources.
• To expand the mitigation algorithm for handling CPG conflicts based on revision type.

Main Methods:

• Utilized first-order logic for representing CPGs and their interactions.
• Developed extended revision operators to support different revision types.
• Enhanced a mitigation algorithm to apply revisions based on their classification.
• Illustrated the framework with a case study of a patient with cardiac artery disease and deep vein thrombosis.

Main Results:

• The enhanced framework accommodates diverse revision types (required/desired).
• The expanded mitigation algorithm effectively applies type-specific revisions.
• Demonstrated successful application in a complex multimorbidity case study.

Conclusions:

• The extended framework improves the management of CPGs in multimorbidity.
• This approach supports personalized and participatory medicine by incorporating patient-relevant revisions.
• The methodology offers a robust solution for clinical decision support in complex patient cases.