A modular knowledge base for the follow-up of clinical protocols

Area of Science:

• Knowledge Engineering
• Medical Informatics
• Artificial Intelligence in Medicine

Background:

• Clinical therapy protocols generate highly structured knowledge.
• Existing knowledge representation methods may not fully capture temporal aspects of medical data.

Purpose of the Study:

• To propose a novel knowledge representation theory for clinical domains.
• To develop a framework for expert systems in medical therapy and follow-up.

Main Methods:

• Utilizing a homogeneous and modular knowledge representation theory.
• Introducing the concept of Generalized Magnitude, inspired by physical magnitudes.
• Incorporating temporal extensions for therapy and follow-up plans.

Main Results:

• The Generalized Magnitudes scheme effectively represents structured medical knowledge.
• Temporal extensions facilitate the management of time-specified medical problems.
• The approach supports the creation of advisory expert systems.

Conclusions:

• Generalized Magnitudes offer a robust framework for medical knowledge engineering.
• This theory enhances the development of intelligent systems for patient care.
• The modular and temporal aspects are key to its applicability in clinical settings.