Workflow-driven clinical decision support for personalized oncology.

Area of Science:

• Oncology
• Medical Informatics
• Clinical Decision Support Systems

Background:

• Clinical Decision Support (CDS) in oncology aims to manage complexity and bridge the research-practice gap, but faces limited clinical uptake.
• Existing oncology CDS solutions struggle with complex patient stratification, personalized treatment decisions, and rapidly evolving therapeutic knowledge.

Purpose of the Study:

• To propose a novel framework for efficient implementation of meaningful CDS in oncology.
• To address the limitations of current CDS by incorporating diverse clinical knowledge models and leveraging real-world data.

Main Methods:

• Developed a framework integrating literature-based and p-medicine project-derived clinical knowledge models.
• Designed an architecture extending the CDS framework with workflow functionality to embed clinical models within clinical processes.
• Ensured the framework supports collaboration and reuse of models within the biomedical community.

Main Results:

• The p-medicine CDS framework enables comprehensive solutions by leveraging the latest domain knowledge.
• Integrated clinical models and workflow execution ensure recommendations are delivered at the point of need.
• The framework supports complex decision-making and adapts to the dynamic nature of oncology.

Conclusions:

• The presented CDS framework and its implementation in p-medicine effectively support complex clinical decisions.
• By embedding clinical knowledge in workflows, the solution enhances decision processes and knowledge exploitation.
• This approach aims to increase CDS adoption and improve patient management in oncology.