Data-Informed Intuition in Hepatology: Integrating Evidence, Context, and Clinical Reasoning

Area of Science:

• Hepatology and Medical Informatics
• Clinical Reasoning and Decision-Making

Background:

• Artificial intelligence and data-driven models are transforming hepatology.
• Expert clinical judgment remains crucial for managing complex, evolving liver diseases.
• Existing models often struggle to integrate numerical data with clinical context.

Purpose of the Study:

• To propose Data-Informed Intuition (DII) as a conceptual framework for clinical reasoning in hepatology.
• To bridge evidence-based medicine with clinical experience and reflective reasoning.
• To enhance clinicians' ability to interpret disease trajectories and manage uncertainty.

Main Methods:

• Conceptual framework development for DII.
• Description of DII through eight axes: time, rate, magnitude, pattern, context, causality, integration, and uncertainty.
• Discussion of DII's application in specific hepatology conditions.

Main Results:

• DII is presented as a trainable skill that improves with data feedback, not guesswork.
• The framework provides a scaffold for integrating data and intuition in clinical reasoning.
• DII aids in adapting predictive scores and handling uncertainty in liver transplantation, HCC, and ALF.

Conclusions:

• DII offers a novel approach to clinical reasoning in hepatology.
• Integrating DII into training and AI systems can foster clinicians with both algorithmic precision and human insight.
• Further research is needed for empirical testing and establishing data-informed professionalism in hepatology.