Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptoms

2026-02-15

AI Summary

This work addresses the limited clinical trust in existing AI models, which often overlook critical symptoms and produce reasoning that lacks alignment with structured clinical thinking, thereby compromising interpretability. To bridge this gap, the paper introduces abductive explanations with formal guarantees into medical AI for the first time, identifying minimal sufficient feature sets that render model decisions transparent and consistent with clinical reasoning. The proposed approach maintains high diagnostic accuracy while significantly enhancing attention to key symptoms and the clinical actionability of explanations. By aligning AI decision-making with established clinical logic, this method establishes a novel framework for trustworthy and interpretable medical artificial intelligence.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of human experts. A key challenge, however, is that AI reasoning frequently diverges from structured clinical frameworks, limiting trust, interpretability, and adoption. Critical symptoms, pivotal for rapid and accurate decision-making, may be overlooked by AI models even when predictions are correct. Existing post hoc explanation methods provide limited transparency and lack formal guarantees. To address this, we leverage formal abductive explanations, which offer consistent, guaranteed reasoning over minimal sufficient feature sets. This enables a clear understanding of AI decision-making and allows alignment with clinical reasoning. Our approach preserves predictive accuracy while providing clinically actionable insights, establishing a robust framework for trustworthy AI in medical diagnosis.

Problem

• AI alignment
• clinical reasoning
• critical symptoms
• interpretability
• trustworthy AI

Innovation

• abductive explanations
• clinical reasoning
• interpretable AI
• critical symptoms
• formal guarantees