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

TL;DR

This paper introduces a formal abductive explanation framework that aligns AI diagnostic reasoning with clinical reasoning, enhancing interpretability and trust without sacrificing accuracy.

Contribution

It presents a novel abductive explanation method that guarantees consistent reasoning and aligns AI decisions with clinical frameworks, improving trustworthiness.

Findings

Preserves predictive accuracy while providing explanations

Offers formal guarantees for reasoning consistency

Enhances interpretability and clinical alignment

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.