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

arXiv: https://arxiv.org/abs/2602.13985 · HTML: https://mlsanity.com/paper/2602.13985/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 48 references that are in the map.
- First posted on arXiv 15 Feb 2026.

## Builds on (most cited first, 10 of 10)

- [On The Reasons Behind Decisions](https://mlsanity.com/paper/2002.09284/) (2020)
- [A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME](https://mlsanity.com/paper/2305.02012/) (2023)
- [Superhuman performance of a large language model on the reasoning tasks of a physician](https://mlsanity.com/paper/2412.10849/) (2024)
- [Eliminating The Impossible, Whatever Remains Must Be True](https://mlsanity.com/paper/2206.09551/) (2022)
- [Explainability is NOT a Game](https://mlsanity.com/paper/2307.07514/) (2023)
- [Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?](https://mlsanity.com/paper/2203.06487/) (2022)
- [Delivering Inflated Explanations](https://mlsanity.com/paper/2306.15272/) (2023)
- [Disproving XAI Myths with Formal Methods -- Initial Results](https://mlsanity.com/paper/2306.01744/) (2023)
- [On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systems](https://mlsanity.com/paper/2509.25662/) (2025)
- [From Explainability to Action: A Generative Operational Framework for Integrating XAI in Clinical Mental Health Screening](https://mlsanity.com/paper/2510.13828/) (2025)

## Abstract (arXiv)

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.