Formal abductive explanations are applied to AI diagnostic models to produce minimal sufficient symptom sets that align with clinical reasoning while preserving predictive accuracy.
On the failings of Shapley values for explainability
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptoms
Formal abductive explanations are applied to AI diagnostic models to produce minimal sufficient symptom sets that align with clinical reasoning while preserving predictive accuracy.
- Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images