Explanation-Guided Medical Named Entity Recognition with Stability and Boundary Awareness for Atopic Dermatitis

2026-06-22

AI Summary

This work addresses the limited reliability and robustness of medical named entity recognition (NER) in Chinese clinical texts on atopic dermatitis by proposing an explanation-guided NER framework that integrates stability and boundary awareness. The approach adaptively fuses local and global explanation signals, enhances explanation stability through perturbation analysis, and incorporates a boundary-sensitivity mechanism to improve entity boundary detection. Furthermore, a consistency constraint is designed to effectively integrate trustworthy explanations into model training. Experimental results on a Chinese atopic dermatitis NER dataset demonstrate that the proposed framework significantly improves both recognition performance and explanation robustness, yielding consistent gains across multiple state-of-the-art NER models.

Abstract

Objective: This study aims to improve the reliability and robustness of medical named entity recognition (NER) in Chinese atopic dermatitis (AD) clinical texts through explanation-guided learning. Methods: We propose a stability and boundary-aware explanation-guided NER framework. Perturbation-based analysis is used to evaluate explanation stability and entity boundary sensitivity. An adaptive fusion strategy dynamically combines local and global explanation to generate more reliable token-level explanations. The fused explanation signals are further incorporated into model training through stability, boundary-aware, and consistency constraints. Results: Experiments on Chinese AD NER datasets show that the proposed framework improves explanation robustness and achieves consistent performance gains across multiple NER models. The adaptive fusion strategy also provides more stable explanations and stronger boundary perception than individual explanation methods. Conclusion: The proposed method effectively integrates reliable explanation signals into medical NER training, improving both recognition performance and explanation reliability. The framework provides a practical and generalizable solution for explainable medical NER and offers reliable support for downstream clinical decision-making and medical knowledge applications.

Problem

• Medical Named Entity Recognition
• Atopic Dermatitis
• Explanation Stability
• Boundary Awareness
• Explainable AI

Innovation

• explanation-guided learning
• stability-aware NER
• boundary-awareness
• adaptive explanation fusion
• medical named entity recognition