Explanation-Guided Medical Named Entity Recognition with Stability and Boundary Awareness for Atopic Dermatitis
2026-06-22 • Computation and Language
Computation and LanguageArtificial Intelligence
AI summaryⓘ
The authors worked on improving a computer program that finds important medical terms in Chinese clinical texts about atopic dermatitis. They created a new way to teach the program using explanations that pay close attention to how stable these explanations are and how well they detect the start and end of medical terms. Their approach combines different types of explanations and uses them during training to make the program more reliable and accurate. Tests showed that this method helps the program perform better and gives clearer explanations, which can help doctors and researchers trust and use the results more effectively.
Named Entity RecognitionAtopic DermatitisMedical Text MiningExplanation-Guided LearningPerturbation AnalysisToken-Level ExplanationAdaptive FusionModel TrainingBoundary DetectionClinical Decision-Making
Authors
Xueguang Li, Di Lin, Xue Jiang, Yanxi Li, Yugang Chi
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.