Rule-augmented constraint learning for semantic error detection in MIMIC-III knowledge graph

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not specified in abstract

• Primary Outcome: Effective preservation of clinically meaningful rules through rule filtering based constraint learning

• Nnt Or Sensitivity: Reliable value groupings achieved through clustering-based method for numeric data

• Confidence Interval: Not reported

Clinical Application

High - framework appears scalable and interpretable for clinical implementation Relevant for Australian digital health initiatives, particularly My Health Record data quality assurance and clinical decision support system development under TGA software classification guidelines Healthcare systems using structured clinical data and knowledge graphs for decision support

Abstract

High-quality, error-free data is essential for developing reliable data-driven models, particularly in clinical decision support systems where inaccurate predictions can have serious consequences. While KGs offer a structured and semantically rich representation for clinical data, ensuring their consistency and correctness remains a challenge. Existing rule mining techniques provide solutions for the automatic extraction of logical constraints from KGs, but they often produce redundant or clinically irrelevant rules, especially when dealing with numeric or categorical literals such as age or lab values. KG constraints-rules intended to capture implausible or conflicting facts in the KG-can be used to spot semantic errors: facts that might conform to the underlying schema but contradict domain knowledge. In this work, we propose a novel framework for constraint learning in clinical KGs that identifies and transforms high-confidence rules into clinically plausible constraints. We propose two approaches, based on class disjointness and literal clustering combined with rule mining. We validate the clinical relevance of these generated rules using expert-curated constraints and large language models (LLMs). The results on the MIMIC-III clinical dataset show that rule filtering based constraint learning effectively preserves clinically meaningful rules that align with established medical knowledge. For numeric data, we achieve reliable value groupings through our clustering-based method, and the rules derived from these groupings were validated by LLMs. Their outputs confirm the clinical relevance of a portion of those discovered rules. By providing interpretable and scalable solutions to semantic inconsistencies in KGs, this study contributes to increasing the KG trustworthiness and its clinical usability.

References

1. 1.Noben, Ö., Durukan Kılıç, Ö., Rienstra, T., Dumontier, M., & Celebi, R. (2026). Rule-augmented constraint learning for semantic error detection in MIMIC-III knowledge graph. International Journal of Medical Informatics, 106297. https://doi.org/10.1016/j.ijmedinf.2026.106297