mlsanityData to 14 Oct 2026

Structured Information Matters: Explainable ICD Coding with Patient-Level Knowledge Graphs

arXiv 2509.09699 ↗First posted 4 Sep 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Mapping clinical documents to standardised clinical vocabularies is an important task, as it provides structured data for information retrieval and analysis, which is essential to clinical research, hospital administration and improving patient care. However, manual coding is both difficult and time-consuming, making it impractical at scale. Automated coding can potentially alleviate this burden, improving the availability and accuracy of structured clinical data. The task is difficult to automate, as it requires mapping to high-dimensional and long-tailed target spaces, such as the International Classification of Diseases (ICD). While external knowledge sources have been readily utilised to enhance output code representation, the use of external resources for representing the input documents has been underexplored. In this work, we compute a structured representation of the input documents, making use of document-level knowledge graphs (KGs) that provide a comprehensive structured view of a patient's condition. The resulting knowledge graph efficiently represents the patient-centred input documents with 23% of the original text while retaining 90% of the information. We assess the effectiveness of this graph for automated ICD-9 coding by integrating it into the state-of-the-art ICD coding architecture PLM-ICD. Our experiments yield improved Macro-F1 scores by up to 3.20% on popular benchmarks, while improving training efficiency. We attribute this improvement to different types of entities and relationships in the KG, and demonstrate the improved explainability potential of the approach over the text-only baseline.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 46 references that are in the map. First posted on arXiv 4 Sep 2025.

Builds on

19 of 46 references.

References · 19

  1. 2017Graph Attention Networkscited by 8,923
  2. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  3. 2015Gated Graph Sequence Neural Networkscited by 796
  4. 2018Explainable Prediction of Medical Codes from Clinical Textcited by 234
  5. 2019ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Networkcited by 73
  6. 2022Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Codingcited by 53
  7. 2023Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Studycited by 49
  8. 2020A Label Attention Model for ICD Coding from Clinical Textcited by 48
  9. 2020An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labelscited by 44
  10. 2022Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Codingcited by 40
  11. 2021Does the Magic of BERT Apply to Medical Code Assignment? A Quantitative Studycited by 39
  12. 2020Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisationcited by 38
7 more
  1. 2022A Unified Review of Deep Learning for Automated Medical Codingcited by 26
  2. 2020Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphscited by 19
  3. 2021Description-based Label Attention Classifier for Explainable ICD-9 Classificationcited by 12
  4. 2022ICDBigBird: A Contextual Embedding Model for ICD Code Classificationcited by 10
  5. 2023A Two-Stage Decoder for Efficient ICD Codingcited by 9
  6. 2022This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Textcited by 6
  7. 2021Multitask Recalibrated Aggregation Network for Medical Code Predictioncited by 5

Built on by

Not cited yet.