mlsanityData to 7 Oct 2026

Towards Semi-Structured Automatic ICD Coding via Tree-based Contrastive Learning

arXiv 2310.09672 ↗First posted 14 Oct 2023cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Automatic coding of International Classification of Diseases (ICD) is a multi-label text categorization task that involves extracting disease or procedure codes from clinical notes. Despite the application of state-of-the-art natural language processing (NLP) techniques, there are still challenges including limited availability of data due to privacy constraints and the high variability of clinical notes caused by different writing habits of medical professionals and various pathological features of patients. In this work, we investigate the semi-structured nature of clinical notes and propose an automatic algorithm to segment them into sections. To address the variability issues in existing ICD coding models with limited data, we introduce a contrastive pre-training approach on sections using a soft multi-label similarity metric based on tree edit distance. Additionally, we design a masked section training strategy to enable ICD coding models to locate sections related to ICD codes. Extensive experimental results demonstrate that our proposed training strategies effectively enhance the performance of existing ICD coding methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 14 Oct 2023.

Builds on

20 of 33 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2020Longformer: The Long-Document Transformercited by 3,362
  4. 2018Explainable Prediction of Medical Codes from Clinical Textcited by 231
  5. 2019Pre-training of Graph Augmented Transformers for Medication Recommendationcited by 124
  6. 2019ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Networkcited by 73
  7. 2022Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Codingcited by 52
  8. 2022PLM-ICD: Automatic ICD Coding with Pretrained Language Modelscited by 49
  9. 2022Revisiting Transformer-based Models for Long Document Classificationcited by 48
  10. 2020A Label Attention Model for ICD Coding from Clinical Textcited by 47
  11. 2022Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Codingcited by 40
  12. 2021Does the Magic of BERT Apply to Medical Code Assignment? A Quantitative Studycited by 39
8 more
  1. 2017Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignmentcited by 37
  2. 2017Towards Automated ICD Coding Using Deep Learningcited by 35
  3. 2021Collaborative Graph Learning with Auxiliary Text for Temporal Event Prediction in Healthcarecited by 30
  4. 2021Towards BERT-based Automatic ICD Coding: Limitations and Opportunitiescited by 25
  5. 2021Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphscited by 20
  6. 2022Classifying Unstructured Clinical Notes via Automatic Weak Supervisioncited by 7
  7. 2021Rare Disease Identification from Clinical Notes with Ontologies and Weak Supervisioncited by 5
  8. 2021Attention-based Aspect Reasoning for Knowledge Base Question Answering on Clinical Notescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2025TACL: Threshold-Adaptive Curriculum Learning Strategy for Enhancing Medical Text Understandingcited by 2
  2. 2024Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rankcited by 0
  3. 2026Label-Conditioned Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Curriculum-Gated Contrastive Alignmentcited by 0
  4. 2026Knowledge-Guided Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Label-Conditioned Contrastive Alignmentcited by 0