RuCCoD: Towards Automated ICD Coding in Russian
Not on the map. Why?
Abstract (arXiv)
This study investigates the feasibility of automating clinical coding in Russian, a language with limited biomedical resources. We present a new dataset for ICD coding, which includes diagnosis fields from electronic health records (EHRs) annotated with over 10,000 entities and more than 1,500 unique ICD codes. This dataset serves as a benchmark for several state-of-the-art models, including BERT, LLaMA with LoRA, and RAG, with additional experiments examining transfer learning across domains (from PubMed abstracts to medical diagnosis) and terminologies (from UMLS concepts to ICD codes). We then apply the best-performing model to label an in-house EHR dataset containing patient histories from 2017 to 2021. Our experiments, conducted on a carefully curated test set, demonstrate that training with the automated predicted codes leads to a significant improvement in accuracy compared to manually annotated data from physicians. We believe our findings offer valuable insights into the potential for automating clinical coding in resource-limited languages like Russian, which could enhance clinical efficiency and data accuracy in these contexts. Our code and dataset are available at https://github.com/auto-icd-coding/ruccod.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 91 references that are in the map. First posted on arXiv 28 Feb 2025.
Builds on
42 of 91 references.
References · 42
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2020Longformer: The Long-Document Transformercited by 3,413
- 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
- 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
- 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 1,009
- 2019Publicly Available Clinical BERT Embeddingscited by 1,002
- 2020Self-Alignment Pretraining for Biomedical Entity Representationscited by 237
- 2018Explainable Prediction of Medical Codes from Clinical Textcited by 234
30 more
- 2015Doctor AI: Predicting Clinical Events via Recurrent Neural Networkscited by 208
- 2019Pre-training of Graph Augmented Transformers for Medication Recommendationcited by 127
- 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
- 2019ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Networkcited by 73
- 2020Biomedical Entity Representations with Synonym Marginalizationcited by 61
- 2020CODER: Knowledge infused cross-lingual medical term embedding for term normalizationcited by 55
- 2022Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Codingcited by 53
- 2022PLM-ICD: Automatic ICD Coding with Pretrained Language Modelscited by 49
- 2023Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Studycited by 49
- 2020A Label Attention Model for ICD Coding from Clinical Textcited by 48
- 2018Multimodal Machine Learning for Automated ICD Codingcited by 41
- 2022Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Codingcited by 40
- 2021Does the Magic of BERT Apply to Medical Code Assignment? A Quantitative Studycited by 39
- 2017Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignmentcited by 37
- 2020BERT-XML: Large Scale Automated ICD Coding Using BERT Pretrainingcited by 37
- 2017Towards Automated ICD Coding Using Deep Learningcited by 35
- 2021Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linkingcited by 28
- 2021Towards BERT-based Automatic ICD Coding: Limitations and Opportunitiescited by 25
- 2022Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learningcited by 24
- 2021Read, Attend, and Code: Pushing the Limits of Medical Codes Prediction from Clinical Notes by Machinescited by 23
- 2021Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphscited by 20
- 2024MedCodER: A Generative AI Assistant for Medical Codingcited by 11
- 2022NEREL-BIO: A Dataset of Biomedical Abstracts Annotated with Nested Named Entitiescited by 10
- 2024Large language models are good medical coders, if provided with toolscited by 8
- 2025Memorize and Rank: Elevating Large Language Models for Clinical Diagnosis Predictioncited by 8
- 2022Classifying Unstructured Clinical Notes via Automatic Weak Supervisioncited by 7
- 2022RuBioRoBERTa: a pre-trained biomedical language model for Russian language biomedical text miningcited by 6
- 2021Rare Disease Identification from Clinical Notes with Ontologies and Weak Supervisioncited by 5
- 2024Next Visit Diagnosis Prediction via Medical Code-Centric Multimodal Contrastive EHR Modelling with Hierarchical Regularisationcited by 5
- 2023Self-training Strategies for Sentiment Analysis: An Empirical Studycited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.