The paper introduces LTR-ICD, a ranking‑aware framework that treats automatic ICD coding as a combined classification and ranking problem rather than a pure classification task. By incorporating the order of diagnostic codes, the method improves the identification of high‑priority codes, achieving a 47% accuracy in correctly ranking primary diagnoses versus 20% for existing classifiers. The model also outperforms prior work on micro‑ and macro‑F1 scores, reaching 0.6065 and 0.2904 respectively.
Automatic medical coding assigns ICD codes to clinical notes, but it remains challenging due to long documents, imbalanced label distributions, and diverse terms. These challenges are especially sever...
CoLa-ICD is a knowledge‑enhanced framework designed to improve automatic medical coding of ICD codes in long, imbalanced clinical documents. It enriches ICD labels with external terms, models dependencies among related codes, and strengthens the alignment between label semantics and clinical evidence, particularly for rare codes. Experiments demonstrate that CoLa-ICD achieves state‑of‑the‑art performance in AUC, F1, and P@k, with larger gains in larger and sparser label spaces.
Generative approaches to automatic International Classification of Diseases (ICD) coding use large language models (LLMs) to predict ICD codes from clinical documents. However, original ICD code strin...
arXiv:2608. 00935v1 Announce Type: new Abstract: Electronic Health Records (EHRs) are widely used for clinical risk prediction using machine learning.
arXiv:2608.20887v1 Announce Type: cross Abstract: Automatic Medical Coding (AMC), which assigns standardized International Classification of Diseases (ICD) codes to clinical notes, is essential for m...
arXiv:2410. 15051v3 Announce Type: replace-cross Abstract: Identifying patient diagnoses from hospital discharge letters is essential for large-scale cohort selection and epidemiological research, but traditional supervised approaches require extensive manual annotation, which is often impractical for large textual datasets.
arXiv:2608. 06614v1 Announce Type: cross Abstract: Large-taxonomy retrieval often assumes that the input already expresses the target concept.
The study demonstrates that instruction‑tuning open‑weight large language models (LLMs) with over 500,000 public question‑answer pairs derived from ICD‑10‑GM, ICD‑O‑3, and OPS catalogues markedly improves ICD coding accuracy for German tumor diagnoses. After fine‑tuning, ICD‑10‑GM exact accuracy rose from 1.4–24 % to 41–58 %, and partial accuracy from 31–74 % to 73–83 %. The approach also eliminated malformed code outputs and achieved 99 % tumor‑diagnosis recognition, with performance scaling positively with model size but narrowing the gap between small and large models.
The paper presents a method for extracting key information from OCR‑digitized clinical reports, addressing challenges posed by heterogeneous documents and noisy OCR output. It introduces an open key space that is iteratively mined, normalized, clustered, and verified to build a canonical key inventory, and defines key coverage as a metric for inventory completeness. Experiments on reports from over 20 hospitals using a 0.2B BERT model show that performance improves steadily with key coverage, achieving high F1 scores when the top 90 keys are covered and outperforming a fine‑tuned Qwen3‑0.6B baseline.
arXiv:2606. 12569v1 Announce Type: cross Abstract: We present EDEN (Emergency Department Electronic Notes), a new and unique large-scale corpus of clinical notes produced in Emergency Departments of Italian hospitals.
This study benchmarks transformer models for Bangla medical named entity recognition (NER), comparing BanglaBERT, multilingual BERT (mBERT), XLM‑RoBERTa, and GPT‑4o mini under zero‑shot and few‑shot prompting. Across a full test set of 3,179 samples, fine‑tuned XLM‑RoBERTa achieves a new state‑of‑the‑art F1‑score of 0.5959, while BanglaBERT lags with 0.4937, suggesting that domain diversity outweighs language specificity. The analysis shows high performance on Medicine and Specialist entities (F1 > 0.83) but lower accuracy on Symptoms (F1 0.4367), and demonstrates that fine‑tuned transformers outperform prompt‑only approaches by a factor of 3.76.
The paper introduces ICD-Deepresearch, a workflow that combines foundation models for electronic health records (EHR) and language models with medical search and ICD dictionaries to forecast future ICD codes for upcoming clinical encounters. It evaluates candidate code transitions by linking patient evidence, external clinical relations, and exact code semantics within a fixed top‑K budget, using SparseEHR for initial priors, GPT‑5 for complementary forecasts, and a final selection step that validates, deduplicates, and ranks candidates. The method achieves patient‑averaged precision/recall of 24.60/35.09% on MIMIC‑III and 25.14/48.32% on MIMIC‑IV, with physicians rating 51–68% of its retrieved documents as useful, outperforming standalone GPT‑5 web search and Medical Deep Research.