# Automated clinical coding using off-the-shelf large language models

arXiv: https://arxiv.org/abs/2310.06552 · HTML: https://mlsanity.com/paper/2310.06552/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 10 Oct 2023.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [PLM-ICD: Automatic ICD Coding with Pretrained Language Models](https://mlsanity.com/paper/2207.05289/) (2022)
- [Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study](https://mlsanity.com/paper/2304.10909/) (2023)
- [Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding](https://mlsanity.com/paper/2210.03304/) (2022)
- [Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs](https://mlsanity.com/paper/2010.07459/) (2020)

## Built on by (most cited first, 14 of 14)

- [SPEER: Sentence-Level Planning of Long Clinical Summaries via Embedded Entity Retrieval](https://mlsanity.com/paper/2401.02369/) (2024)
- [Evaluation of General Large Language Models in Contextually Assessing Semantic Concepts Extracted from Adult Critical Care Electronic Health Record Notes](https://mlsanity.com/paper/2401.13588/) (2024)
- [MedGellan: LLM-Generated Medical Guidance to Support Physicians](https://mlsanity.com/paper/2507.04431/) (2025)
- [KREL: Automatic Medical Coding via Knowledge-Guided Reasoning over Clinical Evidence with LLMs](https://mlsanity.com/paper/2608.20887/) (2026)
- [Coding historical causes of death data with Large Language Models](https://mlsanity.com/paper/2405.07560/) (2024)
- [Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank](https://mlsanity.com/paper/2410.23066/) (2024)
- [The NordDRG AI Benchmark for Large Language Models](https://mlsanity.com/paper/2506.13790/) (2025)
- [Predictive Multimodal Modeling of Diagnoses and Treatments in EHR](https://mlsanity.com/paper/2508.11092/) (2025)
- [Model selection meets clinical semantics: Optimizing ICD-10-CM prediction via LLM-as-Judge evaluation, redundancy-aware sampling, and section-aware fine-tuning](https://mlsanity.com/paper/2509.18846/) (2025)
- [Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration](https://mlsanity.com/paper/2509.21530/) (2025)
- [From Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Coding](https://mlsanity.com/paper/2603.15270/) (2026)
- [Secure On-Premise Deployment of Open-Weights Large Language Models in Radiology: An Isolation-First Architecture with Prospective Pilot Evaluation](https://mlsanity.com/paper/2604.22768/) (2026)
- [LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents](https://mlsanity.com/paper/2609.19721/) (2026)
- [Decomposing Error and Style in Automated Clinical Coding](https://mlsanity.com/paper/2609.24877/) (2026)

## Abstract (arXiv)

The task of assigning diagnostic ICD codes to patient hospital admissions is typically performed by expert human coders. Efforts towards automated ICD coding are dominated by supervised deep learning models. However, difficulties in learning to predict the large number of rare codes remain a barrier to adoption in clinical practice. In this work, we leverage off-the-shelf pre-trained generative large language models (LLMs) to develop a practical solution that is suitable for zero-shot and few-shot code assignment, with no need for further task-specific training. Unsupervised pre-training alone does not guarantee precise knowledge of the ICD ontology and specialist clinical coding task, therefore we frame the task as information extraction, providing a description of each coded concept and asking the model to retrieve related mentions. For efficiency, rather than iterating over all codes, we leverage the hierarchical nature of the ICD ontology to sparsely search for relevant codes.