Automated clinical coding using off-the-shelf large language models
This addresses the challenge of automating diagnostic coding in healthcare, which is currently manual and dominated by supervised models, but it is incremental as it builds on existing LLM capabilities for a specific domain.
The paper tackled the problem of automated clinical coding for ICD codes by using off-the-shelf large language models in a zero-shot or few-shot approach, achieving a practical solution without task-specific training by framing it as information extraction and leveraging the hierarchical ICD ontology for efficient sparse search.
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.