CoLa-ICD: A Knowledge-Enhanced Framework for Long-Tail Automated Medical Coding
2026-08-31 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created CoLa-ICD, a system to help computers automatically assign ICD medical codes to long clinical notes. Their system uses extra information about the codes, understands relationships between similar codes, and better matches medical terms with the right codes. This helps especially with rare codes that usually have few examples and can be confused with others. Tests showed that CoLa-ICD works better than previous methods, especially when there are many codes or when data is sparse.
ICD codesmedical codinglong-tail predictionlabel imbalanceclinical notessemantic alignmentlabel dependenciesmachine learning
Authors
Yihang Cheng, Veronica Liesaputra, Andrew Trotman
Abstract
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 severe for rare codes, which have limited training instances and are easily confused with semantically similar labels. We introduce CoLa-ICD, a knowledge-enhanced framework for long-tail prediction. CoLa-ICD enriches ICD labels with external terms, models dependencies among related codes, and learns stronger alignment between label semantics and clinical evidence for long-tail prediction. Experiments show that CoLa-ICD improves long-tail prediction with larger gains in larger and sparser label spaces and achieves state-of-the-art performance in AUC, F1, and P@k. Our code is available at https://github.com/youwillbethebest/Cola-ICD.