Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codes

About

Clinical coding maps clinical documentation to standardized medical codes, an essential yet time-consuming administrative task that could benefit from automation. Current models on ICD coding are typically optimized for codes from a specific ICD version. However, in reality, ICD systems evolve continuously, and different versions are adopted across time periods and regions. Moreover, ICD coding suffers from the long-tail problem, and rare code performance can be a bottleneck for developing implementable models. We examine whether it is viable to train version-independent models by combining data annotated in different ICD versions, which may help address these challenges. We add ICD-9 data to the training of a modified label-wise attention model for ICD-10 prediction, and find that despite the version mismatch, adding ICD-9 yields a 27% increase in micro F1 for 18K rare ICD codes compared to training on ICD-10 alone. On 8K frequent ICD-10 codes, the multi-version training also substantially improves macro metrics, with far fewer model parameters.

Jinghui Liu, Anthony Nguyen• 2026

Related benchmarks

TaskDatasetResultRank
Automated ICD CodingFrequent ICD-10 codes (test)
AUC-ROC (Micro)99.3
5
Automated ICD CodingMIMIC-IV ICD-10 frequent codes (test)
AUC-ROC (Micro)99.3
5
ICD code predictionMIMIC-IV 26K ICD-10 (test)
AUC-ROC Micro99.7
4
Automated ICD CodingMIMIC-III ICD-9 (frequent codes) (test)
AUC-ROC (Micro)99.2
2
Automated ICD CodingMIMIC-IV ICD-9 (frequent codes) (test)
AUC-ROC (Micro)99.5
2
Showing 5 of 5 rows

Other info

Follow for update