用多版本病历编码数据训练模型，显著提升罕见编码预测效果。
Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codes
- 融合ICD-9与ICD-10数据训练，实现版本无关的编码预测。
- 对1.8万种罕见编码，微F1提升27%，频繁编码也获明显改善。
- 参数更少却性能更强，适合医疗编码自动化落地应用。
临床编码将病历文本映射为标准化医疗代码，是重要但耗时的行政任务，自动化可带来显著效益。当前模型通常针对特定ICD版本优化，但现实中ICD系统持续演进，不同地区和时期采用不同版本。此外，编码存在长尾分布问题，罕见编码表现常成为模型实用化的瓶颈。本文探究是否可通过融合不同版本标注的数据，训练出版本无关的模型以应对上述挑战。我们在改进的逐标签注意力模型中加入ICD-9数据，用于训练ICD-10编码预测，发现尽管存在版本差异，使用ICD-9数据使18,000种罕见编码的微F1提升了27%，相比仅用ICD-10训练效果显著。对于8,000种常见编码，多版本训练同样大幅提升宏指标，且模型参数更少。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。