Medical coding is essential for standardizing clinical data and communication but is often time-consuming and prone to errors. Traditional Natural Language Processing (NLP) methods struggle with automating coding due to the large label space, lengthy text inputs, and the absence of supporting evidence annotations that justify code selection. Recent advancements in Generative Artificial Intelligence (AI) offer promising solutions to these challenges. In this work, we introduce MedCodER, a Generative AI framework for automatic medical coding that leverages extraction, retrieval, and re-ranking techniques as core components. MedCodER achieves a micro-F1 score of 0.60 on International Classification of Diseases (ICD) code prediction, significantly outperforming state-of-the-art methods. Additionally, we present a new dataset containing medical records annotated with disease diagnoses, ICD codes, and supporting evidence texts (https://doi.org/10.5281/zenodo.13308316). Ablation tests confirm that MedCodER's performance depends on the integration of each of its aforementioned components, as performance declines when these components are evaluated in isolation.

翻译：医疗编码对于标准化临床数据和通信至关重要，但通常耗时且容易出错。传统的自然语言处理（NLP）方法由于标签空间庞大、文本输入冗长以及缺乏支持代码选择的证据标注，在实现编码自动化方面面临困难。生成式人工智能（AI）的最新进展为应对这些挑战提供了有前景的解决方案。在本工作中，我们介绍了MedCodER，一个用于自动医疗编码的生成式AI框架，它利用提取、检索和重排序技术作为核心组件。MedCodER在国际疾病分类（ICD）代码预测上取得了0.60的微平均F1分数，显著优于现有最先进方法。此外，我们提出了一个新的数据集，其中包含标注了疾病诊断、ICD代码以及支持证据文本的医疗记录（https://doi.org/10.5281/zenodo.13308316）。消融实验证实，MedCodER的性能依赖于其上述各个组件的集成，当这些组件被单独评估时，性能会下降。