大型语言模型在提供工具的情况下是优秀的医学编码员
Large language models are good medical coders, if provided with tools
AI总结:
本研究提出两阶段检索-排序系统用于自动化ICD-10-CM编码,在100个单一术语病例上达到100%准确率,远超普通LLM的6%,凸显检索方法在医学编码中的价值。
摘要:
本研究提出了一种新颖的两阶段检索-排序系统,用于自动化ICD-10-CM医学编码,并将其性能与普通大型语言模型(LLM)方法进行了比较。在包含100个单一术语医学状况的数据集上评估这两种系统时,检索-排序系统在预测正确的ICD-10-CM代码方面达到了100%的准确率,显著优于普通LLM(GPT-3.5-turbo),后者仅达到6%的准确率。我们的分析表明,检索-排序系统在处理不同专科的各种医学术语方面具有卓越的精确性。尽管这些结果令人鼓舞,但我们承认使用简化输入的局限性,并需要在更复杂、更现实的医学案例上进行进一步测试。这项研究为持续提高医学编码效率和准确性的努力做出了贡献,强调了基于检索的方法的重要性。
英文摘要:
This study presents a novel two-stage Retrieve-Rank system for automated ICD-10-CM medical coding, comparing its performance against a Vanilla Large Language Model (LLM) approach. Evaluating both systems on a dataset of 100 single-term medical conditions, the Retrieve-Rank system achieved 100% accuracy in predicting correct ICD-10-CM codes, significantly outperforming the Vanilla LLM (GPT-3.5-turbo), which achieved only 6% accuracy. Our analysis demonstrates the Retrieve-Rank system's superior precision in handling various medical terms across different specialties. While these results are promising, we acknowledge the limitations of using simplified inputs and the need for further testing on more complex, realistic medical cases. This research contributes to the ongoing effort to improve the efficiency and accuracy of medical coding, highlighting the importance of retrieval-based approaches.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。