arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.01515cs.CLcs.LG
收藏

根据巴西-葡萄牙临床记录预测多个ICD-10代码

Predicting Multiple ICD-10 Codes from Brazilian-Portuguese Clinical Notes

Federal University of Santa Catarina(圣卡塔琳娜联邦大学);Healthcare(3778医疗);Syrian-Lebanese Hospital(叙利亚-黎巴嫩医院)

Arthur D. Reys, Danilo Silva, Daniel Severo, Saulo Pedro, Marcia M. de Souza e Sá, Guilherme A. C. Salgado

摘要:

从电子临床记录中编码ICD是一个人工、耗时且昂贵的过程。然而,代码分配对于计费目的和数据库组织来说是一项重要任务。虽然许多作品已经研究了使用机器学习技术从自由文本自动ICD编码的问题,但大多数使用英语记录,特别是来自MIMIC-III公共数据集的记录。这项工作提出了一个数据集与巴西葡萄牙临床笔记的结果。我们开发并优化了Logistic回归模型、卷积神经网络(CNN)、门控递归单元神经网络和带注意力的CNN(CNN-Att)用于预测诊断ICD代码。我们还报告了MIMIC-III数据集的结果,该数据集在相同家族的模型中表现优于以前的工作,以及最先进的技术水平。与MIMIC-III相比,巴西葡萄牙语数据集包含的每个文档的单词要少得多,仅使用出院摘要。我们尝试连接此数据集中可用的其他文档,从而极大地提高了性能。CNN-Att模型在两个数据集上都取得了最佳结果,MIMIC-III的微平均F1得分为0.537,而我们的数据集上的微平均F1得分为0.485。

英文摘要:

ICD coding from electronic clinical records is a manual, time-consuming and expensive process. Code assignment is, however, an important task for billing purposes and database organization. While many works have studied the problem of automated ICD coding from free text using machine learning techniques, most use records in the English language, especially from the MIMIC-III public dataset. This work presents results for a dataset with Brazilian Portuguese clinical notes. We develop and optimize a Logistic Regression model, a Convolutional Neural Network (CNN), a Gated Recurrent Unit Neural Network and a CNN with Attention (CNN-Att) for prediction of diagnosis ICD codes. We also report our results for the MIMIC-III dataset, which outperform previous work among models of the same families, as well as the state of the art. Compared to MIMIC-III, the Brazilian Portuguese dataset contains far fewer words per document, when only discharge summaries are used. We experiment concatenating additional documents available in this dataset, achieving a great boost in performance. The CNN-Att model achieves the best results on both datasets, with micro-averaged F1 score of 0.537 on MIMIC-III and 0.485 on our dataset with additional documents.

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。

↑