Improving the Factual Accuracy of Abstractive Clinical Text Summarization using Multi-Objective Optimization.
Improving the Factual Accuracy of Abstractive Clinical Text Summarization using Multi-Objective Optimization.
复制标题
使用多目标优化提高抽象临床文本摘要的事实准确性。
DOI：
10.1109/embc48229.2022.9871798
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Cajita,Mia
中科院分区：
文献类型：
--
作者：
Alambo,Amanuel;Banerjee,Tanvi;Thirunarayan,Krishnaprasad;Cajita,Mia
尽管最近在抽象摘要应用于新闻文章、科学文章和博客文章等不同领域方面取得了进展，但这些技术在临床文本摘要中的应用仍然受到限制。这主要是由于缺乏大规模训练数据以及临床记录的混乱/非结构化性质，而不是其他领域的大量训练数据以结构化或半结构化形式出现。此外，临床文本摘要中探索最少且关键的组成部分之一是临床摘要的事实准确性。这在医疗保健领域尤其重要，尤其是心脏病学，在该领域，保留源注释中的事实的准确摘要生成对于患者的福祉至关重要。在这项研究中，我们提出了一个框架，使用知识引导的多目标优化来提高临床文本抽象总结的事实准确性。我们建议在训练期间联合优化我们提出的架构中的三个成本函数：生成损失、实体损失和知识损失，并评估所提出的架构：1）我们为本研究收集的心力衰竭（HF）患者的临床记录； 2) 两个公开的基准数据集：印第安纳大学胸部 X 射线集合 (IU X 射线) 和 MIMIC-CXR。我们对三种 Transformer 编码器-解码器架构进行了实验，并证明优化不同的损失函数可以提高实体级事实准确性方面的性能。
While there has been recent progress in abstractive summarization as applied to different domains including news articles, scientific articles, and blog posts, the application of these techniques to clinical text summarization has been limited. This is primarily due to the lack of large-scale training data and the messy/unstructured nature of clinical notes as opposed to other domains where massive training data come in structured or semi -structured form. Further, one of the least explored and critical components of clinical text summarization is factual accuracy of clinical summaries. This is specifically crucial in the healthcare domain, cardiology in particular, where an accurate summary generation that preserves the facts in the source notes is critical to the well-being of a patient. In this study, we propose a framework for improving the factual accuracy of abstractive summarization of clinical text using knowledge-guided multi-objective optimization. We propose to jointly optimize three cost functions in our proposed architecture during training: generative loss, entity loss and knowledge loss and evaluate the proposed architecture on 1) clinical notes of patients with heart failure (HF), which we collect for this study; and 2) two benchmark datasets, Indiana University Chest X-ray collection (IU X-Ray), and MIMIC-CXR, that are publicly available. We experiment with three transformer encoder-decoder architectures and demonstrate that optimizing different loss functions leads to improved performance in terms of entity-level factual accuracy.