Blockchain Industrial College (CUIT Shuangliu Industrial College), Chengdu University of Information Technology, Chengdu 610225, China. Electronic address: https://twitter.com/zhizhid.
Blockchain Industrial College (CUIT Shuangliu Industrial College), Chengdu University of Information Technology, Chengdu 610225, China; School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu 611130, China.
J Biomed Inform. 2024 Aug;156:104668. doi: 10.1016/j.jbi.2024.104668. Epub 2024 Jun 8.
The objective of this study is to integrate PICO knowledge into the clinical research text summarization process, aiming to enhance the model's comprehension of biomedical texts while capturing crucial content from the perspective of summary readers, ultimately improving the quality of summaries.
We propose a clinical research text summarization method called DKGE-PEGASUS (Domain-Knowledge and Graph Convolutional Enhanced PEGASUS), which is based on integrating domain knowledge. The model mainly consists of three components: a PICO label prediction module, a text information re-mining unit based on Graph Convolutional Neural Networks (GCN), and a pre-trained summarization model. First, the PICO label prediction module is used to identify PICO elements in clinical research texts while obtaining word embeddings enriched with PICO knowledge. Then, we use GCN to reinforce the encoder of the pre-trained summarization model to achieve deeper text information mining while explicitly injecting PICO knowledge. Finally, the outputs of the PICO label prediction module, the GCN text information re-mining unit, and the encoder of the pre-trained model are fused to produce the final coding results, which are then decoded by the decoder to generate summaries.
Experiments conducted on two datasets, PubMed and CDSR, demonstrated the effectiveness of our method. The Rouge-1 scores achieved were 42.64 and 38.57, respectively. Furthermore, the quality of our summarization results was found to significantly outperform the baseline model in comparisons of summarization results for a segment of biomedical text.
The method proposed in this paper is better equipped to identify critical elements in clinical research texts and produce a higher-quality summary.
本研究旨在将 PICO 知识融入临床研究文本摘要过程中，旨在提高模型对生物医学文本的理解能力，同时从摘要读者的角度捕捉关键内容，从而提高摘要的质量。
我们提出了一种称为 DKGE-PEGASUS（基于领域知识和图卷积增强的 PEGASUS）的临床研究文本摘要方法，该方法基于集成领域知识。该模型主要由三个组件组成：PICO 标签预测模块、基于图卷积神经网络（GCN）的文本信息再挖掘单元和预训练的摘要模型。首先，PICO 标签预测模块用于识别临床研究文本中的 PICO 元素，同时获得富含 PICO 知识的词嵌入。然后，我们使用 GCN 增强预训练的摘要模型的编码器，以实现更深层次的文本信息挖掘，同时明确注入 PICO 知识。最后，PICO 标签预测模块、GCN 文本信息再挖掘单元和预训练模型的编码器的输出被融合以产生最终的编码结果，然后由解码器解码以生成摘要。
在两个数据集，PubMed 和 CDSR 上进行的实验证明了我们方法的有效性。Rouge-1 分数分别为 42.64 和 38.57。此外，与基线模型相比，我们的生物医学文本片段的摘要结果质量明显更好。
本文提出的方法能够更好地识别临床研究文本中的关键元素，并生成更高质量的摘要。
