Medical Report Extraction Generation Model Integrated with BioCopy Mechanism

doi:10.3778/j.issn.1002-8331.2210-0071

Abstract

Abstract: Wise information technology of med (WITMED) is a new health care service mode that integrates information technologies such as artificial intelligence. Among them, automatic generation of medical reports is an important task in the field of WITMED. This task generates semi-structured medical reports based on patient self-report and doctor-patient dialogue. The medical report not only contains the chief complaint and other sub parts, but also contains a large number of medical terms from the original text. In view of these characteristics, a summary model integrating extraction and abstraction of BioCopy mechanism is adopted. Firstly, the model extracts key sentences for each sub-part to eliminate the interference of irrelevant information. Then, the BioCopy mechanism is added when generating the medical report to copy the medical terms in the key sentences to ensure the accuracy of the results. The experimental results on CCL 2021 datasets show that this model is superior to the main baseline and has achieved good results.

Key words: automatic generation of medical reports, extraction and generation, BioCopy

摘要： 智慧医疗是融合了人工智能技术的新型健康医疗服务模式，其中医疗报告自动生成是智慧医疗领域的一项重要任务，该任务依据病人自述和医患对话，生成半结构化的医疗报告。医疗报告不仅包含主诉等多个子部分，而且包含大量来自原文的医疗术语。针对这些特点，采用了融入BioCopy机制的抽取与生成结合的摘要模型，模型首先对每个子部分进行关键句抽取，排除无关信息的干扰；然后在生成医疗报告时加入BioCopy机制以复制关键句中的医疗术语，保证结果的准确性。在CCL 2021相关数据集上的实验结果表明：该模型优于主要baseline，取得了较好的效果。

关键词: 医疗报告自动生成, 抽取与生成, BioCopy

LIU Lan, TAN Hongye. Medical Report Extraction Generation Model Integrated with BioCopy Mechanism[J]. Computer Engineering and Applications, 2024, 60(6): 155-162.

刘岚, 谭红叶. 融入BioCopy机制的医疗报告抽取生成模型[J]. 计算机工程与应用, 2024, 60(6): 155-162.

References

[1] SEE A, LIU P J, MANNING C D. Get to the point: summarization with pointer-generator networks[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 1073-1083.
[2] LIU Z, NG A, LEE S, et al. Topic-aware pointer-generator networks for summarizing spoken conversations[C]//2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019: 814-821.
[3] KRISHNA K, KHOSLA S, BIGHAM J, et al. Generating SOAP notes from doctor-patient conversations using modular summarization techniques[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021: 4958-4972.
[4] VINYALS O, FORTUNATO M, JAITLY N. Pointer networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems, 2015: 2692-2700.
[5] LIU Y, ZHANG G, YU P, et al. BioCopy: a plug-and-play span copy mechanism in Seq2Seq models[C]//Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing, 2021: 53-57.
[6] MIHALCEA R, TARAU P. TextRank: bringing order into texts[C]//Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, 2004: 404-411.
[7] CAO Z, WEI F, LI D, et al. Ranking with recursive neural networks and its application to multi-document summarization[C]//Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015: 2153-2159.
[8] LIU Y. Fine-tune BERT for extractive summarization[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 3548-3553.
[9] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017:6000-6010.
[10] MANAKUL P, GALES M. Long-span dependencies in transformer-based summarization systems[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021: 6026-6041.
[11] DONG L, YANG N, WANG W, et al. Unified language model pre-training for natural language understanding and generation[C]//Proceedings of the 33rd International Conference on Neural Information Processing Systems, 2019: 13042-13054.
[12] GULCEHRE C, AHN S, NALLAPATI R, et al. Pointing the unknown words[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016: 140-149.
[13] GU J, LU Z, LI H, et al. Incorporating copying mechanism in sequence?to?sequence learning[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016: 1631-1640.
[14] MADOTTO A, WU C S, FUNG P. Mem2Seq: effectively incorporating knowledge bases into end-to-end task-oriented dialog systems[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 1468-1478.
[15] LIU Y, LAPATA M. Text summarization with pretrained encoders[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 3730-3740.
[16] JOSHI A, KATARIYA N, AMATRIAIN X, et al. Dr. summarize: global summarization of medical dialogue by exploiting local structures[C]//Findings of the Association for Computational Linguistics (EMNLP 2020), 2020: 3755-3763.
[17] SONG Y, TIAN Y, WANG N, et al. Summarizing medical conversations via identifying important utterances[C]//Proceedings of the 28th International Conference on Computational Linguistics, 2020: 717-729.
[18] 谢诗文.基于TextRank算法的在线问诊多轮对话文本摘要研究[D].武汉: 武汉大学, 2020.
XIE S W. Research on multi-round dialogue text summarization in online medical inquiry based on TextRank algorithm[D].Wuhan: Wuhan University, 2020.
[19] ZHANG L, NEGRINHO R, GHOSH A, et al. Leveraging pretrained models for automatic summarization of doctor-patient conversations[C]//Findings of the Association for Computational Linguistics (EMNLP 2021), 2021: 3693-3712.
[20] 何玉洁. 基于命名实体识别的医学病历自动生成研究与实现[D]. 银川: 宁夏大学, 2020.
HE Y J. Research and realization of medical case automatic generation based on named entiry recognition[D].Yinchuan: Ningxia University, 2020.
[21] NALLAPATI R, ZHOU B, SANTOS C, et al. Abstractive text summarization using sequence-to-sequence RNNs and beyond[C]//Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning, 2016: 280-290.
[22] GUO M, AINSLIE J, UTHUS D, et al. LongT5: efficient text-to-text transformer for long sequences[C]//Findings of the Association for Computational Linguistics (NAACL 2022), 2022: 724-736.