In this paper, we present a novel approach for medical synonym extraction. We aim to integrate the term embedding with the medical domain knowledge for healthcare applications. One advantage of our method is that it is very scalable. Experiments on a dataset with more than 1M term pairs show that the proposed approach outperforms the baseline approaches by a large margin.
MedDec: A Dataset for Extracting Medical Decisions from Discharge Summaries
Miner School of Computer & Information Sciences, University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校 Miner 计算机与信息科学学院);Institute for Medical Engineering and Science, Massachusetts Institute of Technology(麻省理工学院医学工程与科学研究院)
Extracting Knowledge from an Arabic-English Machine-Readable Dictionary Using Information Extraction
Department of Computer Science(计算机科学系);Department of EECE(电子工程与计算机科学系);Faculty of Computers and Information, Cairo University(开罗大学计算机与信息学院);Faculty of Engineering, Cairo University(开罗大学工程学院);Department of Arabic Language and Literatures(阿拉伯语言与文学系);Faculty of Arts, Cairo University(开罗大学艺术学院)
Pre-trained Language Models and Few-shot Learning for Medical Entity Extraction
Santa Clara University(圣克拉拉大学);San Francisco State University(旧金山州立大学);Cornell University(康奈尔大学);The Chinese University of Hong Kong(香港中文大学);Stevens Institute of Technology(史蒂文斯理工学院)
Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forest
University of Chinese Academy of Sciences(中国科学院大学);Institute of Software Chinese Academy of Sciences(中国科学院软件研究所);University Of Electronic Science And Technology Of China(电子科技大学)
Assessment of Amazon Comprehend Medical: Medication Information Extraction
NYU Langone Health(纽约大学朗格尼医学中心)
2018年11月27日,Amazon Web Services(AWS)发布了Amazon Comprehend Medical(ACM),这是一个基于深度学习的系统,可以从临床文本笔记中自动提取临床概念(包括解剖结构、医疗状况、受保护的健康信息(PH)I、测试名称、治疗名称、医疗程序和药物)。对任何新数据产品的接受和信任都依赖于跨基准数据集和工具的独立验证,以建立和确认预期的结果质量。这项工作的重点是药物提取任务,特别是使用2009年i2b2药物提取挑战赛和2018年n2c2轨道2的官方测试集评估ACM:不良药物事件和EHR中的药物提取。总体而言,ACM的F评分为0.768和0.828。与各自挑战中的三个最佳系统相比,这些分数排名最低。为了进一步确定其药物提取性能的普遍性,这项工作还包括来自纽约大学Langone医学中心的一组随机内部临床文本注释。在这个语料库中,ACM获得了0.753的F分数。
A Unified Framework of Medical Information Annotation and Extraction for Chinese Clinical Text
HwaMei Hospital, University of Chinese Academy of Sciences(中国科学院大学华美医院);Ningbo Institute of Life and Health Industry, University of Chinese Academy of Sciences(中国科学院大学宁波生命与健康产业研究院)
Syntactic Patterns Improve Information Extraction for Medical Search
King’s College London(伦敦国王学院);University of Pennsylvania(宾夕法尼亚大学);Northeastern University(东北大学);Rutgers University-Camden(罗格斯大学卡姆登分校);Google Inc.(谷歌公司)
A Case Study on Pros and Cons of Regular Expression Detection and Dependency Parsing for Negation Extraction from German Medical Documents. Technical Report
German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心);Oldenburg University(奥尔登堡大学)
Leveraging Dependency Forest for Neural Medical Relation Extraction
University of Rochester(罗切斯特大学);Tencent AI Lab(腾讯人工智能实验室);Institute of Advanced Technology, Westlake Institute for Advanced Study(西湖高等研究院先进技术研究院);IBM T.J. Watson Research(IBM托马斯·J·沃森研究中心);Amazon AWS(亚马逊云科技);Xiamen University(厦门大学)
Large Language Model-based Role-Playing for Personalized Medical Jargon Extraction
Manning College of Information and Computer Sciences, University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校曼宁信息与计算机科学学院);Mendoza College of Business, University of Notre Dame(圣母大学门多萨商学院);University of Massachusetts Medical School(马萨诸塞大学医学院);Miner School of Computer and Information Sciences, University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校迈纳计算机与信息科学学院);VA Bedford Health Care(贝德福德退伍军人事务医疗中心)
Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding
University of Science and Technology of China(中国科学技术大学);Jarvis Research Center, Tencent YouTu Lab(腾讯优图实验室贾维斯研究中心);Peking University(北京大学);Westlake University(西湖大学);City University of Hong Kong(香港城市大学)
A Medical Information Extraction Workbench to Process German Clinical Text
German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心);Charité – Universitätsmedizin Berlin(柏林夏里特医学院);Berlin Institute of Health(柏林健康研究所)
A Knowledge-enhanced Two-stage Generative Framework for Medical Dialogue Information Extraction
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
Fine-tuning ERNIE for chest abnormal imaging signs extraction
Sun Yat-Sen University(中山大学)
胸部影像学报告描述了胸部X线摄影程序的结果。从胸部影像报告中自动提取异常影像征象在临床研究和广泛的下游医疗任务中具有举足轻重的作用。然而,目前对中文胸部影像学报告进行信息抽取的研究还很少。在本文中,我们制定了胸部异常影像体征提取序列标记和匹配问题。在此基础上,提出了一种以预训练的ERNIE为骨干的转移式异常影像体征提取器EASON(fine-tuning ERNIE with CRF for Abnormal Signs ExtractiON),可以解决数据不足的问题。此外,针对序列标注模型的结果,设计了一种简单有效的tag 2 relation算法,将序列标注模型中的身体部位和程度等属性赋予相应的异常影像学征象。我们在一家医疗大数据公司提供的语料库上对我们的方法进行了评估,实验结果表明,与其他基线相比,我们的方法实现了显著且一致的改进。
Pathology Extraction from Chest X-Ray Radiology Reports: A Performance Study
Semion
从放射学报告中提取相关病理术语对于正确的图像标签生成和疾病人群研究非常重要。在这封信中,我们比较了性能的一些已知的应用程序接口(API)的任务,胸部异常提取放射学报告。我们探索了几个医疗领域特定的注释工具,如具有非MEDLINE和Mesh On Demand(MOD)选项的Medical Text Indexer(MTI),以及IBM云提供的通用自然语言理解(NLU)API。我们的研究结果表明,虽然MTI和MOD是用于提取医学术语,但与IBM NLU等通用提取API相比,它们的性能最差。最后,我们训练了一个基于DNN的命名实体识别(NER)模型,从放射学报告中提取关键概念词。我们的模型在很大程度上优于医疗特定和通用API性能。我们的研究结果表明,通用API的病理提取任务的不足,并建立特定领域的模型训练的重要性,以改善结果。我们希望这些结果能够激励研究界发布更大的去识别放射学报告语料库,用于构建高精度的机器学习模型,以完成病理提取的重要任务。
Use of 'off-the-shelf' information extraction algorithms in clinical informatics: a feasibility study of MetaMap annotation of Italian medical notes
Consiglio Nazionale delle Ricerche (CNR)(意大利国家研究委员会);Politecnico di Milano(米兰理工大学);Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico Milano(米兰大医院基金会)
Automatic Extraction of Disease Risk Factors from Medical Publications
School of Computer Science, The Academic College of Tel Aviv-Yaffo(特拉维夫-雅法学术学院计算机科学学院);Division of Cardiology, Tel-Aviv Sourasky Medical Center(特拉维夫苏拉斯基医疗中心心脏病科);Faculty of Medicine, The Hebrew University of Jerusalem(希伯来大学医学院);Bioinformatics, School of Computer Science, The Academic College of Tel Aviv-Yaffo(特拉维夫-雅法学术学院计算机科学学院生物信息学方向)