提取性临床问答与多个答案和多重点问题:数据集开发和评估研究研究
Sungrim Moon1, Huan He1, Heling Jia1
1Department of Artificial Intelligence & Informatics, Mayo Clinic, Rochester, MN, United States.
这项研究介绍了RxWhyQA,这是一个新的数据集,用于训练人工智能以多个答案或重点来回答复杂的临床问题. 该数据集使得用于医疗保健的提取式问答 (EQA) 系统的开发更加现实.
科学领域:
- 自然语言处理 (NLP) 是一种自然语言处理.
- 医疗保健中的人工智能 (AI)
- 临床数据分析 临床数据分析
背景情况:
- 提取式问答 (EQA) 有助于通过临床笔记回答患者的问题.
- 现有的数据集缺乏支持在临床环境中常见的多个答案和多重点问题的支持.
- 开发用于现实的临床EQA的人工智能需要专门的数据集.
研究的目的:
- 为开发和评估临床EQA系统创建一个新的数据集.
- 通过结合多个答案和多重点问题能力来解决现有数据集的局限性.
- 促进创建处理复杂,自然临床查询的AI解决方案.
主要方法:
- 从2018年国家NLP临床挑战库中利用注释关系.
- 创建了一个EQA数据集,包括1-to-N,M-to-1和M-to-N药物原因关系.
- 在新创建的数据集上开发并测试了基线EQA解决方案.
主要成果:
- RxWhyQA数据集包括96,939个问答条目.
- 25%的可回答问题需要多个答案,2%涉及多种药物.
- 基线EQA获得了0.72的F1得分,多个答案和多种药物问题的表现有显著差异.
结论:
- RxWhyQA数据集适用于培训和评估EQA系统的多个答案和多重点问题.
- 多个答案EQA带来了重大挑战,需要进一步的研究和投资.
- 共享的数据集促进了对更现实的临床EQA场景的研究.
更多相关视频
10:43Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes
Published on: June 10, 2021
12:55Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties
Published on: September 27, 2020
相关概念视频
Techniques of Therapeutic Communication II: Focusing, Paraphrasing, and Summarizing
This therapeutic technique can also be used when a patient brings up pertinent information during a health-related conversation. The...
Methods of Documentation IV: Focus Charting
It typically involves three columns for recording information:
Strategies for Assessing and Addressing Confounding
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Patient-centered Care
Critical Thinking II
Nursing Assessment
The nurse collects all aspects of the patient's health in the initial assessment, establishing priorities for ongoing focused assessments...
