Suominen Hanna, Johnson Maree, Zhou Liyuan, Sanchez Paula, Sirel Raul, Basilakis Jim, Hanlen Leif, Estival Dominique, Dawson Linda, Kelly Barbara
Machine Learning Research Group, NICTA, College of Engineering and Computer Science, The Australian National University, Faculty of Health, University of Canberra, and Department of Information Technology, University of Turku, Canberra, Australian Capital Territory, Australia.
Research Faculty of Health Sciences, Australian Catholic University, Sydney, New South Wales, Australia.
J Am Med Inform Assoc. 2015 Apr;22(e1):e48-66. doi: 10.1136/amiajnl-2014-002868. Epub 2014 Oct 21.
We study the use of speech recognition and information extraction to generate drafts of Australian nursing-handover documents.
Speech recognition correctness and clinicians' preferences were evaluated using 15 recorder-microphone combinations, six documents, three speakers, Dragon Medical 11, and five survey/interview participants. Information extraction correctness evaluation used 260 documents, six-class classification for each word, two annotators, and the CRF++ conditional random field toolkit.
A noise-cancelling lapel-microphone with a digital voice recorder gave the best correctness (79%). This microphone was also the most preferred option by all but one participant. Although the participants liked the small size of this recorder, their preference was for tablets that can also be used for document proofing and sign-off, among other tasks. Accented speech was harder to recognize than native language and a male speaker was detected better than a female speaker. Information extraction was excellent in filtering out irrelevant text (85% F1) and identifying text relevant to two classes (87% and 70% F1). Similarly to the annotators' disagreements, there was confusion between the remaining three classes, which explains the modest 62% macro-averaged F1.
We present evidence for the feasibility of speech recognition and information extraction to support clinicians' in entering text and unlock its content for computerized decision-making and surveillance in healthcare.
The benefits of this automation include storing all information; making the drafts available and accessible almost instantly to everyone with authorized access; and avoiding information loss, delays, and misinterpretations inherent to using a ward clerk or transcription services.
我们研究使用语音识别和信息提取来生成澳大利亚护理交接班文件的草稿。
使用15种录音机 - 麦克风组合、6份文件、3名说话者、Dragon Medical 11以及5名调查/访谈参与者来评估语音识别的正确性和临床医生的偏好。信息提取正确性评估使用260份文件、对每个单词进行六类分类、两名注释者以及CRF++条件随机场工具包。
带有数字录音机的降噪翻领麦克风具有最佳的正确性（79%）。除一名参与者外，该麦克风也是所有参与者最青睐的选项。尽管参与者喜欢这款录音机的小巧尺寸，但他们更倾向于平板电脑，因为平板电脑还可用于文件校对和签字等其他任务。带有口音的语音比母语更难识别，男性说话者比女性说话者更容易被识别。信息提取在过滤无关文本（F1值为85%）以及识别与两类相关的文本（F1值分别为87%和70%）方面表现出色。与注释者之间的分歧类似，其余三类之间也存在混淆，这解释了宏观平均F1值为62%的原因。
我们提供了证据，证明语音识别和信息提取在支持临床医生输入文本以及为医疗保健中的计算机化决策和监测解锁其内容方面具有可行性。
这种自动化的好处包括存储所有信息；使草稿几乎能立即供所有获得授权访问的人使用和获取；以及避免使用病房办事员或转录服务所固有的信息丢失、延迟和误解。
