Lee Tso-Ying, Li Chin-Ching, Chou Kuei-Ru, Chung Min-Huey, Hsiao Shu-Tai, Guo Shu-Liu, Hung Lung-Yun, Wu Hao-Ting
Director of Nursing Research Center, Nursing Department, Taipei Medical University Hospital, Taipei, Taiwan; Associate Professor, School of Nursing, College of Nursing, Taipei Medical University, Taipei, Taiwan.
Assistant Professor, Department of Nursing, Mackay Medical College, New Taipei City, Taiwan.
Int J Med Inform. 2023 Oct;178:105213. doi: 10.1016/j.ijmedinf.2023.105213. Epub 2023 Sep 9.
Considering the significant workload of nursing tasks, enhancing the efficiency of nursing documentation is imperative. This study aimed to evaluate the effectiveness of a machine learning-based speech recognition (SR) system in reducing the clinical workload associated with typing nursing records, implemented in a psychiatry ward.
The study was conducted between July 15, 2020, and June 30, 2021, at Cheng Hsin General Hospital in Taiwan. The language corpus was based on the existing records from the hospital nursing information system. The participating ward's nursing activities, clinical conversation, and accent data were also collected for deep learning-based SR-engine training. A total of 21 nurses participated in the evaluation of the SR system. Documentation time and recognition error rate were evaluated in parallel between SR-generated records and keyboard entry over 4 sessions. Any differences between SR and keyboard transcriptions were regarded as SR errors.
A total of 200 data were obtained from four evaluation sessions, 10 participants were asked to use SR and keyboard entry in parallel at each session and 5 entries were collected from each participant. Overall, the SR system processed 30,112 words in 32,456 s (0.928 words per second). The mean accuracy of the SR system improved after each session, from 87.06% in 1st session to 95.07% in 4th session.
This pilot study demonstrated our machine learning-based SR system has an acceptable recognition accuracy and may reduce the burden of documentation for nurses. However, the potential error with the SR transcription should continually be recognized and improved. Further studies are needed to improve the integration of SR in digital documentation of nursing records, in terms of both productivity and accuracy across different clinical specialties.
鉴于护理任务的工作量巨大，提高护理记录的效率势在必行。本研究旨在评估基于机器学习的语音识别（SR）系统在减少精神病病房中与录入护理记录相关的临床工作量方面的有效性。
该研究于2020年7月15日至2021年6月30日在台湾的成信综合医院进行。语言语料库基于医院护理信息系统的现有记录。还收集了参与病房的护理活动、临床对话和口音数据，用于基于深度学习的SR引擎训练。共有21名护士参与了SR系统的评估。在4个阶段中，对SR生成的记录和键盘录入的文档时间和识别错误率进行了并行评估。SR和键盘转录之间的任何差异都被视为SR错误。
从四个评估阶段共获得200个数据，每个阶段要求10名参与者同时使用SR和键盘录入，每个参与者收集5条记录。总体而言，SR系统在32456秒内处理了30112个单词（每秒0.928个单词）。SR系统的平均准确率在每个阶段后都有所提高，从第一阶段的87.06%提高到第四阶段的95.07%。
这项初步研究表明，我们基于机器学习的SR系统具有可接受的识别准确率，可能会减轻护士的文档记录负担。然而，应持续认识并改进SR转录的潜在错误。需要进一步研究，以提高SR在护理记录数字文档中的集成度，包括不同临床专科的生产力和准确性。
