Ambient technology in epilepsy clinical practice.

IF 2.8 3区 医学 Q2 CLINICAL NEUROLOGY
Epilepsia Open Pub Date : 2025-05-22 DOI:10.1002/epi4.70066
Haania Kakwan, Justin F Rousseau, Lidia M Moura, Irfan S Sheikh
{"title":"Ambient technology in epilepsy clinical practice.","authors":"Haania Kakwan, Justin F Rousseau, Lidia M Moura, Irfan S Sheikh","doi":"10.1002/epi4.70066","DOIUrl":null,"url":null,"abstract":"<p><p>The utilization of large language model-based artificial intelligence (AI) in the field of neurology has gained attention as a viable tool to enhance and assist providers with processes ranging from scheduling patients to providing preliminary interpretations of testing results, pending orders, and documenting encounters. Epileptologists could benefit from these technologies by utilizing ambient AI models, recent applications of which offer promising solutions for automating clinical documentation. While the potential benefits of using these tools are significant and include reduced physician burnout and improved patient experience, the deployment of these technologies also raises critical concerns, such as potential biases in model training and the risk of errors being inserted into the electronic health record (EHR), among other yet to be realized unintended consequences. The accuracy of clinical documentation is essential in epilepsy care, where detailed seizure histories and accurate medication records are critical to patient safety. Another concern may be paradoxically increased physician burnout as increased expectations of providers are created. This article examines the challenges, risks, and practical considerations in applying documentation tools that utilize ambient intelligence (AmI) for outpatient epilepsy clinic encounters, highlighting key examples from clinical practice and underscoring the importance of human oversight. Although AmI models may enhance clinical documentation efficiency as measured by time to close a note and reduced rates of burnout in providers, their role in clinical environments must be carefully regulated, with further studies needed to validate this claim, provide ongoing monitoring of performance, and establish safeguards for patient safety. Collaborative efforts among clinicians, clinical informatics professionals, AI developers, and regulatory bodies are pressingly needed to ensure the safe deployment of AmI into clinical care settings. PLAIN LANGUAGE SUMMARY: Ambient artificial intelligence technology takes advantage of sensors embedded in the environment to automate tasks without the need for human input. It has the potential to streamline numerous tasks within outpatient epilepsy clinics and reduce the workload of providers as well as improve patient care. This technology has already been brought to the market as a tool for clinical documentation. The current challenges and limitations associated with its implementation require careful human oversight, which we show with examples. Further research, regulations, and ongoing monitoring are necessary to ensure ambient artificial intelligence benefits both patients and healthcare providers while minimizing risks.</p>","PeriodicalId":12038,"journal":{"name":"Epilepsia Open","volume":" ","pages":""},"PeriodicalIF":2.8000,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Epilepsia Open","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/epi4.70066","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

The utilization of large language model-based artificial intelligence (AI) in the field of neurology has gained attention as a viable tool to enhance and assist providers with processes ranging from scheduling patients to providing preliminary interpretations of testing results, pending orders, and documenting encounters. Epileptologists could benefit from these technologies by utilizing ambient AI models, recent applications of which offer promising solutions for automating clinical documentation. While the potential benefits of using these tools are significant and include reduced physician burnout and improved patient experience, the deployment of these technologies also raises critical concerns, such as potential biases in model training and the risk of errors being inserted into the electronic health record (EHR), among other yet to be realized unintended consequences. The accuracy of clinical documentation is essential in epilepsy care, where detailed seizure histories and accurate medication records are critical to patient safety. Another concern may be paradoxically increased physician burnout as increased expectations of providers are created. This article examines the challenges, risks, and practical considerations in applying documentation tools that utilize ambient intelligence (AmI) for outpatient epilepsy clinic encounters, highlighting key examples from clinical practice and underscoring the importance of human oversight. Although AmI models may enhance clinical documentation efficiency as measured by time to close a note and reduced rates of burnout in providers, their role in clinical environments must be carefully regulated, with further studies needed to validate this claim, provide ongoing monitoring of performance, and establish safeguards for patient safety. Collaborative efforts among clinicians, clinical informatics professionals, AI developers, and regulatory bodies are pressingly needed to ensure the safe deployment of AmI into clinical care settings. PLAIN LANGUAGE SUMMARY: Ambient artificial intelligence technology takes advantage of sensors embedded in the environment to automate tasks without the need for human input. It has the potential to streamline numerous tasks within outpatient epilepsy clinics and reduce the workload of providers as well as improve patient care. This technology has already been brought to the market as a tool for clinical documentation. The current challenges and limitations associated with its implementation require careful human oversight, which we show with examples. Further research, regulations, and ongoing monitoring are necessary to ensure ambient artificial intelligence benefits both patients and healthcare providers while minimizing risks.

环境技术在癫痫临床实践中的应用。
基于大型语言模型的人工智能(AI)在神经病学领域的应用已经引起了人们的关注,作为一种可行的工具,它可以增强和帮助提供者处理从安排患者到提供测试结果的初步解释、待处理的订单和记录遭遇等过程。通过使用环境人工智能模型,癫痫病医生可以从这些技术中受益,最近的应用为自动化临床文档提供了有前途的解决方案。虽然使用这些工具的潜在好处是巨大的,包括减少医生的职业倦怠和改善患者的体验,但这些技术的部署也引起了严重的担忧,例如模型训练中的潜在偏差和将错误插入电子健康记录(EHR)的风险,以及其他尚未实现的意外后果。临床文件的准确性在癫痫治疗中至关重要,详细的癫痫发作史和准确的用药记录对患者安全至关重要。另一个令人担忧的问题可能是,随着对医疗服务提供者期望的增加,医生的职业倦怠反而增加了。本文探讨了在门诊癫痫门诊就诊中应用环境智能(AmI)文档工具的挑战、风险和实际考虑,强调了临床实践中的关键例子,并强调了人类监督的重要性。虽然AmI模型可以提高临床记录效率(以结束记录的时间衡量),并降低提供者的倦怠率,但它们在临床环境中的作用必须仔细监管,需要进一步研究来验证这一说法,提供持续的绩效监测,并建立患者安全保障措施。迫切需要临床医生、临床信息学专业人员、人工智能开发人员和监管机构之间的合作努力,以确保在临床护理环境中安全部署AmI。摘要:环境人工智能技术利用嵌入环境中的传感器来自动执行任务,而无需人工输入。它有可能简化门诊癫痫诊所的许多任务,减少提供者的工作量,并改善患者护理。这项技术已经作为临床记录的工具推向了市场。目前与执行有关的挑战和限制需要谨慎的人为监督,我们将举例说明这一点。为了确保环境人工智能对患者和医疗保健提供者都有利,同时最大限度地降低风险,需要进一步的研究、法规和持续监测。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Epilepsia Open
Epilepsia Open Medicine-Neurology (clinical)
CiteScore
4.40
自引率
6.70%
发文量
104
审稿时长
8 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信