基于人工智能干预的临床试验研究进展

许璐; 王胜锋; 詹思延

doi:10.16462/j.cnki.zhjbkz.2021.01.003

基于人工智能干预的临床试验研究进展

doi: 10.16462/j.cnki.zhjbkz.2021.01.003

100191 北京，北京大学公共卫生学院流行病与卫生统计学系

基金项目:

国家自然科学基金 81973146

国家自然科学基金 81502884

详细信息

通讯作者:
詹思延，E-mail：siyan-zhan@bjmu.edu.cn

王胜锋，E-mail：shengfeng1984@126.com

中图分类号: R181.2
计量
- 文章访问数: 463
- HTML全文浏览量: 137
- PDF下载量: 112
- 被引次数: 0
出版历程
- 收稿日期: 2020-12-08
- 修回日期: 2020-12-21
- 刊出日期: 2021-01-10

Research progress of clinical trials with artificial intelligence intervention

Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing 100191, China

Funds:

National Natural Science Foundation of China 81973146

National Natural Science Foundation of China 81502884

More Information

Corresponding author: WANG Sheng-feng, E-mail: shengfeng1984@126.com; ZHAN Si-yan, E-mail: siyan-zhan@bjmu.edu.cn

摘要

摘要: 随着越来越多的人工智能技术被开发应用于医疗卫生领域，近年来以人工智能为干预的临床试验开始不断出现。本文将介绍以人工智能为干预措施的临床试验的发展现状、方案指南、报告规范和面临的挑战与展望，以便于未来研究者规范地开展此类临床试验，推动人工智能技术在医疗卫生领域的发展与应用。
- 人工智能 /
- 临床试验 /
- 指南
Abstract: With artificial intelligence technology increasingly developed and applied in the field of health care, clinical trials with artificial intelligence intervention have been emerging in recent years. This article will introduce the status quo, protocol guidelines, reporting guidelines, challenges and prospects of clinical trials with artificial intelligence intervention, so as to facilitate future researchers to carry out clinical trials in a standardized manner, and promote the development and application of artificial intelligence technology in the field of health care.
- Artificial intelligence /
- Clinical trial /
- Guideline

HTML全文

表 1 已发表的高质量AI临床试验研究示例

Table 1. Examples of published high-quality AI clinical trials

表 2 SPIRIT-AI条目^a

Table 2. Items in SPIRIT-AI ^a

条目	涉及方案内容	具体条目内容
SPIRIT-AI 1(ⅰ)	标题	指出干预涉及AI^b/机器学习，或指出模型类型
SPIRIT-AI 1(ⅱ)	指明AI干预的预期用途
SPIRIT-AI 6^a (ⅰ)	背景和合理性	解释AI干预在临床背景下的预期用途，包括其目的和预期受众(如：医务人员、患者及公众)
SPIRIT-AI 6^a (ⅱ)	描述与AI干预相关的现有证据
SPIRIT-AI 9	方法：研究场所	描述将AI干预整合到试验场所中所需的现场和场外条件
SPIRIT-AI 10 (ⅰ)	方法：入选标准	说明研究对象的纳入排除标准
SPIRIT-AI 10 (ⅱ)		说明AI干预所需输入数据的纳入排除标准
SPIRIT-AI 11^a (ⅰ)	方法：干预	说明使用的AI算法版本
SPIRIT-AI 11^a (ⅱ)		说明获取和选择AI干预所需输入数据的程序
SPIRIT-AI 11^a (ⅲ)		说明评估和处理质量差或不可用的AI干预所需输入数据的程序
SPIRIT-AI 11^a (ⅳ)		说明在处理AI干预所需输入数据的过程中是否存在人与AI的交互，以及需要用户达到的专业水平
SPIRIT-AI 11^a (ⅴ)		说明AI干预的输出
SPIRIT-AI 11^a (ⅵ)		解释AI干预的输出如何有助于决策或临床实践的其他要素
SPIRIT-AI 22	方法：监测可能的错误	说明识别和分析AI干预出现错误的任何计划。如果没有这方面的计划，说明为什么不这样做。
SPIRIT-AI 29	伦理和传播：代码获取	说明是否可以获取AI干预和/或其代码。如果可以，如何获取(包括对获取或再使用的任何限制条件)。
注：^a标准方案条目：对人工智能干预试验的建议(standard protocol items: recommendations for interventional trials-artificial intelligence, SPIRIT-AI)，人工智能(artificial intelligence, AI)。

下载: 导出CSV

参考文献(18)

[1]	He J, Baxter SL, Xu J, et al. The practical implementation of artificial intelligence technologies in medicine[J]. Nat Med, 2019, 25(1):30-36. DOI: 10.1038/s41591-018-0307-0.
[2]	Rivera SC, Liu X, Chan AW, et al. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI Extension[J]. BMJ, 2020, 370:m3210. DOI: 10.1136/bmj.m3210.
[3]	Caballero RE, García SG, Rigl AM, et al. A web-based clinical decision support system for gestational diabetes: Automatic diet prescription and detection of insulin needs[J]. Int J Med Inform, 2017, 102:35-49. DOI: 10.1016/j.ijmedinf.2017.02.014.
[4]	Kim TWB, Gay N, Khemka A, et al. Internet-based exercise therapy using algorithms for conservative treatment of anterior knee pain: a pragmatic randomized controlled trial[J]. JMIR Rehabil Assist Technol, 2016, 3(2):e12. DOI: 10.2196/rehab.5148.
[5]	Labovitz DL, Shafner L, Reyes GM, et al. Using artificial intelligence to reduce the risk of nonadherence in patients on anticoagulation therapy[J]. Stroke, 2017, 48(5):1416-1419. DOI: 10.1161/STROKEAHA.116.016281.
[6]	Lin H, Li R, Liu Z, et al. Diagnostic efficacy and therapeutic decision-making capacity of an artificial intelligence platform for childhood cataracts in eye clinics: a multicentre randomized controlled trial[J]. EClinical Medicine, 2019, 9:52-59. DOI: 10.1016/j.eclinm.2019.03.001.
[7]	Voss C, Schwartz J, Daniels J, et al. Effect of wearable digital intervention for improving socialization in children with autism spectrum disorder: a randomized clinical trial[J]. JAMA Pediatr, 2019, 173(5):446-454. DOI: 10.1001/jamapediatrics.2019.0285.
[8]	Mathew B, Norris D, Hendry D, et al. Artificial intelligence in the diagnosis of low-back pain and sciatica[J]. Spine, 1988, 13(2):168-172. DOI: 10.1097/00007632-198802000-00007.
[9]	Pavel AM, Rennie JM, De Vries LS, et al. A machine-learning algorithm for neonatal seizure recognition: a multicentre, randomised, controlled trial[J]. Lancet Child Adolesc Health, 2020, 4(10):740-749. DOI: 10.1016/s2352-4642(20)30239-x.
[10]	Wang P, Liu X, Berzin TM, et al. Effect of a deep-learning computer-aided detection system on adenoma detection during colonoscopy (CADe-DB trial): a double-blind randomised study[J]. Lancet Gastroenterol Hepatol, 2020, 5(4):343-351. DOI: 10.1016/s2468-1253(19)30411-x.
[11]	Wijnberge M, Geerts BF, Hol L, et al. Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial[J]. JAMA, 2020, 323(11):1052-1060. DOI: 10.1001/jama.2020.0592.
[12]	Wang P, Berzin TM, Glissen Brown JR, et al. Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study[J]. Gut, 2019, 68(10):1813-1819. DOI: 10.1136/gutjnl-2018-317500.
[13]	Persell SD, Peprah YA, Lipiszko D, et al. Effect of home blood pressure monitoring via a smartphone hypertension coaching application or tracking application on adults with uncontrolled hypertension: a randomized clinical trial[J]. JAMA Netw Open, 2020, 3(3):e200255. DOI: 10.1001/jamanetworkopen.2020.0255.
[14]	Chan AW, Tetzlaff JM, Altman DG, et al. SPIRIT 2013 statement: defining standard protocol items for clinical trials[J]. Ann Intern Med, 2013, 158(3):200-207. DOI: 10.7326/0003-4819-158-3-201302050-00583.
[15]	Liu X, Rivera SC, Moher D, et al. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension[J]. BMJ, 2020, 370:m3164. DOI: 10.1136/bmj.m3164.
[16]	Chan AW, Tetzlaff JM, Gøtzsche PC, et al. SPIRIT 2013 explanation and elaboration: guidance for protocols of clinical trials[J]. BMJ, 2013, 346:e7586. DOI: 10.1136/bmj.e7586.
[17]	Washington P, Voss C, Kline A, et al. SuperpowerGlass: a wearable aid for the at-home therapy of children with autism[J]. Proc ACM Interact Mob Wearable Ubiquitous Technol, 2017, 1(3):112. DOI: 10.1145/3130977.
[18]	Daniels J, Schwartz JN, Voss C, et al. Exploratory study examining the at-home feasibility of a wearable tool for social-affective learning in children with autism[J]. NPJ Digit Med, 2018, 1:32. DOI: 10.1038/s41746-018-0035-3.