• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

系统评价和荟萃分析的高昂成本:呼吁机器学习更多地参与评估临床试验的前景。

The significant cost of systematic reviews and meta-analyses: A call for greater involvement of machine learning to assess the promise of clinical trials.

作者信息

Michelson Matthew, Reuter Katja

机构信息

Evid Science, 2361 Rosecrans Ave #348, El Segundo, 90245, Los Angeles, CA, United States.

Institute for Health Promotion and Disease Prevention Research, Department of Preventive Medicine, Keck School of Medicine, University of Southern California, 2001 N Soto St, Los Angeles, CA, 90032, United States.

出版信息

Contemp Clin Trials Commun. 2019 Aug 25;16:100443. doi: 10.1016/j.conctc.2019.100443. eCollection 2019 Dec.

DOI:10.1016/j.conctc.2019.100443
PMID:31497675
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC6722281/
Abstract

BACKGROUND

More than 90% of clinical-trial compounds fail to demonstrate sufficient efficacy and safety. To help alleviate this issue, systematic literature review and meta-analysis (SLR), which synthesize current evidence for a research question, can be applied to preclinical evidence to identify the most promising therapeutics. However, these methods remain time-consuming and labor-intensive. Here, we introduce an economic formula to estimate the expense of SLR for academic institutions and pharmaceutical companies.

METHODS

We estimate the manual effort involved in SLR by quantifying the amount of labor required and the total associated labor cost. We begin with an empirical estimation and derive a formula that quantifies and describes the cost.

RESULTS

The formula estimated that each SLR costs approximately $141,194.80. We found that on average, the ten largest pharmaceutical companies publish 118.71 and the ten major academic institutions publish 132.16 SLRs per year. On average, the total cost of all SLRs per year to each academic institution amounts to $18,660,304.77 and for each pharmaceutical company is $16,761,234.71.

DISCUSSION

It appears that SLR is an important, but costly mechanisms to assess the totality of evidence.

CONCLUSIONS

With the increase in the number of publications, the significant time and cost of SLR may pose a barrier to their consistent application to assess the promise of clinical trials thoroughly. We call on investigators and developers to develop automated solutions to help with the assessment of preclinical evidence particularly. The formula we introduce provides a cost baseline against which the efficiency of automation can be measured.

摘要

背景

超过90%的临床试验化合物未能证明足够的疗效和安全性。为帮助缓解这一问题,可将系统文献综述和荟萃分析(SLR)应用于临床前证据,以识别最有前景的治疗方法,SLR可综合针对某一研究问题的现有证据。然而,这些方法仍然耗时且费力。在此,我们引入一个经济公式来估算学术机构和制药公司进行SLR的费用。

方法

我们通过量化所需工作量和相关总劳动力成本来估算SLR所涉及的人工工作量。我们从实证估计开始,推导出一个量化和描述成本的公式。

结果

该公式估计每次SLR的成本约为141,194.80美元。我们发现,平均而言,十大制药公司每年发表118.71篇SLR,十大主要学术机构每年发表132.16篇SLR。平均而言,每个学术机构每年所有SLR的总成本达18,660,304.77美元,每个制药公司的总成本为16,761,234.71美元。

讨论

看来SLR是评估证据总体的一项重要但成本高昂的机制。

结论

随着出版物数量的增加,SLR的大量时间和成本可能成为其持续应用以全面评估临床试验前景的障碍。我们呼吁研究者和开发者开发自动化解决方案,特别是帮助评估临床前证据。我们引入的公式提供了一个成本基线,据此可衡量自动化的效率。

相似文献

1
The significant cost of systematic reviews and meta-analyses: A call for greater involvement of machine learning to assess the promise of clinical trials.系统评价和荟萃分析的高昂成本:呼吁机器学习更多地参与评估临床试验的前景。
Contemp Clin Trials Commun. 2019 Aug 25;16:100443. doi: 10.1016/j.conctc.2019.100443. eCollection 2019 Dec.
2
The future of Cochrane Neonatal.考克兰新生儿协作网的未来。
Early Hum Dev. 2020 Nov;150:105191. doi: 10.1016/j.earlhumdev.2020.105191. Epub 2020 Sep 12.
3
4
A rapid and systematic review of the clinical effectiveness and cost-effectiveness of topotecan for ovarian cancer.拓扑替康治疗卵巢癌的临床有效性和成本效益的快速系统评价。
Health Technol Assess. 2001;5(28):1-110. doi: 10.3310/hta5280.
5
6
Clinical effectiveness, tolerability and cost-effectiveness of newer drugs for epilepsy in adults: a systematic review and economic evaluation.成人癫痫新药的临床疗效、耐受性及成本效益:一项系统评价与经济学评估
Health Technol Assess. 2005 Apr;9(15):1-157, iii-iv. doi: 10.3310/hta9150.
7
Informative value of Patient Reported Outcomes (PRO) in Health Technology Assessment (HTA).患者报告结局(PRO)在卫生技术评估(HTA)中的信息价值。
GMS Health Technol Assess. 2011 Feb 2;7:Doc01. doi: 10.3205/hta000092.
8
Prevention of alcohol misuse among children, youths and young adults.预防儿童、青少年和青年酒精滥用。
GMS Health Technol Assess. 2011;7:Doc04. doi: 10.3205/hta000095. Epub 2011 Jul 22.
9
[Health technology assessment report: Computer-assisted Pap test for cervical cancer screening].[卫生技术评估报告:用于宫颈癌筛查的计算机辅助巴氏试验]
Epidemiol Prev. 2012 Sep-Oct;36(5 Suppl 3):e1-43.
10
Clinical effectiveness and cost-effectiveness of laparoscopic surgery for colorectal cancer: systematic reviews and economic evaluation.腹腔镜手术治疗结直肠癌的临床疗效与成本效益:系统评价与经济学评估
Health Technol Assess. 2006 Nov;10(45):1-141, iii-iv. doi: 10.3310/hta10450.

引用本文的文献

1
Artificial intelligence for the science of evidence synthesis: how good are AI-powered tools for automatic literature screening?用于证据综合科学的人工智能:人工智能驱动的自动文献筛选工具效果如何?
BMC Med Res Methodol. 2025 Aug 25;25(1):199. doi: 10.1186/s12874-025-02644-9.
2
Evaluating a Customized Version of ChatGPT for Systematic Review Data Extraction in Health Research: Development and Usability Study.评估定制版ChatGPT在健康研究系统评价数据提取中的应用:开发与可用性研究
JMIR Form Res. 2025 Aug 11;9:e68666. doi: 10.2196/68666.
3
Evaluation of SURUS: a named entity recognition NLP system to extract knowledge from interventional study records.SURUS评估:一种用于从介入性研究记录中提取知识的命名实体识别自然语言处理系统。
BMC Med Res Methodol. 2025 Jul 31;25(1):184. doi: 10.1186/s12874-025-02624-z.
4
A foundation model for human-AI collaboration in medical literature mining.医学文献挖掘中人类与人工智能协作的基础模型。
ArXiv. 2025 Jan 27:arXiv:2501.16255v1.
5
Using Artificial Intelligence Tools as Second Reviewers for Data Extraction in Systematic Reviews: A Performance Comparison of Two AI Tools Against Human Reviewers.使用人工智能工具作为系统评价中数据提取的二审人员:两种人工智能工具与人类评审员的性能比较
Cochrane Evid Synth Methods. 2025 Jul 14;3(4):e70036. doi: 10.1002/cesm.70036. eCollection 2025 Jul.
6
Will AI speed up literature reviews or derail them entirely?人工智能会加快文献综述的速度还是会使其完全偏离正轨?
Nature. 2025 Jul;643(8071):329-331. doi: 10.1038/d41586-025-02069-w.
7
Use of deep learning-based NLP models for full-text data elements extraction for systematic literature review tasks.基于深度学习的自然语言处理模型在系统文献综述任务的全文数据元素提取中的应用。
Sci Rep. 2025 Jun 3;15(1):19379. doi: 10.1038/s41598-025-03979-5.
8
Examining the availability/findability of stimuli employed in social media and body image research.审视社交媒体和身体形象研究中所使用刺激因素的可得性/可查找性。
PLoS One. 2025 May 22;20(5):e0324514. doi: 10.1371/journal.pone.0324514. eCollection 2025.
9
Large Language Model-Supported Systematic Reviews to Augment Clinical Guideline Development: An American Gastroenterological Association Pilot.支持临床指南制定的大语言模型系统评价:美国胃肠病学会试点项目
Gastroenterology. 2025 Sep;169(4):715-717. doi: 10.1053/j.gastro.2025.03.034. Epub 2025 Apr 6.
10
Enhancing systematic literature reviews with generative artificial intelligence: development, applications, and performance evaluation.利用生成式人工智能加强系统文献综述:开发、应用及性能评估
J Am Med Inform Assoc. 2025 Apr 1;32(4):616-625. doi: 10.1093/jamia/ocaf030.

本文引用的文献

1
Drugs, Devices, and the FDA: Part 2: An Overview of Approval Processes: FDA Approval of Medical Devices.药物、器械与美国食品药品监督管理局:第二部分:审批流程概述:医疗器械的美国食品药品监督管理局审批
JACC Basic Transl Sci. 2016 Jun 27;1(4):277-287. doi: 10.1016/j.jacbts.2016.03.009. eCollection 2016 Jun.
2
Drugs, Devices, and the FDA: Part 1: An Overview of Approval Processes for Drugs.药物、器械与美国食品药品监督管理局:第一部分:药物审批流程概述
JACC Basic Transl Sci. 2016 Apr 25;1(3):170-179. doi: 10.1016/j.jacbts.2016.03.002. eCollection 2016 Apr.
3
A Deep Learning Method to Automatically Identify Reports of Scientifically Rigorous Clinical Research from the Biomedical Literature: Comparative Analytic Study.一种从生物医学文献中自动识别科学严谨的临床研究报告的深度学习方法:比较分析研究。
J Med Internet Res. 2018 Jun 25;20(6):e10281. doi: 10.2196/10281.
4
Meta-analysis and the science of research synthesis.元分析与研究综合的科学。
Nature. 2018 Mar 7;555(7695):175-182. doi: 10.1038/nature25753.
5
Analysis of the time and workers needed to conduct systematic reviews of medical interventions using data from the PROSPERO registry.利用PROSPERO注册库的数据,分析对医学干预措施进行系统评价所需的时间和人员。
BMJ Open. 2017 Feb 27;7(2):e012545. doi: 10.1136/bmjopen-2016-012545.
6
Consider drug efficacy before first-in-human trials.在首次人体试验之前考虑药物疗效。
Nature. 2017 Jan 30;542(7639):25-27. doi: 10.1038/542025a.
7
Network meta-analyses performed by contracting companies and commissioned by industry.由签约公司执行并受行业委托进行的网络荟萃分析。
Syst Rev. 2016 Nov 25;5(1):198. doi: 10.1186/s13643-016-0377-3.
8
Meta-analysis in clinical trials revisited.再谈临床试验中的荟萃分析。
Contemp Clin Trials. 2015 Nov;45(Pt A):139-45. doi: 10.1016/j.cct.2015.09.002. Epub 2015 Sep 4.
9
"Right-to-Try" Legislation: Progress or Peril?“尝试权”立法:进步还是风险?
J Clin Oncol. 2015 Aug 20;33(24):2597-9. doi: 10.1200/JCO.2015.62.8057. Epub 2015 Jul 20.
10
Publish or perish: Where are we heading?不发表就灭亡:我们正走向何方?
J Res Med Sci. 2014 Feb;19(2):87-9.