Section of Hygiene, Department of Life Sciences and Public Health, Università Cattolica Del Sacro Cuore, Rome, Italy.
Front Public Health. 2022 Aug 12;10:949377. doi: 10.3389/fpubh.2022.949377. eCollection 2022.
Clinical trials are essential for bringing new drugs, technologies and procedures to the market and clinical practice. Considering the design and the four-phase development, only 10% of them complete the entire process, partly due to the increasing costs and complexity of clinical trials. This low completion rate has a huge negative impact in terms of population health, quality of care and health economics and sustainability. Automating some of the process' tasks with artificial intelligence (AI) tools could optimize some of the most burdensome ones, like patient selection, matching and enrollment; better patient selection could also reduce harmful treatment side effects. Although the pharmaceutical industry is embracing artificial AI tools, there is little evidence in the literature of their application in clinical trials.
To address this issue, we performed a scoping review. Following the PRISMA-ScR guidelines, we performed a search on PubMed for articles on the implementation of AI in the development of clinical trials.
The search yielded 772 articles, of which 15 were included. The articles were published between 2019 and 2022 and the results were presented descriptively. About half of the studies addressed the topic of patient recruitment; 12 articles reported specific examples of AI applications; five studies presented a quantitative estimate of the effectiveness of these tools.
All studies present encouraging results on the implementation of AI-based applications to the development of clinical trials. AI-based applications have a lot of potential, but more studies are needed to validate these tools and facilitate their adoption.
临床试验对于将新药、技术和程序推向市场和临床实践至关重要。考虑到设计和四阶段开发，只有 10%的临床试验完成了整个过程，部分原因是临床试验的成本和复杂性不断增加。这种低完成率对人口健康、护理质量和健康经济及可持续性产生了巨大的负面影响。通过人工智能（AI）工具自动化部分流程任务，可以优化其中一些最繁琐的任务，如患者选择、匹配和入组；更好的患者选择也可以减少有害的治疗副作用。尽管制药行业正在接受人工智能 AI 工具，但文献中几乎没有它们在临床试验中应用的证据。
为了解决这个问题，我们进行了范围综述。根据 PRISMA-ScR 指南，我们在 PubMed 上搜索了关于 AI 在临床试验开发中应用的文章。
搜索结果为 772 篇文章，其中 15 篇被纳入。这些文章发表于 2019 年至 2022 年，结果以描述性方式呈现。大约一半的研究涉及患者招募主题；12 篇文章报道了 AI 应用的具体例子；五篇研究报告了这些工具有效性的定量估计。
所有研究都对基于 AI 的应用于临床试验开发的实施结果表示了鼓舞人心。基于 AI 的应用具有很大的潜力，但需要更多的研究来验证这些工具并促进其采用。
