Otolaryngology Unit, Santi Paolo e Carlo Hospital, Department of Health Sciences, Università degli Studi di Milano, Milan, Italy.
Ohio University Heritage College of Osteopathic Medicine, Dublin, OH, USA.
Eur Arch Otorhinolaryngol. 2023 Feb;280(2):529-542. doi: 10.1007/s00405-022-07701-3. Epub 2022 Oct 19.
This PRISMA-compliant systematic review aims to analyze the existing applications of artificial intelligence (AI), machine learning, and deep learning for rhinological purposes and compare works in terms of data pool size, AI systems, input and outputs, and model reliability.
MEDLINE, Embase, Web of Science, Cochrane Library, and ClinicalTrials.gov databases. Search criteria were designed to include all studies published until December 2021 presenting or employing AI for rhinological applications. We selected all original studies specifying AI models reliability. After duplicate removal, abstract and full-text selection, and quality assessment, we reviewed eligible articles for data pool size, AI tools used, input and outputs, and model reliability.
Among 1378 unique citations, 39 studies were deemed eligible. Most studies (n = 29) were technical papers. Input included compiled data, verbal data, and 2D images, while outputs were in most cases dichotomous or selected among nominal classes. The most frequently employed AI tools were support vector machine for compiled data and convolutional neural network for 2D images. Model reliability was variable, but in most cases was reported to be between 80% and 100%.
AI has vast potential in rhinology, but an inherent lack of accessible code sources does not allow for sharing results and advancing research without reconstructing models from scratch. While data pools do not necessarily represent a problem for model construction, presently available tools appear limited in allowing employment of raw clinical data, thus demanding immense interpretive work prior to the analytic process.
本符合 PRISMA 标准的系统评价旨在分析人工智能（AI）、机器学习和深度学习在鼻科学中的现有应用，并比较各项研究在数据池规模、AI 系统、输入和输出以及模型可靠性方面的差异。
检索 MEDLINE、Embase、Web of Science、Cochrane 图书馆和 ClinicalTrials.gov 数据库，设计检索策略以纳入截至 2021 年 12 月所有提出或使用 AI 进行鼻科学应用的研究。我们选择了所有指定 AI 模型可靠性的原始研究。在去除重复项、摘要和全文筛选以及质量评估后，我们对符合条件的文章进行了数据池规模、使用的 AI 工具、输入和输出以及模型可靠性的回顾。
在 1378 篇独特的参考文献中，有 39 篇研究被认为符合条件。大多数研究（n=29）为技术论文。输入包括编译数据、口头数据和 2D 图像，而输出在大多数情况下为二分类或在名义类别中选择。最常使用的 AI 工具是编译数据的支持向量机和 2D 图像的卷积神经网络。模型可靠性各不相同，但在大多数情况下报告在 80%到 100%之间。
AI 在鼻科学中有广泛的应用潜力，但由于缺乏可访问的代码源，无法在不从头重新构建模型的情况下共享结果和推进研究。虽然数据池不一定是模型构建的问题，但目前可用的工具似乎在允许使用原始临床数据方面受到限制，因此在分析过程之前需要进行大量的解释工作。
