公众号 / 文章技术与安全

放射学研究教育中的开放问题:数据完整性、研究可重复性、同行评审、证据水平及与数据科学家的交叉融合

Open issues for education in radiological research: data integrity, study reproducibility, peer-review, levels of evidence, and cross-fertilization with data scientists.
PubMed 文献 · Radiol Med · 2022-12-31

本文讨论放射学研究教育中应回归「基本要素」,重点关注数据完整性(包括作者提交稿件时的声明)、研究结果的可重复性和同行评审过程。作者强调需将放射学研究的证据水平从诊断性能评估提升至诊断影响、治疗影响、患者结局和社会影响层面,并建议在影像组学和人工智能领域与数据科学家交叉融合,可让其参与临床科室工作。

要点

  • 放射学研究教育应强调数据完整性与研究可重复性
  • 证据水平需从诊断性能提升至诊断影响、治疗影响、患者结局和社会影响
  • 影像组学和人工智能研究应与数据科学家交叉融合

核心结论

  • 放射学研究教育需回归基本要素,关注数据完整性、可重复性和同行评审,并提升证据水平至诊断影响、治疗影响、患者结局和社会影响层面。

研究设计与样本

  • 本文为关于放射学研究教育开放问题的论述性文章,未报告系统检索范围、纳入文献数量或证据分级方法。

临床应用与阅片要点

  • 在放射学研究中应重视数据完整性声明、研究可重复性和同行评审过程。
  • 评估放射学研究时需关注其证据水平是否超越诊断性能,达到诊断影响、治疗影响、患者结局或社会影响层面。
  • 开展影像组学和人工智能研究时建议与数据科学家交叉融合,可考虑让其参与临床科室工作。

局限性

  • 本文为论述性文章,未报告系统检索策略、纳入文献数量或定量证据分级,结论基于作者观点。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

We are currently facing extraordinary changes. A harder and harder competition in the field of science is open in each country as well as in continents and worldwide. In this context, what should we teach to young students and doctors? There is a need to look backward and return to "fundamentals", i.e. the deep characteristics that must characterize the research in every field, even in radiology. In this article, we focus on data integrity (including the "declarations" given by the authors who submit a manuscript), reproducibility of study results, and the peer-review process. In addition, we highlight the need of raising the level of evidence of radiological research from the estimation of diagnostic performance to that of diagnostic impact, therapeutic impact, patient outcome, and social impact. Finally, on the emerging topic of radiomics and artificial intelligence, the recommendation is to aim for cross-fertilization with data scientists, possibly involving them in the clinical departments.

来源:Radiol Med,查看原文。版权归原作者所有。

引用

  1. Sardanelli, Colarieti. Open issues for education in radiological research: data integrity, study reproducibility, peer-review, levels of evidence, and cross-fertilization with data scientists. Radiol Med. 2022. PMID: 36586083. doi:10.1007/s11547-022-01582-6

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。