Ordak Michal
Department of Pharmacotherapy and Pharmaceutical Care, Faculty of Pharmacy, Medical University of Warsaw, Banacha 1 Str., 02-097 Warsaw, Poland.
Clin Med (Lond). 2024 Oct 18:100257. doi: 10.1016/j.clinme.2024.100257.
Contemporary observations indicate insufficient quality in the reporting of statistical data. Despite the publication of the SAMPL guidelines in 2015, they have not been widely adopted. The aim of this article is to highlight the incorporation of SAMPL Guidelines in the statistical reviews of articles related to clinical medicine, as well as the changes implemented by authors in revised manuscripts as a result of such guidance. An additional objective is to provide recommendations for biomedical journals regarding the necessity of integrating SAMPL Guidelines into their daily practices.
The study incorporated 100 selected statistical reviews of original clinical medicine articles from 8 biomedical journals, conducted between 2016 and 2023. Each of these reviews suggested specific SAMPL Guidelines to be implemented in the revised manuscript. It was evaluated which specific SAMPL Guidelines were most frequently enforced and what changes resulted from their implementation.
Seventy-five percent of the manuscripts in question garnered acceptance following a solitary round of statistical evaluation. Among the most frequently recommended and subsequently implemented SAMPL Guidelines by the authors are a more thorough description of the purpose of the applied statistical tests (65%), indication of the practical significance of the obtained results, including calculation of relevant effect size measures (64%), analysis of assumptions necessary for the application of specific statistical tests (58%), and consideration of the impact of outlier values on the obtained results (34%).
To improve the quality of statistical reporting in biomedical journals, greater emphasis should be placed on implementing SAMPL Guidelines.
当代观察表明统计数据报告的质量不足。尽管2015年发布了《统计分析与医学出版列表（SAMPL）指南》，但它们尚未得到广泛采用。本文的目的是强调在临床医学相关文章的统计审查中纳入SAMPL指南，以及作者因这种指导在修订稿件中所做的更改。另一个目标是就生物医学期刊将SAMPL指南纳入日常实践的必要性提供建议。
该研究纳入了2016年至2023年间对8种生物医学期刊的100篇原创临床医学文章进行的选定统计审查。这些审查中的每一篇都建议在修订稿件中实施特定的SAMPL指南。评估了哪些特定的SAMPL指南被最频繁地执行以及执行后产生了哪些变化。
75%的相关稿件在一轮统计评估后获得接受。作者最常推荐并随后实施的SAMPL指南包括更全面地描述所应用统计检验的目的（65%）、指出所得结果的实际意义，包括计算相关效应量指标（64%）、分析应用特定统计检验所需的假设（58%）以及考虑异常值对所得结果的影响（34%）。
为提高生物医学期刊统计报告的质量，应更加强调实施SAMPL指南。
