Abstract：
BACKGROUND: Taxonomies are needed for automated analysis of clinical data in healthcare. Few reviews of the taxonomy development methods used in health sciences are found. This systematic review aimed to describe the scope of the available taxonomies relative to patient safety, the methods used for taxonomy development, and the strengths and limitations of the methods. The purpose of this systematic review is to guide future taxonomy development projects.
METHODS: The CINAHL, PubMed, Scopus, and Web of Science databases were searched for studies from January 2012 to April 25, 2023. Two authors selected the studies using inclusion and exclusion criteria and critical appraisal checklists. The data were analysed inductively, and the results were reported narratively.
RESULTS: The studies (n = 13) across healthcare concerned mainly taxonomies of adverse events and medication safety but little for specialised fields and information technology. Critical appraisal indicated inadequate reporting of the used taxonomy development methods. Ten phases of taxonomy development were identified: (1) defining purpose and (2) the theory base for development, (3) relevant data sources\' identification, (4) main terms\' identification and definitions, (5) items\' coding and pooling, (6) reliability and validity evaluation of coding and/or codes, (7) development of a hierarchical structure, (8) testing the structure, (9) piloting the taxonomy and (10) reporting application and validation of the final taxonomy. Seventeen statistical tests and seven software systems were utilised, but automated data extraction methods were used rarely. Multimethod and multi-stakeholder approach, code- and hierarchy testing and piloting were strengths and time consumption and small samples in testing limitations.
CONCLUSIONS: New taxonomies are needed on diverse specialities and information technology related to patient safety. Structured method is needed for taxonomy development, reporting and appraisal to strengthen taxonomies\' quality. A new guide was proposed for taxonomy development, for which testing is required. Prospero registration number CRD42023411022.
METHODS: The CINAHL, PubMed, Scopus, and Web of Science databases were searched for studies from January 2012 to April 25, 2023. Two authors selected the studies using inclusion and exclusion criteria and critical appraisal checklists. The data were analysed inductively, and the results were reported narratively.
RESULTS: The studies (n = 13) across healthcare concerned mainly taxonomies of adverse events and medication safety but little for specialised fields and information technology. Critical appraisal indicated inadequate reporting of the used taxonomy development methods. Ten phases of taxonomy development were identified: (1) defining purpose and (2) the theory base for development, (3) relevant data sources\' identification, (4) main terms\' identification and definitions, (5) items\' coding and pooling, (6) reliability and validity evaluation of coding and/or codes, (7) development of a hierarchical structure, (8) testing the structure, (9) piloting the taxonomy and (10) reporting application and validation of the final taxonomy. Seventeen statistical tests and seven software systems were utilised, but automated data extraction methods were used rarely. Multimethod and multi-stakeholder approach, code- and hierarchy testing and piloting were strengths and time consumption and small samples in testing limitations.
CONCLUSIONS: New taxonomies are needed on diverse specialities and information technology related to patient safety. Structured method is needed for taxonomy development, reporting and appraisal to strengthen taxonomies\' quality. A new guide was proposed for taxonomy development, for which testing is required. Prospero registration number CRD42023411022.
摘要：
背景：医疗保健中临床数据的自动分析需要分类。很少有关于健康科学中使用的分类学开发方法的评论。本系统综述旨在描述与患者安全相关的可用分类范围。用于分类学开发的方法，以及这些方法的优点和局限性。本系统综述的目的是指导未来的分类学发展项目。
方法：TheCINAHL，PubMed,Scopus,从2012年1月至2023年4月25日，搜索了WebofScience数据库的研究。两位作者使用纳入和排除标准以及关键评估清单选择了研究。数据进行了归纳分析，结果以叙述方式报告。
结果：整个医疗保健领域的研究（n=13）主要涉及不良事件和药物安全性的分类，但很少涉及专业领域和信息技术。关键评估表明，对所用分类学开发方法的报告不足。确定了分类学发展的十个阶段：（1）定义目的；（2）发展的理论基础，（3）相关数据源的识别，(4)主要术语的识别和定义，(5)项目编码和汇集，(6)编码和/或编码的可靠性和有效性评估，(7)发展层次结构，（8）测试结构，（9）试行分类法；（10）报告最终分类法的应用和验证。使用了十七个统计测试和七个软件系统，但是很少使用自动数据提取方法。多方法和多利益相关者方法，代码和层次结构测试和试点是优势和时间消耗和小样本测试的局限性。
结论：与患者安全相关的不同专业和信息技术需要新的分类法。分类学开发需要结构化方法，报告和评估，以加强分类质量。提出了一个新的分类学发展指南，需要进行测试。Prospero注册号CRD42023411022。
方法：TheCINAHL，PubMed,Scopus,从2012年1月至2023年4月25日，搜索了WebofScience数据库的研究。两位作者使用纳入和排除标准以及关键评估清单选择了研究。数据进行了归纳分析，结果以叙述方式报告。
结果：整个医疗保健领域的研究（n=13）主要涉及不良事件和药物安全性的分类，但很少涉及专业领域和信息技术。关键评估表明，对所用分类学开发方法的报告不足。确定了分类学发展的十个阶段：（1）定义目的；（2）发展的理论基础，（3）相关数据源的识别，(4)主要术语的识别和定义，(5)项目编码和汇集，(6)编码和/或编码的可靠性和有效性评估，(7)发展层次结构，（8）测试结构，（9）试行分类法；（10）报告最终分类法的应用和验证。使用了十七个统计测试和七个软件系统，但是很少使用自动数据提取方法。多方法和多利益相关者方法，代码和层次结构测试和试点是优势和时间消耗和小样本测试的局限性。
结论：与患者安全相关的不同专业和信息技术需要新的分类法。分类学开发需要结构化方法，报告和评估，以加强分类质量。提出了一个新的分类学发展指南，需要进行测试。Prospero注册号CRD42023411022。
