PDF(Pubmed)
Abstract：
Suicide remains a critical global health issue despite advancements in mental health treatment. The purpose of this analysis is to emphasize the development, patterns, and noteworthy outcomes of suicide prediction research. It also helps to uncover gaps and areas of under-researched topics within suicide prediction. A scientometric analysis was conducted using Biblioshiny and VOSviewer. To thoroughly assess the academic literature on suicide prediction, various scientometric methodologies such as trend analysis and citation analysis were employed. We utilized the temporal features of the Web of Science to analyze publication trends over time. Author affiliation data were used to investigate the geographic distribution of research. Cluster analysis was performed by grouping related keywords into clusters to identify overarching themes within the literature. A total of 1,703 articles from 828 different sources, spanning from 1942 to 2023, were collected for the analysis. Machine learning techniques might have a big influence on suicide-related event prediction, which would enhance attempts at suicide prevention and intervention. The conceptual understanding of suicide prediction is enhanced by scientometric analysis, which further uncovers the research gap and literature in this area. Suicide prediction research underscores that suicidal behavior is not caused by a single factor but is the result of a complex interplay of multiple factors. These factors may include biological, psychological, social, and environmental factors. Understanding and integrating these factors into predictive models is a theoretical advancement in the field. Unlike previous bibliometric studies in the field of suicide prediction that have typically focused on specific subtopics or data sources, our analysis offers a comprehensive mapping of the entire landscape. We encompass a wide range of suicide prediction literature, including research from medical, psychological, and social science domains, thus providing a holistic overview.
摘要：
尽管心理健康治疗取得了进步，但自杀仍然是一个关键的全球健康问题。这种分析的目的是强调发展，模式,以及自杀预测研究的值得注意的结果。它还有助于发现自杀预测中研究不足的主题的差距和领域。使用Biblioshiny和VOSviewer进行了科学计量分析。为了彻底评估关于自杀预测的学术文献，采用了各种科学计量学方法，如趋势分析和引文分析。我们利用WebofScience的时间特征来分析一段时间内的出版趋势。作者隶属关系数据用于调查研究的地理分布。通过将相关关键词分组到集群中来进行聚类分析，以识别文献中的总体主题。共有来自828个不同来源的1703篇文章，从1942年到2023年，收集用于分析。机器学习技术可能会对自杀相关事件的预测产生重大影响。这将加强自杀预防和干预的尝试。通过科学计量学分析增强了对自杀预测的概念理解，这进一步揭示了该领域的研究空白和文献。自杀预测研究强调，自杀行为不是由单个因素引起的，而是多个因素复杂相互作用的结果。这些因素可能包括生物学，心理,社会,和环境因素。理解并将这些因素整合到预测模型中是该领域的理论进步。与以前自杀预测领域的文献计量学研究不同，这些研究通常集中在特定的子主题或数据源上，我们的分析提供了整个景观的全面绘图。我们涵盖了广泛的自杀预测文献，包括医学研究，心理,和社会科学领域，从而提供了一个整体的概述。
