Semi-automated title-abstract screening using natural language processing and machine learning.

IF 6.3 4区医学 Q1 MEDICINE, GENERAL & INTERNAL

Systematic Reviews Pub Date : 2024-11-01 DOI:10.1186/s13643-024-02688-w

Maximilian Pilz, Samuel Zimmermann, Juliane Friedrichs, Enrica Wördehoff, Ulrich Ronellenfitsch, Meinhard Kieser, Johannes A Vey

{"title":"Semi-automated title-abstract screening using natural language processing and machine learning.","authors":"Maximilian Pilz, Samuel Zimmermann, Juliane Friedrichs, Enrica Wördehoff, Ulrich Ronellenfitsch, Meinhard Kieser, Johannes A Vey","doi":"10.1186/s13643-024-02688-w","DOIUrl":null,"url":null,"abstract":"Background: Title-abstract screening in the preparation of a systematic review is a time-consuming task. Modern techniques of natural language processing and machine learning might allow partly automatization of title-abstract screening. In particular, clear guidance on how to proceed with these techniques in practice is of high relevance.Methods: This paper presents an entire pipeline how to use natural language processing techniques to make the titles and abstracts usable for machine learning and how to apply machine learning algorithms to adequately predict whether or not a publication should be forwarded to full text screening. Guidance for the practical use of the methodology is given.Results: The appealing performance of the approach is demonstrated by means of two real-world systematic reviews with meta analysis.Conclusions: Natural language processing and machine learning can help to semi-automatize title-abstract screening. Different project-specific considerations have to be made for applying them in practice.","PeriodicalId":22162,"journal":{"name":"Systematic Reviews","volume":"13 1","pages":"274"},"PeriodicalIF":6.3000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11529237/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Systematic Reviews","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s13643-024-02688-w","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Title-abstract screening in the preparation of a systematic review is a time-consuming task. Modern techniques of natural language processing and machine learning might allow partly automatization of title-abstract screening. In particular, clear guidance on how to proceed with these techniques in practice is of high relevance.

Methods: This paper presents an entire pipeline how to use natural language processing techniques to make the titles and abstracts usable for machine learning and how to apply machine learning algorithms to adequately predict whether or not a publication should be forwarded to full text screening. Guidance for the practical use of the methodology is given.

Results: The appealing performance of the approach is demonstrated by means of two real-world systematic reviews with meta analysis.

Conclusions: Natural language processing and machine learning can help to semi-automatize title-abstract screening. Different project-specific considerations have to be made for applying them in practice.

查看原文本刊更多论文

利用自然语言处理和机器学习进行标题-摘要半自动筛选。

背景：编写系统综述时的标题-摘要筛选是一项耗时的工作。现代自然语言处理和机器学习技术可使标题-摘要筛选部分自动化。特别是，如何在实践中使用这些技术的明确指导具有重要意义：本文介绍了如何使用自然语言处理技术使标题和摘要可用于机器学习，以及如何应用机器学习算法充分预测出版物是否应转入全文筛选的整个流程。此外，还给出了该方法的实际使用指南：结果：通过两篇真实世界的系统综述和元分析，展示了该方法的吸引力：自然语言处理和机器学习有助于实现标题-摘要筛选的半自动化。在实际应用中，必须针对具体项目做出不同的考虑。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Systematic Reviews Medicine-Medicine (miscellaneous)

CiteScore

8.30

自引率

0.00%

发文量

241

审稿时长

11 weeks

期刊介绍： Systematic Reviews encompasses all aspects of the design, conduct and reporting of systematic reviews. The journal publishes high quality systematic review products including systematic review protocols, systematic reviews related to a very broad definition of health, rapid reviews, updates of already completed systematic reviews, and methods research related to the science of systematic reviews, such as decision modelling. At this time Systematic Reviews does not accept reviews of in vitro studies. The journal also aims to ensure that the results of all well-conducted systematic reviews are published, regardless of their outcome.