[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118546-en":3,"doc-seo-118546-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118546,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Semi-automated title-abstract screening - using natural language processing and machine learning","Title-abstract screening during systematic review preparation consumes substantial reviewer time, especially when thousands of biomedical citations must be screened in two stages for inclusion versus exclusion. The paper presents a practical NLP-to-ML pipeline that converts titles and abstracts into machine-learning-ready representations and trains algorithms to predict forward-to-full-text decisions. Guidance is provided for applying the approach in project-specific settings, and performance is evaluated on two real-world systematic reviews with meta-analysis.","Pilz et al. Systematic Reviews (2024) 13:274 [https://doi.org/10.1186/s13643-024-02688-w](https://doi.org/10.1186/s13643-024-02688-w)  \nSystematic Reviews  \n RESEARCH Open Access  \nSemi-automated title-abstract screening  \nusing natural language processing and machine learning  \nMaximilian Pilz 1,2* , Samuel Zimmermann 1, Juliane Friedrichs3, Enrica Wördehoff3, Ulrich Ronellenfitsch3, Meinhard Kieser1 and Johannes A. Vey 1  \nAbstract  \nBackground 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.  \nResults The appealing performance of the approach is demonstrated by means of two real-world systematic reviews with meta analysis.  \nConclusions 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.  \nKeywords Machine learning, Natural language processing, Language models, Systematic review, Meta analysis, Automatization, Title-abstract screening  \nBackground  \nCollecting knowledge from different studies by combining them within a systematic review with or without meta analysis is an important contribution to the generation of high-level evidence in medicine. This evidence is often used for the development of trustworthy guidelines  \n*Correspondence:  \nMaximilian Pilz [maximilian.pilz@itwm.fraunhofer.de](maximilian.pilz@itwm.fraunhofer.de)  \n1 University of Heidelberg- Institute of Medical Biometry, Heidelberg, Germany  \n2 Fraunhofer Institute for Industrial Mathematics-Department of Optimization, Kaiserslautern, Germany  \n3 Medical Faculty of the Martin Luther University Halle-WittenbergDepartment of Visceral, Vascular and Endocrine Surgery, Halle (Saale), Germany  \nand to inform policy makers, health care providers, and patients [1]. However, collecting the information included in different studies is a time-consuming task and the amount of biomedical literature is growing. The comprehensive literature search should be as extensive as possible to identify all relevant studies and to reduce the risk of reporting bias. As a consequence, thousands of citations matching the search criteria may be found. Subsequently, these citations need to be screened in two stages with regard to the inclusion and exclusion criteria to answer a particular medical research question. In a first stage, the abstracts of all identified studies are screened and determined to be relevant or not. In the second stage, the full texts of the relevant studies are assessed regarding inclusion in the systematic review meeting the specific criteria.  \n© The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from","cbCaiteXyWTkTSly","https://ap.wps.com/l/cbCaiteXyWTkTSly","pdf",1588396,1,14,"English","en",105,"# Abstract\n## Background\n## Methods\n## Results\n## Conclusions\n# Background\n## Two-stage screening workflow\n## Need for (semi-)automation\n# Related tools and approaches\n## Software for TIAB screening","[{\"question\":\"Why is title-abstract screening time-consuming in systematic reviews?\",\"answer\":\"Because reviewers must read and judge large numbers of citations, typically with independent decisions and later resolution of disagreements. The task relies on plain text interpretation and is repeated in two stages for inclusion versus exclusion.\"},{\"question\":\"What does the proposed semi-automated pipeline do?\",\"answer\":\"It converts titles and abstracts into a dataset usable for machine learning and then applies machine learning algorithms to predict whether a publication should be forwarded to full-text screening.\"},{\"question\":\"How is the approach evaluated in the paper?\",\"answer\":\"Performance is demonstrated using two real-world systematic reviews with meta-analysis, showing that NLP and machine learning can effectively semi-automatize title-abstract screening.\"}]","Semi-automated title-abstract screening - using natural language processing and machine learning | PDF",1785684079,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"semi-automated-title-abstract-screening-using-natural-language-processing-and-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/semi-automated-title-abstract-screening-using-natural-language-processing-and-machine-learning/118546/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is title-abstract screening time-consuming in systematic reviews?","Question",{"text":75,"@type":76},"Because reviewers must read and judge large numbers of citations, typically with independent decisions and later resolution of disagreements. The task relies on plain text interpretation and is repeated in two stages for inclusion versus exclusion.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the proposed semi-automated pipeline do?",{"text":80,"@type":76},"It converts titles and abstracts into a dataset usable for machine learning and then applies machine learning algorithms to predict whether a publication should be forwarded to full-text screening.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the approach evaluated in the paper?",{"text":84,"@type":76},"Performance is demonstrated using two real-world systematic reviews with meta-analysis, showing that NLP and machine learning can effectively semi-automatize title-abstract screening.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]