Scholarlink

<p>In this study, we present the <i>AIM Review Tool</i>, a modern web-based application that integrates active and supervised machine learning to accelerate the screening of publications for systematic reviews. <i>AIM Review</i> combines advanced text vectorization methods with machine learning models executed directly in the web browser, enabling rapid and privacy-preserving analysis. Unlike existing tools, <i>AIM Review</i> uniquely incorporates nested cross-validation and semi-automated screening strategies, enhancing both efficiency and precision in evidence synthesis. Using six real-world case studies across various topics, we demonstrate substantial workload reductions through active learning, with the percentage of publications not requiring screening while achieving ≥95% recall (WSS<sub>95%</sub>) ranging from 20% to 95%. Supervised learning pipelines trained on a subset of screened records predicted the relevance of unscreened publications with balanced accuracies between 75% and 87%. <i>AIM Review</i> provides a flexible, scalable, and accessible solution for large-scale literature screening and can be readily integrated into existing manual workflows.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AIM review tool: artificial intelligence for smarter systematic review screening

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月21日

查看全文
  • Sergio Mena,
  • Esther Rituerto-González,
  • Fiona Coutts,
  • Jana von Trott,
  • Grace R. Jacobs,
  • Linda Bryant,
  • Louise Moles,
  • Nicoleta Sirbu,
  • Liisi Promet,
  • Dominic Oliver,
  • Muhammad S. Ahmed,
  • Paolo Fusar-Poli,
  • Marian J. Bakermans-Kranenburg,
  • Marinus H. van IJzendoorn,
  • Nikolaos Koutsouleris,
  • Paris Alexandros Lalousis

摘要

In this study, we present the AIM Review Tool, a modern web-based application that integrates active and supervised machine learning to accelerate the screening of publications for systematic reviews. AIM Review combines advanced text vectorization methods with machine learning models executed directly in the web browser, enabling rapid and privacy-preserving analysis. Unlike existing tools, AIM Review uniquely incorporates nested cross-validation and semi-automated screening strategies, enhancing both efficiency and precision in evidence synthesis. Using six real-world case studies across various topics, we demonstrate substantial workload reductions through active learning, with the percentage of publications not requiring screening while achieving ≥95% recall (WSS95%) ranging from 20% to 95%. Supervised learning pipelines trained on a subset of screened records predicted the relevance of unscreened publications with balanced accuracies between 75% and 87%. AIM Review provides a flexible, scalable, and accessible solution for large-scale literature screening and can be readily integrated into existing manual workflows.