Development and Validation of a Literature Screening Tool: Few-Shot Learning Approach in Systematic Reviews
Our FSL framework demonstrates the potential for reducing workload in SR screening by over 50%. However, the model did not achieve 100% recall at this threshold, highlighting the potential for omitting eligible studies. Future work should focus on developing a web application to implement the FSL framework, making it accessible to researchers.
Authors
- Amarit Tansawet (ORCID: https://orcid.org/0000-0002-2040-7970)
- Panu Looareesuwan (ORCID: https://orcid.org/0000-0001-8179-9149)
- Wanchana Ponthongmak (ORCID: https://orcid.org/0000-0002-9896-1349)
- John Attia (ORCID: https://orcid.org/0000-0001-9800-1308)
- Gareth J. McKay (ORCID: https://orcid.org/0000-0001-8197-6280)
- Ammarin Thakkinstian (ORCID: https://orcid.org/0000-0001-9991-386X)
- Pawin Numthavaj (ORCID: https://orcid.org/0000-0002-1369-2945)
- Phongphat Wiwatthanasetthakarn (ORCID: https://orcid.org/0009-0003-8656-1932)
Institutions
- Queen's University Belfast (GB)
- Mahidol University (TH)
- Navamindradhiraj University (TH)
- Vajira Hospital (TH)
- Ramathibodi Hospital (TH)
- University of Newcastle Australia (AU)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2024-12-11
- DOI
- https://doi.org/10.2196/56863
- Primary Topic
- Health Sciences Research and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Mahidol University
- National Research Council of Thailand