Applying machine learning to enhance core outcome set development: automating the data extraction and classification of outcomes
This study demonstrates the feasibility of applying ML-based outcome extraction and classification within a specific COS development context for lower limb lengthening surgery. By reducing annotation requirements from 149 to just 20 articles while maintaining high accuracy, our approach offers a scalable, reproducible solution that substantially reduces the manual workload in COS development. This pipeline can play a significant role in streamlining evidence synthesis processes, potentially accelerating the generation of outcome lists for consensus-building exercises in COS development.
Authors
- Hans‐Christen Husum (ORCID: https://orcid.org/0000-0001-6953-042X)
- Shima Gholinezhad (ORCID: https://orcid.org/0000-0002-0364-8844)
- Ole Rahbek (ORCID: https://orcid.org/0000-0002-5602-4533)
- Ali Yalçınkaya (ORCID: https://orcid.org/0000-0002-5427-8118)
- Søren Kold (ORCID: https://orcid.org/0000-0002-3387-1473)
- Kristian Gade Kjelmann
Institutions
- Nationwide Children's Hospital (US)
- Aalborg University Hospital (DK)
- Regional Hospital Randers (DK)
- Aalborg University (DK)
Publication Details
- Journal
- Journal of Orthopaedic Surgery and Research
- Published
- 2025-11-07
- DOI
- https://doi.org/10.1186/s13018-025-06386-8
- Primary Topic
- Total Knee Arthroplasty Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Netherlands eScience Center
- Danish e-Infrastructure Cooperation
- Syddansk Universitet