A biomedical BERT ensemble (TITAN-SR) outperformed active learning and LLM chatbots for systematic-review title and abstract screening: development and external validation

Tyler Pitre, Dena Zeraatkar, John Granton, Jason Busse, Bram Rochwerg, Gordon Guyatt

Open source

DOI
10.1016/j.jclinepi.2026.112514
Published
2026-09
Container
Journal of Clinical Epidemiology
Publisher
Elsevier BV
Open access
unknown

Credibility signals

uncertain Score 64/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1016/j.jclinepi.2026.112514,
  title = {A biomedical BERT ensemble (TITAN-SR) outperformed active learning and LLM chatbots for systematic-review title and abstract screening: development and external validation},
  author = {Tyler Pitre and Dena Zeraatkar and John Granton and Jason Busse and Bram Rochwerg and Gordon Guyatt},
  year = {2026},
  journal = {Journal of Clinical Epidemiology},
  doi = {10.1016/j.jclinepi.2026.112514},
  url = {https://doi.org/10.1016/j.jclinepi.2026.112514}
}

RIS

TY  - JOUR
TI  - A biomedical BERT ensemble (TITAN-SR) outperformed active learning and LLM chatbots for systematic-review title and abstract screening: development and external validation
AU  - Tyler Pitre
AU  - Dena Zeraatkar
AU  - John Granton
AU  - Jason Busse
AU  - Bram Rochwerg
AU  - Gordon Guyatt
PY  - 2026
JO  - Journal of Clinical Epidemiology
DO  - 10.1016/j.jclinepi.2026.112514
UR  - https://doi.org/10.1016/j.jclinepi.2026.112514
ER  - 

APA

Pitre, T., Zeraatkar, D., Granton, J., Busse, J., Rochwerg, B., & Guyatt, G. (2026). A biomedical BERT ensemble (TITAN-SR) outperformed active learning and LLM chatbots for systematic-review title and abstract screening: development and external validation. Journal of Clinical Epidemiology. https://doi.org/10.1016/j.jclinepi.2026.112514

Source records