Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 15 min ago
Peer-reviewedCC BY 4.0NPJ Digital Medicine

Fast information and slow evidence in the large language models era

  • Yilan Wu1,2
  • Ariel Yuhan Ong1,3,4,5
  • Kuang Hu1,5
  • Tien Yin Wong2,6,7
  • Pearse A. Keane1,5
7 affiliations
  1. 1Institute of Ophthalmology, University College London, London, UK
  2. 2Beijing Visual Science and Translational Eye Research Institute (BERI), Beijing Tsinghua Changgung Hospital Eye Center, School of Clinical Medicine, Tsinghua Medicine, Tsinghua University, Beijing, China
  3. 3Moorfields Eye Hospital NHS Foundation Trust, London, UK
  4. 4Oxford Eye Hospital, Oxford University NHS Foundation Trust, Oxford, UK
  5. 5NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust, London, UK
  6. 6School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University, Beijing, China
  7. 7Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
Read full textPDFDOICite

Abstract

LLMs accelerate medical information work, but speed of synthesis does not justify reliance. As T.S. Eliot asked, “Where is the knowledge we have lost in information?” Using a data-information-evidence-practice hierarchy, LLM outputs enter clinical setting as information and become evidence only through appraisal, validation, and contextual judgement. We highlight how LLMs can support evidence infrastructures, clarify evidence boundaries, and reshape clinical expertise to strengthen rather than replace evidence-based medicine.

Related

  1. Reply to: "Evaluating the Clinical Readiness of General-Purpose Large Language Models in Evidence Synthesis".
    Masaki Sakamoto, Shintaro Honda, Bungo Otsuki +9
    Spine surgery and related researchPeer-reviewedCC BY-NC-NDFull textEpidemiology & public healthEurope PMC
  2. Extraction of clinical information from faxed medical records using a small local large language model pipeline on consumer hardware
    Z. Tang
    medRxivPreprintCC BY-NCFull textEpidemiology & public healthmedRxiv
  3. Quality, Readability, and Content Deficiencies of Three Large Language Models in Bee Sting Health Information: A Comparative Evaluation with Patient Perspectives
    R. Xu, L. Yang, X. Zhang +3
    medRxivPreprintCC BYFull textEpidemiology & public healthmedRxiv
  4. Performance of large language models in providing patient- oriented information on gingival recession: a comparative study.
    Sultan Albeshri
    The Saudi dental journalPeer-reviewedCC BY-NC-NDFull textEpidemiology & public healthEurope PMCDOAJ
  5. Quality, readability, and information fidelity of large language model–generated versus physician-authored informed-consent content for targeted therapies: a blinded, paired comparative study
    Yue Xie, Yuan Gao, Jiajing Peng +6
    Frontiers in PharmacologyPeer-reviewedCC BY 4.0Pharmacology & toxicologyFrontiersCrossref

Cite

BibTeXRIS
BibTeX
@article{wu2026fast,
  title = {{Fast information and slow evidence in the large language models era}},
  author = {Yilan Wu and Ariel Yuhan Ong and Kuang Hu and Tien Yin Wong and Pearse A. Keane},
  journal = {NPJ Digital Medicine},
  year = {2026},
  month = jul,
  doi = {10.1038/s41746-026-02909-7},
  url = {https://doi.org/10.1038/s41746-026-02909-7},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Fast information and slow evidence in the large language models era
AU  - Yilan Wu
AU  - Ariel Yuhan Ong
AU  - Kuang Hu
AU  - Tien Yin Wong
AU  - Pearse A. Keane
PY  - 2026
DA  - 2026/07/03
JO  - NPJ Digital Medicine
DO  - 10.1038/s41746-026-02909-7
UR  - https://doi.org/10.1038/s41746-026-02909-7
AB  - LLMs accelerate medical information work, but speed of synthesis does not justify reliance. As T.S. Eliot asked, “Where is the knowledge we have lost in information?” Using a data-information-evidence-practice hierarchy, LLM outputs enter clinical setting as information and become evidence only through appraisal, validation, and contextual judgement. We highlight how LLMs can support evidence infrastructures, clarify evidence boundaries, and reshape clinical expertise to strengthen rather than replace evidence-based medicine.
SN  - 2398-6352
ER  -