跳到正文
原文
Nature 健康护理主题·· 24 天前AI 评分51

急诊科 2496 例前瞻性研究:AI 辅助放射技师骨折判读准确率升至 98.0%

Radiographer fracture detection with and without AI assistance in prospective emergency department use

AI 导读

在一家急诊科为期三个月的前瞻性部署中,13 名放射技师借助 AI 判读 2496 例肌骨影像,准确率由 97.6% 升至 98.0%(p=0.0064)。AI 独立判读敏感度为 75.6%,对细微骨折降至 46.2%,低于技师基线的 91.6%。技师仅在 729 例判读分歧中的 11 例改变决定,8.8% 的检查未返回完整 AI 输出,研究未测量下游临床结局。

正文

npj Digital Medicine (2026) Cite this article

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

Abstract

Artificial intelligence (AI) systems for fracture detection perform strongly in controlled settings, but prospective real-world evidence is limited. In a three-month deployment in one emergency department, thirteen radiographers in a radiographer-led screening programme independently interpreted 2496 consecutive musculoskeletal examinations (one radiographer per examination), reviewed output from a commercial deep-learning system, then recorded a final decision, giving 2496 paired reads against a radiologist reference standard. Standalone AI sensitivity was 75.6%, falling to 46.2% for subtle fractures, below the radiographers’ baseline sensitivity of 91.6%. Radiographers’ baseline accuracy was high (97.6%; specificity 99.0%) and improved modestly with AI assistance (98.0%; exact McNemar p = 0.0064). With AI assistance, radiographers corrected 11 errors and introduced 1, a net gain of 10 cases. Subgroup gains were directionally consistent but not significant after correction. Radiographers changed their decision in only 11 of 729 discordant cases, and most negative interactions were correct AI recommendations not adopted. No or incomplete AI output was returned for 8.8% of acquired examinations. AI assistance delivered a small, selective benefit arising from complementary rather than superior algorithmic performance. Operational reliability proved as consequential as diagnostic accuracy, and behavioural inferences rest on few events. Downstream clinical outcomes were not measured.

Acknowledgements

The authors would like to thank AZmed and CARPL for technical support throughout the pre-, during and post-deployment phases.

Author information

Authors and Affiliations

  1. Department of Musculoskeletal Radiology (Primary), Singapore, Singapore

    Jin Rong Tan, May San Mak, Siew Kune Wong & Meng Ai Png

  2. Duke-NUS Medical School, Singapore, Singapore

    Jin Rong Tan, Anh Nguyen Tuan Tran, May San Mak, Siew Kune Wong & Meng Ai Png

  3. Department of Cardiothoracic and Abdominal Radiology (Primary), Singapore, Singapore

    Anh Nguyen Tuan Tran

  4. Radiography Department (Primary), Singapore, Singapore

    Wei Yow Sim & Jia Rong Jonathan Mok

  5. Imaging Informatics (Primary), Singapore, Singapore

    Felicia Hui Min Thng & Jason Hong Seng Toh

Authors

  1. Jin Rong Tan
  2. Anh Nguyen Tuan Tran
  3. Wei Yow Sim
  4. Jia Rong Jonathan Mok
  5. Felicia Hui Min Thng
  6. Jason Hong Seng Toh
  7. May San Mak
  8. Siew Kune Wong
  9. Meng Ai Png

Corresponding author

Correspondence to Jin Rong Tan.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tan, J.R., Tran, A.N.T., Sim, W.Y. et al. Radiographer fracture detection with and without AI assistance in prospective emergency department use. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03313-x

Download citation

  • Received: 30 May 2026

  • Accepted: 15 September 2026

  • Published: 27 October 2026

  • DOI: https://doi.org/10.1038/s41746-026-03313-x

来源:Nature 健康护理主题 · nature.com