SynSight — 通过合成数据提高快速诊断测试人工智能解读的公平性
Synthetic data to lower barriers towards equitable artificial intelligence in rapid diagnostic test interpretation
研究团队开发了SynSight — 一种基于合成数据的机器学习快速诊断测试分割和分类管道,已在HIV和COVID-19测试中验证(敏感性98%,特异性99%,准确率高达99%)。该方法无需使用真实世界图像即可快速训练机器学习模型,有助于跟上新测试的开发步伐。
- Brief Communication
- Open access
- Published: 10 November 2026
- Elliott Rogers ORCID: orcid.org/0000-0002-8348-86591,2,
- Valérian Turbé1,
- Dickman Gareta ORCID: orcid.org/0000-0002-4004-56553,4,5,6,
- Carina Herbst3,
- Rachel A. McKendry1,
- Kobus Herbst ORCID: orcid.org/0000-0002-5436-93863,7 &
- …
- Maryam Shahmanesh2,3
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
Rapid diagnostic tests (RDTs) support affordable disease diagnosis. Machine learning (ML) can improve RDT interpretation but often relies on large, proprietary, and costly real-world image libraries. We present SynSight – a ML-enabled RDT segmentation and classification pipeline trained on synthetic data. Validated on HIV (98% sensitivity, 99% specificity) and COVID-19 RDTs (up to 99% accuracy), SynSight enables rapid ML training without real-world training images, keeping pace with new RDT development.
Acknowledgements
We would like to thank the authors, institutions and participants who contributed to collecting and providing access to real-world image libraries, as outlined in Turbé et al. and Arumugam et al. For the purpose of open access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission.
Funding
We acknowledge funding for this research: Medical Research Council for the PhD studentship (MR/W006774/1 to E.R.); EPSRC Digital Health Hub for AMR (EP/X031276/1 to R.A.M.); M.S. is an NIHR Research Professor (NIHR 301634); AHRI is supported by core funding from the Wellcome Trust (082384/Z/07/Z and 201433/Z/16/Z to K.H. and M.S.).
Author information
Authors and Affiliations
London Centre for Nanotechnology and Division of Medicine, University College London, London, UK
Elliott Rogers, Valérian Turbé & Rachel A. McKendry
Institute of Global Health, University College London, London, UK
Elliott Rogers & Maryam Shahmanesh
Africa Health Research Institute, Durban, South Africa
Dickman Gareta, Carina Herbst, Kobus Herbst & Maryam Shahmanesh
Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
Dickman Gareta
Graduate School for Health Sciences, University of Bern, Bern, Switzerland
Dickman Gareta
School of Laboratory Medicine and Medical Sciences, University of KwaZulu Natal, Durban, South Africa
Dickman Gareta
DSI-SAMRC South Africa Population Research Infrastructure Network, Durban, South Africa
Kobus Herbst
Authors
- Elliott Rogers
- Valérian Turbé
- Dickman Gareta
- Carina Herbst
- Rachel A. McKendry
- Kobus Herbst
- Maryam Shahmanesh
Corresponding author
Correspondence to Maryam Shahmanesh.
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.
Clinical trial number
not applicable.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, 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 changes were made. 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/4.0/.
About this article
Cite this article
Rogers, E., Turbé, V., Gareta, D. et al. Synthetic data to lower barriers towards equitable artificial intelligence in rapid diagnostic test interpretation. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03380-0
Received: 09 October 2025
Accepted: 28 September 2026
Published: 10 November 2026
DOI: https://doi.org/10.1038/s41746-026-03380-0
来源:Nature 健康护理主题 · nature.com