跳到正文
原文
Nature 健康护理主题·· 15 天前AI 评分35

外部验证图像仅超声模型在智利四家公立医院的产前日期预测

External validation of an image-only ultrasound model for delivery-date prediction in four Chilean public hospitals

AI 导读

研究对外部验证了一款商业图像仅超声深度学习模型在智利四家公立医院的产前日期预测能力,该模型在64,235帧图像中预测的平均绝对误差为6.9天,优于传统预产期11.6天,但误差主要源于妊娠时间较短。模型在预设的里程碑分析中区分早产的AUC为0.86,优于单独使用妊娠年龄的0.52。

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

Pregnancy dating fails the women who need it most: those who reach care without a first-trimester scan. We externally validated a commercial image-only ultrasound deep-learning model for delivery-date prediction, applied unmodified to 64,235 frames from 3788 examinations of 2550 pregnancies (34% migrant) at four Chilean public hospitals. Mean absolute error was 6.9 days versus 11.6 for the conventional due date, yet most of this gain reflected a shorter local gestation and fell below one day against recentred comparators. Fixed-term comparators assign every pregnancy the same gestational age at birth and therefore cannot rank who will deliver early, at any level of point accuracy: accuracy metrics are blind to the ranking on which management turns whenever the outcome distribution is concentrated, as in term-dominated cohorts. In a prespecified landmark analysis the model’s separate image-only risk score discriminated preterm birth with an area under the curve of 0.86, against 0.52 for gestational age alone; outside the landmark restriction it exceeded a clinical baseline of coded diagnoses plus same-examination biometry by 0.09, although it was miscalibrated. Error and calibration were also assessed by maternal nationality. These classification analyses are exploratory, and no woman was managed with the model; they identify what a prospective study should test.

Acknowledgements

No funding was received for this research. We thank the sonographers, midwives and clinical staff of the four participating hospitals.

Funding

The authors received no specific funding for this work.

Author information

Authors and Affiliations

  1. Department of Obstetrics & Gynecology, Hospital Padre Hurtado, Santiago, Chile

    Rodrigo Alliende-Ferrada & Andrés Ruz

  2. Department of Obstetrics & Gynecology, Hospital Santiago Oriente Dr. Luis Tisné Brousse, Santiago, Chile

    Rodrigo Alliende-Ferrada

  3. Maternity Unit, Hospital Barros Luco Trudeau, San Miguel, Chile

    Ignacia Inostroza

  4. Department of Obstetrics & Gynecology, Hospital y CRS El Pino, San Bernardo, Chile

    Jocelyn Stern

  5. School of Engineering, Pontificia Universidad Católica de Chile, Macul, Chile

    Cristobal Pérez-Cotapos

  6. Hospital Clínico de la Universidad de Chile, Santiago, Chile

    Andrés Ruz

Authors

  1. Rodrigo Alliende-Ferrada
  2. Ignacia Inostroza
  3. Jocelyn Stern
  4. Cristobal Pérez-Cotapos
  5. Andrés Ruz

Corresponding author

Correspondence to Rodrigo Alliende-Ferrada.

Ethics declarations

Competing interests

The system evaluated in this study is a commercial product of Ultrasound AI, Inc. (Greenwood Village, CO, USA), deployed in health systems outside Chile. R.A.-F. declares a financial competing interest: he is listed as a strategic advisor to that company, a role concerning technical input on future projects in gynecologic-oncology imaging and predictive AI. No benefit under it arises from or is contingent on this work or its findings. This study received no funding. The product holds no authorisation from the Chilean Instituto de Salud Pública and cannot lawfully be sold or used clinically in Chile. The company’s sole contribution was unpaid access to its web platform for the upload of de-identified JPG image files (declared as support in kind). It had no role in the design, conduct, analysis, interpretation, writing or submission of this work, and received no clinical variable and no delivery outcome at any point. All other authors (I.I., J.S., C.P.-C., A.R.) 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 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/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Alliende-Ferrada, R., Inostroza, I., Stern, J. et al. External validation of an image-only ultrasound model for delivery-date prediction in four Chilean public hospitals. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03453-0

Download citation

  • Received: 11 June 2026

  • Accepted: 18 October 2026

  • Published: 05 November 2026

  • DOI: https://doi.org/10.1038/s41746-026-03453-0

来源:Nature 健康护理主题 · nature.com