跳到正文
原文
Nature 健康护理主题·· 2026-10-17AI 评分42

肿瘤科 AI 辅助首诊准备的真实世界临床可用性研究

AI-supported first consultation preparation in oncology: a real-world clinical usability study

AI 导读

一项真实世界临床研究评估了 AI 系统 AI-FCP 在荷兰癌症研究所头颈肿瘤科首次门诊准备中的临床可用性。该研究由 Top Sector Life Sciences & Health 资助,数据及分析由无商业利益关联的研究人员负责。研究涉及多家荷兰医疗机构,其中部分作者来自合作企业 kaiko.ai,已采取版本冻结等冲突利益管理措施。

正文

Acknowledgements

We thank the involved physicians and nurse specialists from the Department of Head and Neck Oncology at the Netherlands Cancer Institute for sharing their time and expertise. We thank Martijn Stuiver for providing independent biostatistical advice during manuscript revision. We also thank kaiko.ai for their partnership and expertise in data and AI and appreciate the efforts of many colleagues whose input extended beyond the listed authors. In particular, we thank Dawud Hage for his significant contributions to earlier versions of AI-FCP that formed the basis of the model used in this study.

Funding

This research was funded by Top Sector Life Sciences & Health (Health~Holland), grant number 50545-3.

Author information

Authors and Affiliations

  1. Department of Head and Neck Surgery, Antoni van Leeuwenhoek-Netherlands Cancer Institute, Amsterdam, The Netherlands

    Josephine W. van Koevorden, Marene Kroon, Luc Karssemakers, Ludi Smeele & Richard Dirven

  2. Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, The Netherlands

    Josephine W. van Koevorden & Michel W. Wouters

  3. Department of Medical Informatics, Amsterdam University Medical Center, Amsterdam, the Netherlands

    Rachael Mertooetomo

  4. eHealth Living and Learning Lab Amsterdam, Department of Medical Informatics, Amsterdam University Medical Center, Amsterdam, the Netherlands

    David Neal

  5. Kaiko.ai, Amsterdam, The Netherlands

    Bilge Çelik, Veerle Struben, Nanne Aben & Niels van den Hork

  6. Department of Biometrics, Antoni van Leeuwenhoek-Netherlands Cancer Institute, Amsterdam, The Netherlands

    Vincent van der Noort

  7. Department of Surgical Oncology, Antoni van Leeuwenhoek-Netherlands Cancer Institute, Amsterdam, The Netherlands

    Michel W. Wouters

  8. Dutch Institute for Clinical Auditing, Leiden, The Netherlands

    Michel W. Wouters

  9. Department of Otorhinolaryngology and Head and Neck Surgery, Radboud University Medical Center, Nijmegen, the Netherlands

    Richard Dirven

Authors

  1. Josephine W. van Koevorden
  2. Rachael Mertooetomo
  3. David Neal
  4. Bilge Çelik
  5. Veerle Struben
  6. Nanne Aben
  7. Niels van den Hork
  8. Vincent van der Noort
  9. Marene Kroon
  10. Ludi Smeele
  11. Michel W. Wouters
  12. Richard Dirven

Corresponding author

Correspondence to Josephine W. van Koevorden.

Ethics declarations

Competing interests

The authors declare the following potential conflict of interest: V.S., N.A., and N.H. are employees of kaiko.ai, which may have a commercial interest in the outcomes of this research. B.Ç. is no longer employed by kaiko.ai and has no commercial interest in the outcomes of this research. The other authors do not have a competing interest. To mitigate the risk of bias arising from these affiliations, several safeguards were applied. The AI-FCP system was version-frozen prior to the first study session, and no model or prompt changes were introduced during the study period. All primary outcome data, including questionnaire responses (NASA-TLX, UTAUT-based items, NPS), self-reported time-savings estimates, and qualitative session notes, were collected, curated, and analyzed exclusively by non-commercially affiliated authors at the Netherlands Cancer Institute, who retained final responsibility for data interpretation and manuscript content. During study use, participants independently identified potential discrepancies between AI-generated summaries and the underlying source documents. A subsequent review of the four participant-reported cases was performed to support consistent classification of discrepancies by V.S., a trained physician, to ensure clinically informed categorization. This secondary review process was limited to safety evaluation and did not influence the primary outcome analysis. Commercially affiliated authors V.S., N.A., B.Ç., and N.H. did not collect raw data presented in this research, did not perform the primary outcome analyses, or influence analytic decisions.

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

van Koevorden, J.W., Mertooetomo, R., Neal, D. et al. AI-supported first consultation preparation in oncology: a real-world clinical usability study. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03396-6

Download citation

  • Received: 17 April 2026

  • Accepted: 30 September 2026

  • Published: 17 October 2026

  • DOI: https://doi.org/10.1038/s41746-026-03396-6

来源:Nature 健康护理主题 · nature.com