跳到正文
原文
Nature 健康护理主题·· 9 天前AI 评分35

Transformer模型预测糖尿病肾病患者肾功能轨迹

Transformer-based model for EHR data-derived development for prediction of kidney function trajectories in diabetic kidney disease

AI 导读

研究开发了一种基于Transformer的模型,用于预测糖尿病患者正常肾功能下的肾功能下降和慢性肾病分期。该模型在预测晚期慢性肾病方面表现良好,但对所有时间点的肾功能下降预测不如LightGBM和XGBoost。模型在输入数据降级时表现更稳健,但在时间验证中表现下降。这些发现支持了Transformer模型在电子健康记录数据中的技术可行性,但需进一步校准和外部验证才能临床使用。

正文

Abstract

We aimed to develop a transformer-based model to predict kidney outcomes from longitudinal electronic health records (EHR) of patients with diabetes and normal kidney function, and compared it with. logistic regression (LR), support vector machine (SVM), LightGBM, and XGBoost. Using EHR data from 8,772 patients (Seoul National University Bundang Hospital, 2003–2014), we predicted ≥ 30% estimated Glomerular filtration rate (eGFR) decline and advanced chronic kidney disease (CKD) stage at 1, 3, 5, and 10 years (event 1.2–8.4%). ForeGFR decline, LightGBM and XGBoost both outperformed the transformer at every horizon (AUROC 0.68–0.80 vs. 0.56–0.75), for advanced CKD, the transformer-based model achieved AUROC of 0.77–0.85, comparable to the trees. At a matched operating point (recall 0.8), F1 scores were comparable across models. The transformer was overconfident and, unlike the trees, did not exceed treat-all net benefit in decision-curve analysis. It was, however, more robust to input degradation: retaining only 25% of laboratory values reduced AUROC by 0.03 versus 0.23–0.30 for the trees. Under temporal validation (training ≤ 2009, testing 2009–2016), AUROC fell by an average of 0.09. These findings support the technical feasibility of sequence models for EHR data while highlighting the need for recalibration and external validation before clinical use.

Funding

This research was supported by Digital Healthcare Research Grant through the Seokchun Caritas Foundation (SCY2201P) as well as from grant no.18-2018-0031 from the SNUBH Research Fund. This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP)-Global Data-X Leader HRD program grant funded by the Korea government (MSIT)(IITP-2024-RS-2024-00441407).

Author information

Author notes

  1. Jiwon Ryu, Seong-Eun Moon, Sejoong Kim and Hyung-Jin Yoon contributed equally to this work.

Authors and Affiliations

  1. Division of General Internal Medicine, Department of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Republic of Korea

    Jiwon Ryu & Sejoong Kim

  2. Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea

    Jiwon Ryu & Sejoong Kim

  3. Samsung Research, Samsung Electronics, Seoul, Republic of Korea

    Seong-Eun Moon

  4. NAVER Applied AI Group, NAVER, Seongnam, Republic of Korea

    Haanju Yoo

  5. Center for Artificial Intelligence in Healthcare, Seoul National University Bundang Hospital, Seongnam, Republic of Korea

    Jinyeong Yi

  6. Department of Human Systems Medicine, Seoul National University Hospital, Seoul, Republic of Korea

    Hyung-Jin Yoon

  7. Medical Bigdata Research Center, Seoul National University, Seoul, Republic of Korea

    Hyung-Jin Yoon

  8. Department of Internal Medicine, Seoul National University Bundang Hospital, 82, Gumi-ro 173 beon-gil, Bundang-gu, Seongnam-si, 13620, Gyeonggi-do, Republic of Korea

    Sejoong Kim

  9. Department of Biomedical Engineering, College of Medicine and Hospital, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 110-744, Korea

    Hyung-Jin Yoon

Authors

  1. Jiwon Ryu
  2. Seong-Eun Moon
  3. Haanju Yoo
  4. Jinyeong Yi
  5. Sejoong Kim
  6. Hyung-Jin Yoon

Corresponding authors

Correspondence to Sejoong Kim or Hyung-Jin Yoon.

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 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

Ryu, J., Moon, SE., Yoo, H. et al. Transformer-based model for EHR data-derived development for prediction of kidney function trajectories in diabetic kidney disease. Sci Rep (2026). https://doi.org/10.1038/s41598-026-76546-1

Download citation

  • Received: 13 April 2026

  • Accepted: 14 October 2026

  • Published: 11 November 2026

  • DOI: https://doi.org/10.1038/s41598-026-76546-1

Keywords

来源:Nature 健康护理主题 · nature.com