Nature Communications (Jun 2023)

Predicting in-hospital outcomes of patients with acute kidney injury

  • Changwei Wu,
  • Yun Zhang,
  • Sheng Nie,
  • Daqing Hong,
  • Jiajing Zhu,
  • Zhi Chen,
  • Bicheng Liu,
  • Huafeng Liu,
  • Qiongqiong Yang,
  • Hua Li,
  • Gang Xu,
  • Jianping Weng,
  • Yaozhong Kong,
  • Qijun Wan,
  • Yan Zha,
  • Chunbo Chen,
  • Hong Xu,
  • Ying Hu,
  • Yongjun Shi,
  • Yilun Zhou,
  • Guobin Su,
  • Ying Tang,
  • Mengchun Gong,
  • Li Wang,
  • Fanfan Hou,
  • Yongguo Liu,
  • Guisen Li

DOI
https://doi.org/10.1038/s41467-023-39474-6
Journal volume & issue
Vol. 14, no. 1
pp. 1 – 9

Abstract

Read online

Abstract Acute kidney injury (AKI) is prevalent and a leading cause of in-hospital death worldwide. Early prediction of AKI-related clinical events and timely intervention for high-risk patients could improve outcomes. We develop a deep learning model based on a nationwide multicenter cooperative network across China that includes 7,084,339 hospitalized patients, to dynamically predict the risk of in-hospital death (primary outcome) and dialysis (secondary outcome) for patients who developed AKI during hospitalization. A total of 137,084 eligible patients with AKI constitute the analysis set. In the derivation cohort, the area under the receiver operator curve (AUROC) for 24-h, 48-h, 72-h, and 7-day death are 95·05%, 94·23%, 93·53%, and 93·09%, respectively. For dialysis outcome, the AUROC of each time span are 88·32%, 83·31%, 83·20%, and 77·99%, respectively. The predictive performance is consistent in both internal and external validation cohorts. The model can predict important outcomes of patients with AKI, which could be helpful for the early management of AKI.