此页面是自动翻译的,不保证翻译的准确性。请参阅 英文版 对于源文本。

External Validation of the FedHist Dynamic Early Warning Model for Mortality Risk in Critically Ill Patients: A Prospective Multicenter Study

2026年9月13日 更新者:Jianfeng Xie、Southeast University, China

The purpose of this study is to assess how accurately FedHist, an artificial intelligence model, predicts the risk of death in critically ill patients. Patients in intensive care units (ICUs) can become worse quickly. Updating risk estimates as new clinical information becomes available may help identify patients at higher risk. FedHist uses routinely collected clinical information to estimate a patient's risk of dying in the ICU within the next 24 hours. These estimates are updated every 6 hours.

This study will evaluate FedHist prospectively across several hospitals. The model will be integrated into hospital clinical information systems, and its predictions will be compared with observed patient outcomes. The study aims to determine whether FedHist provides accurate predictions across hospitals with different patient populations and clinical practices.

研究概览

地位

尚未招聘

条件

详细说明

Critically ill patients can deteriorate rapidly, creating a need for timely and repeated assessment of mortality risk. Conventional severity assessments, including the Acute Physiology and Chronic Health Evaluation II (APACHE II) and Sequential Organ Failure Assessment (SOFA) scores, provide clinically useful information. However, risk assessments based on data from defined assessment periods may not fully capture evolving clinical trajectories. Models that incorporate longitudinal clinical data may support more frequent assessment of short-term mortality risk.

Artificial intelligence offers opportunities to integrate clinical information collected over time for dynamic risk prediction. However, models developed using data from a single center or database may perform differently in other settings. Differences in patient characteristics, disease severity, measurement frequency, and clinical workflows can affect predictive performance. Privacy requirements, data governance policies, and institutional control over data also limit the pooling of patient records for conventional centralized model development.

FedHist was developed using a federated learning framework incorporating electronic health records from more than 250,000 critically ill patients across five countries and regions. This framework enabled collaborative model development while raw patient data remained at the contributing institutions. FedHist generates an updated estimate of the risk of ICU death within the next 24 hours at 6-hour intervals.

Previous evaluations showed a macro-averaged area under the receiver operating characteristic curve (AUROC) of 0.893 in internal validation. AUROCs were 0.881 in the NWICU external validation cohort and 0.961 in the prospective CDIC cohort. FedHist outperformed the corresponding locally trained models. When only 10% of the development data at each site were used, its performance approached or exceeded that of local models trained on the full development datasets. These findings support further prospective evaluation following integration into routine clinical information systems across multiple hospitals.

This prospective multicenter study will externally validate the previously developed FedHist model in participating ICUs. The model will be integrated into local clinical information systems to generate risk estimates using prospectively collected clinical data. Predictions will be compared with observed ICU outcomes to assess performance in predicting death within the subsequent 24 hours. The study will evaluate predictive performance across participating hospitals and assess the generalizability of FedHist under routine clinical conditions.

研究类型

观察性的

注册 (估计的)

23579

联系人和位置

本节提供了进行研究的人员的详细联系信息,以及有关进行该研究的地点的信息。

学习联系方式

参与标准

研究人员寻找符合特定描述的人,称为资格标准。这些标准的一些例子是一个人的一般健康状况或先前的治疗。

资格标准

适合学习的年龄

  • 成人
  • 年长者

接受健康志愿者

不

取样方法

非概率样本

研究人群

All patients admitted to the participating ICU

描述

Inclusion Criteria:

  • Admission to a participating ICU

Exclusion Criteria:

  • Age younger than 18 years.
  • Expected ICU length of stay shorter than 24 hours.
  • Refusal to provide written informed consent.

学习计划

本节提供研究计划的详细信息,包括研究的设计方式和研究的衡量标准。

研究是如何设计的?

设计细节

研究衡量的是什么?

主要结果指标

结果测量
措施说明
大体时间
ICU mortality
大体时间:From ICU admission to ICU discharge or 90 days after ICU admission, whichever occurs first.
The proportion of patients who die from any cause during the ICU stay, with follow-up capped at 90 days after ICU admission. For patients whose ICU stay exceeds 90 days, vital status at day 90 will be used to determine the mortality outcome.
From ICU admission to ICU discharge or 90 days after ICU admission, whichever occurs first.

合作者和调查者

在这里您可以找到参与这项研究的人员和组织。

研究记录日期

这些日期跟踪向 ClinicalTrials.gov 提交研究记录和摘要结果的进度。研究记录和报告的结果由国家医学图书馆 (NLM) 审查,以确保它们在发布到公共网站之前符合特定的质量控制标准。

研究主要日期

学习开始 (估计的)

2026年10月1日

初级完成 (估计的)

2027年12月1日

研究完成 (估计的)

2027年12月31日

研究注册日期

首次提交

2026年9月13日

首先提交符合 QC 标准的

2026年9月13日

首次发布 (实际的)

2026年9月17日

研究记录更新

最后更新发布 (实际的)

2026年9月17日

上次提交的符合 QC 标准的更新

2026年9月13日

最后验证

2026年9月1日

更多信息

与本研究相关的术语

其他研究编号

  • 2026ZDSYLL335-P01

计划个人参与者数据 (IPD)

计划共享个人参与者数据 (IPD)?

未定

药物和器械信息、研究文件

研究美国 FDA 监管的药品

不

研究美国 FDA 监管的设备产品

不

此信息直接从 clinicaltrials.gov 网站检索,没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求,请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改,我们的网站上也会自动更新.

订阅