文献速递血液净化与透析肾血管病与高血压

利用机器学习与云计算基础设施实时预测透析中低血压

Real-time prediction of intradialytic hypotension using machine learning and cloud computing infrastructure.
PubMed 文献 · Nephrol Dial Transplant · 2023-01-01

本研究开发机器学习模型,提前15–75分钟预测维持性血液透析患者透析中低血压(IDH,定义收缩压<90 mmHg)。利用693例患者42656次透析的355693条透析中收缩压数据建模,IDH发生率为16.2%,模型预测AUROC为0.89。作者认为实时预测IDH可行且具临床可操作性,但能否降低IDH发生率并改善预后尚需前瞻性研究。

要点

  • 模型可提前15–75分钟预测透析中低血压,AUROC为0.89。
  • IDH定义为透析中收缩压<90 mmHg,本队列发生率为16.2%。
  • 最强预测因子为最近一次透析中收缩压、IDH发生率及前10次透析平均最低收缩压。

核心结论

  • 在透析进行中实时预测IDH是可行的,且预测性能具有临床可操作性。
  • 该预测信息能否促进及时部署预防干预、降低IDH发生率并改善患者结局,尚需前瞻性研究。

研究设计与样本

  • 开发机器学习模型,提前15–75分钟预测在中心血液透析患者的IDH,IDH定义为收缩压<90 mmHg。
  • 从电子健康记录提取人口学、临床、治疗相关和实验室数据,并与实时发送至云端的透析中机器数据合并。
  • 透析 sessions 随机分为训练集(80%)和测试集(20%),以受试者工作特征曲线下面积(AUROC)衡量预测性能。
  • 纳入693例患者,共42656次血液透析 sessions 和355693条透析中收缩压测量。

主要发现

  • IDH发生于16.2%的血液透析治疗中。
  • 模型提前15–75分钟预测IDH的AUROC为0.89。
  • 最强IDH预测因子为最近一次透析中收缩压、IDH发生率以及前10次透析 sessions 的平均最低收缩压。

关键数值与推荐

  • IDH定义:透析中收缩压<90 mmHg。
  • 模型预测IDH的AUROC为0.89,提前时间为15–75分钟。
  • IDH在血液透析治疗中的发生率为16.2%。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文结论指出该预测信息能否促进预防干预的及时部署并转化为更低的IDH发生率和更好的患者结局尚需前瞻性研究。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: In maintenance hemodialysis patients, intradialytic hypotension (IDH) is a frequent complication that has been associated with poor clinical outcomes. Prediction of IDH may facilitate timely interventions and eventually reduce IDH rates. METHODS: We developed a machine learning model to predict IDH in in-center hemodialysis patients 15-75 min in advance. IDH was defined as systolic blood pressure (SBP) <90 mmHg. Demographic, clinical, treatment-related and laboratory data were retrieved from electronic health records and merged with intradialytic machine data that were sent in real-time to the cloud. For model development, dialysis sessions were randomly split into training (80%) and testing (20%) sets. The area under the receiver operating characteristic curve (AUROC) was used as a measure of the model's predictive performance. RESULTS: We utilized data from 693 patients who contributed 42 656 hemodialysis sessions and 355 693 intradialytic SBP measurements. IDH occurred in 16.2% of hemodialysis treatments. Our model predicted IDH 15-75 min in advance with an AUROC of 0.89. Top IDH predictors were the most recent intradialytic SBP and IDH rate, as well as mean nadir SBP of the previous 10 dialysis sessions. CONCLUSIONS: Real-time prediction of IDH during an ongoing hemodialysis session is feasible and has a clinically actionable predictive performance. If and to what degree this predictive information facilitates the timely deployment of preventive interventions and translates into lower IDH rates and improved patient outcomes warrants prospective studies.

来源:Nephrol Dial Transplant,查看原文。版权归原作者所有。

引用

  1. Zhang H, Wang LC, Chaudhuri S, et al. Real-time prediction of intradialytic hypotension using machine learning and cloud computing infrastructure. Nephrol Dial Transplant. 2023. PMID: 37055366. doi:10.1093/ndt/gfad070

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。