文献速递临床生化临床免疫临床血液与体液

机器学习算法早期鉴别尿源性脓毒症与尿路感染

Developing a machine learning prediction algorithm for early differentiation of urosepsis from urinary tract infection.
PubMed 文献 · Clin Chem Lab Med · 2022-11-17

该研究回顾性纳入157例尿源性脓毒症患者和417例尿路感染患者,采集降钙素原、D-二聚体、C反应蛋白等实验室指标,按80%与20%划分训练集与验证集并交叉验证。研究初步筛选26个变量、其中18个有统计学意义,六种机器学习模型预测尿源性脓毒症的准确率均高于80%,人工神经网络(ANN)表现最佳,仅用排名前八的生物标志物时准确率达92.9%、受试者工作特征曲线下面积为0.946。

要点

  • 仅用排名前八的生物标志物即可预测尿源性脓毒症,ANN模型准确率92.9%。
  • 六种机器学习模型预测准确率均高于80%,ANN表现最优。
  • 数据驱动的预测模型有助于临床快速准确诊断尿源性脓毒症。

核心结论

  • 仅使用排名方法确定的前八位生物标志物即可预测尿源性脓毒症。
  • 该数据驱动预测模型有望帮助临床医生快速、准确地进行诊断。

研究设计与样本

  • 回顾性分析,纳入157例尿源性脓毒症患者和417例尿路感染患者。
  • 采集降钙素原、D-二聚体、C反应蛋白等生物标志物实验室数据。
  • 数据分为训练集(80%)和验证集(20%),通过交叉验证确定模型平均预测准确率。

主要发现

  • 初步筛选26个变量,其中18个具有统计学意义。
  • 用三种排序方法对18个变量的影响排序,Gini重要性排序法适合变量筛选。
  • 六种机器学习模型预测尿源性脓毒症的准确率均高于80%,人工神经网络(ANN)表现最佳。
  • ANN纳入影响排名最高的八个生物标志物时预测性能最佳,准确率92.9%,受试者工作特征曲线下面积0.946。

关键数值与推荐

  • ANN模型仅用排名前八的生物标志物:准确率92.9%,AUC 0.946。
  • 六种机器学习模型预测准确率均高于80%。
  • 初步筛选26个变量,18个有统计学意义。

临床怎么用

  • 临床可借助基于生物标志物的机器学习模型早期识别尿源性脓毒症,辅助快速诊断。
  • 优先关注排名前八的生物标志物组合,可支撑ANN模型获得较高预测准确率。

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

OBJECTIVES: Early recognition and timely intervention for urosepsis are key to reducing morbidity and mortality. Blood culture has low sensitivity, and a long turnaround time makes meeting the needs of clinical diagnosis difficult. This study aimed to use biomarkers to build a machine learning model for early prediction of urosepsis. METHODS: Through retrospective analysis, we screened 157 patients with urosepsis and 417 patients with urinary tract infection. Laboratory data of the study participants were collected, including data on biomarkers, such as procalcitonin, D-dimer, and C-reactive protein. We split the data into training (80%) and validation datasets (20%) and determined the average model prediction accuracy through cross-validation. RESULTS: In total, 26 variables were initially screened and 18 were statistically significant. The influence of the 18 variables was sorted using three ranking methods to further determine the best combination of variables. The Gini importance ranking method was found to be suitable for variable filtering. The accuracy rates of the six machine learning models in predicting urosepsis were all higher than 80%, and the performance of the artificial neural network (ANN) was the best among all. When the ANN included the eight biomarkers with the highest influence ranking, its model had the best prediction performance, with an accuracy rate of 92.9% and an area under the receiver operating characteristic curve of 0.946. CONCLUSIONS: Urosepsis can be predicted using only the top eight biomarkers determined by the ranking method. This data-driven predictive model will enable clinicians to make quick and accurate diagnoses.

来源:Clin Chem Lab Med,查看原文。版权归原作者所有。

引用

  1. Su M, Guo J, Chen H, et al. Developing a machine learning prediction algorithm for early differentiation of urosepsis from urinary tract infection. Clin Chem Lab Med. 2022. PMID: 36383696. doi:10.1515/cclm-2022-1006

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。