相关实验视频
Updated: Jan 10, 2026

07:42
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
465
使用可解释机器学习在ICU中早期预测败血症诱导的凝血病:一个多中心的回顾性队列研究
Tao Sha1, Hao Jiang1, Lei Feng1
1Department of Emergency, Huadong hospital, Fudan University, Shanghai, China.
Frontiers in medicine
|November 21, 2025
概括
这项研究开发了一种可解释的机器学习模型,用于预测ICU患者的败血症诱导凝血病 (SIC). 该模型准确地识别了早期干预的高风险患者.
科学领域:
- 关键护理医学 关键护理医学
- 医疗保健中的机器学习
- 凝血障碍 凝血障碍 凝血障碍
背景情况:
- 败血症引起的凝血病 (SIC) 是重症监护室 (ICU) 患者的严重并发症.
- 早期预测SIC仍然是一个重大的临床挑战.
- 开发准确的预测模型对于及时干预至关重要.
研究的目的:
- 开发和验证一个可解释的机器学习模型,用于在ICU入院后七天内预测SIC.
- 确定与SIC发展相关的关键临床变量.
- 创建一个用户友好的工具,用于临床应用.
主要方法:
- 使用MIMIC-IV数据库进行模型开发,并使用eICU-CRD数据库进行外部验证.
- 采用了特征选择技术,包括LASSO,RF-RFE和Boruta.
- 通过5倍交叉验证训练和评估了10个机器学习模型,其中LightGBM被认为是最佳的.
主要成果:
- 一个包含13个变量的LightGBM模型实现了0.885 (内部) 和0.831 (外部) 的AUROC.
- 关键预测因素包括INR,血小板计数,SOFA得分,乳酸,SBP,RDW,碳酸盐,酸盐,血红蛋白,年龄,高血压,IHD和CRRT.
- 该模型被部署为一个交互式Web应用程序.
结论:
- 开发的机器学习模型显示出强大的预测性能和可用于早期SIC识别的可解释性.
- 这种工具可以帮助临床医生为患有SIC风险的患者实施有针对性的干预措施.
- 可访问的网络应用程序有助于临床采用和改善患者的治疗结果.
更多相关视频
05:28Evaluation of a Reliable Biomarker in a Cecal Ligation and Puncture-Induced Mouse Model of Sepsis
Published on: December 9, 2022
4.3K
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.6K
相关概念视频
Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
286
Diagnosing Pulmonary EmbolismDiagnosing pulmonary embolism (PE) involves clinical assessment and advanced imaging tests. The preferred diagnostic tool is the spiral (helical) CT scan or CT angiography (CTA), which uses intravenous contrast media to visualize the pulmonary vasculature and identify emboli.A ventilation-perfusion (V/Q) scan is an alternative for patients unable to receive contrast media. This scan includes both perfusion and ventilation scanning. Perfusion scanning involves...
286
Acute Kidney Injury IV: Diagnostic Studies and Prevention
249
Accurate diagnosis and effective prevention are critical in managing Acute Kidney Injury (AKI), which is linked to high mortality rates ranging from 10% to 80%. Timely recognition of at-risk patients and careful monitoring can significantly reduce the likelihood of kidney damage.Diagnostic Assessments:The diagnostic process starts with a comprehensive medical history to identify prerenal, intrarenal, and postrenal causes.Prerenal causes, such as dehydration, hypotension, or blood loss, should...
249