相关实验视频

Updated: May 26, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

预测计划外重症监护室再接收风险的预测模型:基于HSROC模型的系统审查和元分析

Huiling Hu¹, Jiashuai Li¹, Hui Ge¹

¹School of Nursing, Peking University, Beijing, People's Republic of China.

Nursing in critical care

|February 25, 2025

概括

与传统的评分系统相比,机器学习模型在预测重症监护室 (ICU) 再入院方面表现更好. 纳入临床笔记可以进一步提高预测准确性,以获得更好的患者护理.

科学领域:

关键护理医学关键护理医学
医疗信息学医疗信息学
生物统计学生物统计学

背景情况:

重症监护室 (ICU) 的再接收是影响患者护理和资源分配的关键结果.
现有的ICU再接收的预后模型在方法上有所不同,需要进行全面的绩效评估.
系统性审查对于评估各种ICU再接收预测模型的有效性和适用性至关重要.

研究的目的:

确定非计划性ICU再接收的预后模型.
将机器学习模型的预测性能与传统评分系统进行比较.
评估现有的ICU再接收预测模型的整体质量和适用性.

主要方法:

对队列研究进行系统审查和元分析.
搜索了11个数据库,查找到2024年8月21日的相关文献.
使用预测模型偏差风险评估工具评估模型偏差风险和适用性.
使用等级总结接收器操作特征曲线模型进行的元分析.

主要成果:

包括67项描述335个模型和67个评分系统的研究.
与评分系统相比,机器学习模型的聚合灵敏度 (0.711) 和特异性 (0.899) 较高 (灵敏度0.607,特异性0.699).
深度学习模型显示高灵敏度 (0.745) 但较低的特异性 (0.709);所有研究都显示出偏差的高风险.

结论:

机器学习模型在ICU再入院预测方面表现优于评分系统.
未来的模型应该包含非结构化的临床数据,以提高预测准确度.
对模型的外部验证对于确保不同医疗机构的可靠性和通用性至关重要.

关键词:

根据HSROC的模型,在ICU重新接收.预测模型的预测模型.预测风险预测风险系统性审查系统性审查

更多相关视频

Noninvasive and Invasive Renal Hypoxia Monitoring in a Porcine Model of Hemorrhagic Shock

Noninvasive and Invasive Renal Hypoxia Monitoring in a Porcine Model of Hemorrhagic Shock

Published on: October 28, 2022

Observational Study Protocol for Repeated Clinical Examination and Critical Care Ultrasonography Within the Simple Intensive Care Studies

Observational Study Protocol for Repeated Clinical Examination and Critical Care Ultrasonography Within the Simple Intensive Care Studies

Published on: January 16, 2019

相关概念视频

Receiver Operating Characteristic Plot

Receiver Operating Characteristic Plot

A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...