相关实验视频
Updated: Jul 12, 2025

07:42
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
179
诊断怀疑偏见和机器学习:打破败血症检测意识局
Varesh Prasad1,2, Baturay Aydemir3, Iain E Kehoe3
1Harvard-MIT Program in Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America.
PLOS digital health
|November 1, 2023
概括
预测模型可以使用随时可用的临床数据或通过添加几个问题在分拣时识别败血症. 后者显示性能有所改善,为后评估算法提供了替代方案.
科学领域:
- 紧急医疗 紧急医疗
- 临床信息学 临床信息学
- 预测分析是一种预测分析.
背景情况:
- 败血症的早期预警算法通常依赖于最初临床评估和诊断测试后生成的数据.
- 这种下游方法可以限制它们的实用性,如果不怀疑疾病或没有订购适当的测试.
- 从无序测试中缺少的数据可能导致不准确的低风险评估.
研究的目的:
- 开发和评估用于在急诊室 (ED) 的分拣阶段识别败血症的预测方法.
- 为了比较一个只使用基本分拣数据的算法的性能,与一个包含额外的有针对性的问题.
主要方法:
- 在ED的成年患者 (2014-2018) 的回顾性研究,分为培训,测试和验证队列.
- 开发了使用贪前进特征选择的L2-规范化后勤回归模型.
- 将使用人口统计,生命体征和过去病史的模型与第二个模型进行比较,其中包括三个额外的是/否查询.
主要成果:
- 基本的临床数据模型在验证队列中实现了0.74-0.79的ROC AUC.
- 结合辅助查询的模型表现出卓越的性能,ROC AUCs范围为0.78-0.83.
- 改进后的模型显示了对优异败血症预测的趋势,但需要额外的用户输入.
结论:
- 使用分拣数据的预测模型可以比传统的下游算法更早地发现败血症.
- 将简单的,有针对性的问题添加到分类中可以提高败血症的预测准确性.
- 对医院早期预警算法来说,考虑数据的可用性,偏差和可用性至关重要.
相关概念视频
Steps in Outbreak Investigation
135
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
135
Sensitivity, Specificity, and Predicted Value
433
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
433

