对于急性住院病人的恶化,只有生命体征的机器学习模型:一项回顾性多中心研究
Santiago Romero-Brufau1,2, Radit Smunyahirun3, Timothée Filhol3
1Department of Otolaryngology, Head and Neck Surgery, SW Rochester, MN.
Mayo Clinic proceedings. Innovations, quality & outcomes
|October 2, 2025
概括
一个新的机器学习模型使用生命体征准确预测患者的临床恶化. 这种与监控设备兼容的预测模型旨在通过更早地识别有风险的人来减少虚假警报并改善患者护理.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的机器学习
- 临床决策支持 临床决策支持
背景情况:
- 临床恶化需要及时干预,以防止不良结果.
- 预测恶化的现有方法经常遭受低正预测值 (PPVs),导致警报疲劳.
- 开发与生命体征监测设备兼容的准确预测模型对于早期风险识别至关重要.
研究的目的:
- 开发和验证一种机器学习模型,用于识别临床恶化风险的患者.
- 确保该模型与生命体征监测设备兼容,以便无集成到临床工作流程中.
- 尽量减少假阳性,同时保持在检测低患病率恶化事件的临床相关性.
主要方法:
- 利用了来自多医院系统的3万多名住院患者的生命体征数据.
- 在大量高质量的生命体征数据集上训练了一种光梯度增强机器模型.
- 采用了一种新的两窗特征提取方法,以捕捉短期和长期的患者状态变化.
主要成果:
- 该模型实现了73.4%的灵敏度和30.4%的正预测值 (PPV).
- 显示高C-统计值为0.874,表明强大的区分能力.
- 在特定地点的PPV显著更高 (例如,罗切斯特54.9%),表现优于现有指数.
结论:
- 开发的机器学习模型有效地预测临床恶化,准确度提高.
- 新的2窗口特征提取方法通过分析时间趋势来提高预测性能.
- 高PPV对于减少虚假警报和提高临床恶化警报的可靠性至关重要.
相关概念视频
Guidelines For Measuring Vital Signs
2.7K
Following these guidelines can help nurses accurately measure vital signs, assess changes in patient conditions, and provide timely treatment when necessary. Adhering closely to the guidelines ensures the accuracy and reliability of the results.
Before taking a patient's vital signs, a nurse would consider and assess the patient's comfort level and ensure appropriate equipment is available.
Before taking a patient's vital signs, a nurse would consider and assess the patient's comfort level and ensure appropriate equipment is available.
2.7K
Introduction to Vital Signs
7.5K
Vital signs are physiological measurements that help key into the status of the body's essential functions. These include body temperature, pulse rate, respiratory rate, and blood pressure, commonly abbreviated as T, P, R, and BP. Some healthcare settings also consider oxygen saturation (SpO2) and, in specific contexts, pain and level of consciousness as additional vital signs.
Vital signs help healthcare professionals assess an individual's well-being and detect any functional changes...
Vital signs help healthcare professionals assess an individual's well-being and detect any functional changes...
7.5K
Pulse rhythm
1.3K
Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
1.3K
Errors occurring during blood pressure monitoring
1.3K
Blood pressure monitoring is a crucial clinical procedure in diagnosing and managing various cardiovascular conditions. Despite its significance, the accuracy of blood pressure measurements can be compromised by multiple factors, potentially leading to either falsely high or low readings. These inaccuracies are critical as they can significantly impact patient care. So, it is vital to understand these challenges deeply and adopt strategic approaches to minimize errors.
Several factors...
Several factors...
1.3K

