基于生命体征的恶化预测模型假设可能导致预测性能损失
Robin Blythe1, Rex Parsons1, Adrian G Barnett1
1Australian Centre for Health Services Innovation, Centre for Healthcare Transformation, School of Public Health and Social Work, Faculty of Health, Queensland University of Technology, 60 Musk Ave, Kelvin Grove, Queensland, 4059, Australia.
使用生命体征预测临床恶化是具有挑战性的,因为缺少数据. 总结统计和归算方法可以提高模型性能,但临床意义仍然不确定.
科学领域:
- 医疗信息学 医疗信息学
- 临床预测建模临床预测建模
- 健康 数据科学 数据科学
背景情况:
- 电子医疗记录 (EMR) 中的生命体征数据通常具有重复的测量和缺失的值,使临床恶化预测复杂化.
- 了解建模假设对这些数据集的影响对于开发可靠的预测工具至关重要.
研究的目的:
- 研究常见生命体征对临床恶化预测模型的模拟假设的影响.
- 评估汇总统计和数据归算方法如何影响模型的区分和校准.
主要方法:
- 利用来自五家澳大利亚医院 (2019-2020) 的EMR数据,包括超过560万次观察.
- 创建了先前生命体征的总结统计数据,调查了缺失的数据模式,并应用了常见的归算技术.
- 开发并评估了后勤回归和极度梯度提升模型,用于使用C统计和校准图表预测住院死亡率.
主要成果:
- 缺少生命体征与观察频率,可变性和患者的意识有关.
- 总结统计数据增强了模型歧视,特别是在极端梯度提升方面.
- 不同的归算方法在模型歧视和校准中产生了显著的差异,这通常是糟糕的.
结论:
- 虽然总结统计和归算可以改善歧视和减少偏见,但它们的临床意义需要仔细考虑.
- 研究人员必须分析数据缺失的原因及其对预测模型临床实用性的潜在影响.
更多相关视频
04:05Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
相关概念视频
Errors occurring during blood pressure monitoring
Several factors...
Assumptions of Survival Analysis
Guidelines For Measuring Vital Signs
Before taking a patient's vital signs, a nurse would consider and assess the patient's comfort level and ensure appropriate equipment is available.
Introduction to Vital Signs
Vital signs help healthcare professionals assess an individual's well-being and detect any functional changes...
Survival Tree
Building a Survival Tree
Constructing a...
Data Validation
Nursing assessment guides are generally based on holistic models rather than medical...
