基于机器学习的预测心血管和脑血管疾病的再接收风险,使用患者EMR数据
Prasad V R Panchangam1, Tejas A1, Thejas B U1
1Data Science Team, Saigeware Inc., Karnataka 560070, India.
Healthcare (Basel, Switzerland)
|August 9, 2024
概括
一个新的XGBoost模型准确地预测了使用电子健康记录的心血管和脑血管患者的再入院情况,其表现优于LACE加分. 这种工具有助于临床决策,以改善患者护理.
科学领域:
- 心血管和脑血管医学
- 医疗信息学 医疗信息学
- 预测分析是一种预测分析.
背景情况:
- 在管理心血管和脑血管疾病患者方面,再入院是一个重大挑战.
- 现有的风险分层工具可能无法充分捕捉重新接收风险的复杂性.
- 准确预测再入院对于优化患者护理途径和资源配置至关重要.
研究的目的:
- 开发和验证一种新的基于风险的再接收预测模型,使用医院出院时的电子病历 (EMR) 数据.
- 为了比较开发模型的性能与已建立的LACE加分数来预测再录取.
主要方法:
- 分析了大约31万名因心血管和脑血管疾病住院患者的队列.
- 电子医疗记录数据,包括实验室结果,生命体,药物和并发症,被用作输入.
- 使用XGBoost机器学习模型 (v1.7.6) 预测下一次入院的时间.
主要成果:
- XGBoost模型实现了高预测性能,精度为0.74 (±0.03) 和回忆率为0.75 (±0.02),整体精度约为82% (±5%).
- 该模型在识别早期 (30天) 和晚期 (超过六个月) 再录取方面,与LACE加分相比,显示出更高的准确性.
- 较高的并发症负担和较低的血红蛋白水平被确定为增加再接收风险的显著预测因素.
结论:
- 开发的XGBoost模型提供了一种强大而准确的方法,用于预测心血管和脑血管患者群体的再入院情况.
- 该模型显示了提高临床决策的潜力,并可以作为LACE加分的优质替代方案.
- 这些发现支持通过先进的预测分析来实现差异化患者护理策略.
更多相关视频
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
7.0K
07:25Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
3.4K
相关概念视频
01:30Pulse rhythm
777
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...
777
01:25Errors occurring during blood pressure monitoring
661
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...
661