基于机器学习的冠心病治疗单位再入院预测:一项多医院验证研究
Fei-Fei Flora Yau1, I-Min Chiu1,2, Kuan-Han Wu1
1Department of Emergency Medicine, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.
Digital health
|September 3, 2024
概括
准确预测冠状动脉护理单元 (CCU) 再入院的情况至关重要. 一个机器学习梯度增强模型有效地识别了高风险患者,在多家医院中展示了强大的预测性能.
科学领域:
- 心脏病学 心脏病学
- 医疗信息学 医疗信息学
- 机器学习 机器学习
背景情况:
- 冠状动脉护理单位 (CCU) 的再接收对患者的治疗结果和医疗保健费用产生重大影响.
- 准确识别高风险重收CCU患者对于及时干预至关重要.
研究的目的:
- 开发和外部验证CCU再接收的预测模型.
- 利用机器学习 (ML) 算法来增强患者风险分层.
主要方法:
- 从电子健康记录中收集患者数据,包括人口统计,病史和实验室结果 (40个特征).
- 评估了五种ML模型:逻辑回归,随机森林,支向量机,梯度增强和多层感知.
- 为其卓越的性能选择了梯度增强模型.
主要成果:
- 在内部验证中,梯度增强模型在接收器运行特征曲线 (AUC) 下的面积达到0.887.
- 在多个中心进行的外部验证证实了该模型的稳定性,AUC从0.852到0.879.
- 该模型在预测CCU再接收时表现一致.
结论:
- 机器学习算法可以有效地提高医疗保健环境中的患者风险分层.
- 开发的预测模型显示了优化临床干预和降低CCU再入院率的前景.
- 将ML纳入临床实践可以改善患者管理和资源配置.
更多相关视频
相关概念视频
01:15Receiver Operating Characteristic Plot
104
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...
104
01:30Pulse rhythm
775
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...
775