An excellent mortality prediction model based on support vector machine (SVM)-a pilot study
An excellent mortality prediction model based on support vector machine (SVM)-a pilot study
复制标题
基于支持向量机（SVM）的优秀死亡率预测模型——初步研究
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Hsien
中科院分区：
文献类型：
--
作者：
Chien;Chia;Hsien
重症监护是现代医疗体系最重要的组成部分之一。医疗保健专业人员需要有效地利用重症监护资源。死亡率预测模型帮助医生决定哪些病人最需要重症监护，哪些不需要。本研究回顾性收集了695例重症监护病房住院患者的数据，并利用支持向量机（SVM）构建了一种新的死亡率预测模型。新模型的精度较好。准确率为0.899。召回率为0.902。f值是0.899。ROC曲线为0.932。该模型可为重症监护医师的决策提供支持。
Intensive care is one of the most important components of the modern medical system. Healthcare professionals need to utilize intensive care resources effectively. Mortality prediction models help physicians decide which patients require intensive care the most and which do not. This pilot study retrospectively collected data on 695 patients admitted to intensive care units and constructed a novel mortality prediction model with support vector machine (SVM). The accuracy of new model is good. The precision rate is 0.899. The recall rate is 0.902. The F-Measure is 0.899. The ROC curve is 0.932. This new model can support the physician's in intensive care decision making.