Prediction of Severe Sepsis Using a Machine Learning Algorithm
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 发起方
- 入组人数
- 2,296
- 试验地点
- 1
- 主要终点
- In-hospital mortality
研究概览
简要总结
In this prospective study, the ability of a machine learning algorithm to predict sepsis and influence clinical outcomes, will be investigated at Cabell Huntington Hospital (CHH).
研究设计
- 研究类型
- Interventional
- 分配方式
- Non Randomized
- 干预模型
- Factorial
- 主要目的
- Diagnostic
- 盲法
- None
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •All adult patients visiting the emergency department, or admitted to the participating intensive care unit (ICU) wards of Cabell Huntington Hospital will be eligible.
排除标准
- •All patients younger than 18 years of age will be excluded.
研究组 & 干预措施
With InSight
Healthcare provider receives an alert from InSight for patients trending towards severe sepsis. Healthcare provider also receives information from the severe sepsis detector in the CHH electronic health record.
干预措施: Severe Sepsis Prediction (Other)
With InSight
Healthcare provider receives an alert from InSight for patients trending towards severe sepsis. Healthcare provider also receives information from the severe sepsis detector in the CHH electronic health record.
干预措施: Severe Sepsis Detection (Other)
Without Insight
Healthcare provider does not receive any alerts from InSight. Healthcare provider receives information from the severe sepsis detector in the CHH electronic health record.
干预措施: Severe Sepsis Detection (Other)
结局指标
主要结局
In-hospital mortality
时间窗: Through study completion, an average of 30 days
次要结局
- Hospital length of stay(Through study completion, an average of 30 days)