Development of an Artificial Intelligence Model for Predicting Intraoperative Changes in Cardiac Output Using Capnography During General Anesthesia
试验速览
- 阶段
- 不适用
- 状态
- 招募中
- 入组人数
- 2,005
- 试验地点
- 1
- 主要终点
- Predictability of algorithm
研究概览
简要总结
Conventional monitoring of cardiac output requires an invasive procedure and an additional device, which can lead to increased risk and cost. Investigators developed an artificial intelligence algorithm to predict intraoperative changes in cardiac output using capnography in patients undergoing surgery under general anesthesia.
详细描述
Anesthesiologists strive to maintain adequate cardiac output during surgery. However, conventional monitoring of cardiac output requires an invasive procedure (risk) and an additional device (cost).
Because most surgeries are performed without any invasive monitors, anesthesiologists must manage the patients without cardiac output information.
However, modern anesthesia machines usually provide capnography, and continuous capnography monitoring can help estimate changes in cardiac output. Therefore, investigators aim to develop an artificial intelligence algorithm to predict intraoperative changes in cardiac output using capnography in patients undergoing surgery under general anesthesia.
Investigators train a model using capnography data (5-minute duration) related to a 20% or greater decrease in cardiac output during the same period. The developed model can provide an alarm for a decrease in cardiac output based on the change in capnography.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Retrospective
入排标准
- 年龄范围
- 19 Years 至 75 Years（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Elective surgery under general anesthesia
- •Adult patients (18 < age < 76)
- •Patients who were monitored invasive arterial blood pressure (waveform) and capnography (numeric)
排除标准
- •Emergency surgery
- •Cardiovascular and thoracic surgery
- •Known Asthma and Chronic obstructive pulmonary disease (COPD)
- •Preoperative pulmonary function test (PFT) abnormality over moderate grade
- •Intraoperative monitoring duration less than 30 minutes
结局指标
主要结局
Predictability of algorithm
时间窗: Every time points with interval of 5 minutes during surgery
The performance of the algorithm to predict whether cardiac output has decreased by more than 20% compared to 5 minutes ago. Predictability is estimated by area under the receiver-operating characteristic curve analysis.
次要结局
未报告次要终点
研究者
Heejoon Jeong
Clinical Assistant Professor
Samsung Medical Center