Application of Machine Learning to Predict Postoperative Acute Kidney Injury in Patients Undergoing Cytoreduction and Hyperthermic Intraperitoneal Chemotherapy Using High-resolution, Time-synchronized Physiological Data From Vital Recorder
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 入组人数
- 57
- 试验地点
- 1
- 主要终点
- number of patients with postoperative acute kidney injury staged by Kidney Disease: Improving Global Outcomes (KDIGO)
研究概览
简要总结
Patients undergoing cytoreductive surgery with hyperthermic intraoperative chemotherapy (CRS with HIPEC) are prone to postoperative kidney dysfunction. Previous models predicting kidney injury after CRS with HIPEC did not include intraoperative physiologic data. This study is designed to include not only mean arterial pressure but other parameters such as systolic, diastolic arterial pressure, heart rate, oxygen saturation, body temperature, cardiac index, stroke volume variation and many other physical parameters using a data collection system that can record them every 1-7 seconds. The data will be analyzed using machine learning algorithms.
研究设计
- 研究类型
- Observational
- 观察模型
- Case Only
- 时间视角
- Prospective
入排标准
- 年龄范围
- 19 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Patients undergoing cytoreductive surgery with hyperthermic intraoperative chemotherapy
排除标准
- •patients under 19
结局指标
主要结局
number of patients with postoperative acute kidney injury staged by Kidney Disease: Improving Global Outcomes (KDIGO)
时间窗: during postoperative day 7
Stage 1: Increased sCr × 1.5 to 1.9 baseline or ≥ 0.3 mg/dl from baseline or urine output \< 0.5 ml/kg/h for 6 to 12 h, Stage 2: Increased sCr × 2.0 to 2.9 baseline or urine output \< 0.5 ml/kg/h for 12 h, Stage 3: Increased sCr × 3 baseline or ≥ 4 mg/dl or initiation of RRT, or GFR decrease \< 35 ml/min/1.73 m2 for patients \< 18 years of age or urine output \< 0.3 ml/kg/h for 24 h or anuria for 12 h
次要结局
未报告次要终点
研究者
Ji-young Kim
Associate professor
Gangnam Severance Hospital