摘要
目的建立一套基于患者术前信息的风险预测系统,使得待手术患者麻醉手术风险建立定性评估指导临床。方法基于APACHE II、P-POSSSUM、ACS NSQIP评估数据结合临床观察指标的比重选择变量,通过提取麻醉信息系统、电子病历系统、病案系统中手术患者数据信息,建立训练集和验证集建立模型,经过测试以随机森林法建立模型。结果完成开发预测模型软件进行临床应用。结论本预测系统能够对围术期手术麻醉患者的手术风险并发症进行良好的预测为临床提供指导价值。
Objective To establish a risk prediction system based on the preoperative information of patients,so that the patients undergoing anesthesia can establish a qualitative assessment of clinical risk and guide the clinic.Methods Based on APACHE II,P-POSSSUM,ACS NSQIP evaluation data combined with the proportion of clinical observation indicators to select variables,by extracting surgical patient data information in anesthesia information system,electronic medical record system,and case history system,a training set and a validation set were established to establish a model.The model was built by random forest method.Results Complete the development of predictive model software for clinical application.Conclusion The prediction system can provide good predictive value for clinical risk complications of perioperative anesthesia patients.
作者
范双炽
FAN Shuangchi(Department of Anesthesiology,Sanming First Hospital Affiliated to Fujian Medical University,Sanming Fujian 365000,China)
出处
《中国卫生标准管理》
2020年第21期11-15,共5页
China Health Standard Management
基金
福建省自然科学基金(2016J01655)。
关键词
围手术期
风险评估
大数据挖掘
并发症
预测
机器学习
perioperative period
risk assessment
big data mining
complications
forecast
machine learning
