齐霜, 徐浩然, 胡婕, 毛智, 胡新, 周飞虎. 基于机器学习的重症监护病房脓毒症患者早期死亡风险预测模型[J]. 解放军医学院学报, 2021, 42(2): 150-155, 181. DOI: 10.3969/j.issn.2095-5227.2021.02.006
引用本文: 齐霜, 徐浩然, 胡婕, 毛智, 胡新, 周飞虎. 基于机器学习的重症监护病房脓毒症患者早期死亡风险预测模型[J]. 解放军医学院学报, 2021, 42(2): 150-155, 181. DOI: 10.3969/j.issn.2095-5227.2021.02.006
QI Shuang, XU Haoran, HU Jie, MAO Zhi, HU Xin, ZHOU Feihu. Early mortality risk prediction model for sepsis patients in intensive care unit based on machine learning[J]. ACADEMIC JOURNAL OF CHINESE PLA MEDICAL SCHOOL, 2021, 42(2): 150-155, 181. DOI: 10.3969/j.issn.2095-5227.2021.02.006
Citation: QI Shuang, XU Haoran, HU Jie, MAO Zhi, HU Xin, ZHOU Feihu. Early mortality risk prediction model for sepsis patients in intensive care unit based on machine learning[J]. ACADEMIC JOURNAL OF CHINESE PLA MEDICAL SCHOOL, 2021, 42(2): 150-155, 181. DOI: 10.3969/j.issn.2095-5227.2021.02.006

基于机器学习的重症监护病房脓毒症患者早期死亡风险预测模型

Early mortality risk prediction model for sepsis patients in intensive care unit based on machine learning

  • 摘要:
      背景  脓毒症患者死亡率高。准确预测不良结局的发生,有助于医疗资源的有效分配。
      目的  建立一种机器学习模型预测脓毒症患者早期死亡风险,辅助临床医生进行临床决策。
      方法  从重症监护医疗信息市场(Medical Information Mart for Intensive Care,MIMIC)Ⅲ数据库筛选出符合Sepsis-3标准的脓毒症患者,随机抽取70%的病例作为训练集用于建立模型,其余30%的数据用作验证集。使用极度梯度提升(extreme gradient boosting,XGBoost)模型集成相关参数预测脓毒症患者重症监护病房(intensive care unit,ICU)死亡风险,预测能力通过受试者工作特征(receiver operating characteristic,ROC)曲线评估,并与简化急性生理评分(simplified acute physiology score,SAPS)Ⅱ、序贯性器官衰竭评分(sequential organ failure assessment,SOFA)、全身炎症反应综合征(systemic inflammatory response syndrome,SIRS)标准、快速器官衰竭评分(quick sequential organ failure assessment,qSOFA)等对比验证模型的预测价值。
      结果  共纳入4 939例脓毒症患者,其中ICU内死亡患者551例,存活患者4388例;以患者是否ICU死亡作为结局,建立XGBoost 模型获得ROC曲线下面积(AUC)为0.848,敏感度0.841,特异性0.711,准确性0.726,均较其他评分高(P<0.05)。模型中排名前10的特征主要为:入ICU后24 h内血乳酸平均值、血管活性药物评分(vasoactive-inotropic score,VIS)、是否患有恶性肿瘤、天冬氨酸氨基转移酶(aspartate aminotransferase,AST)、阴离子间隙(anion gap,AG)、是否接受机械通气治疗、国际标准化比值(international normalized ratio,INR)、格拉斯哥昏迷指数(Glasgow coma scale,GCS)、重症监护病房类型、入ICU后24 h内血乳酸最大值。
      结论  XGBoost模型较临床常用评分能够更加准确地预测脓毒症患者的死亡风险,有助于辅助临床决策,分配医疗资源。

     

    Abstract:
      Background  Patients with sepsis have a high mortality rate. Accurate predicting the occurrence of adverse outcomes will benefit the effective allocation of medical resources.
      Objective  To construct machine learning model to predict the risk of early mortality in patients with sepsis and provide evidences for clinical decision-making.
      Methods  Patients with sepsis meeting the Sepsis-3 criteria were screened from the Medical Information Mart for Intensive Care (MIMIC)- Ⅲ database. We randomly selected 70% of the data as the training set to build the model, and the remaining 30% of the data were used as the validation set. Extreme gradient boosting (XGBoost) model was applied to integrate relevant parameters to predict the risk of death in intensive care unit (ICU) of patients with sepsis. The predictive ability of the model was evaluated by receiver operating characteristic (ROC) curve, and the model was compared with simplified acute physiology score (SAPSⅡ, sequential organ failure assessment (SOFA), system inflammatory reaction syndrome (SIRS), quick sequential organ failure assessment (qSOFA) to verify the predictive value.
      Results  A total of 4939 sepsis patients meeting the inclusion criteria were included, of which 551 died in the ICU and 4388 survived. Based on whether the patient died in ICU as the outcome, the area under ROC curve (AUC) obtained by the established XGBoost model was 0.848, with sensitivity of 0.841, specificity of 0.711 and accuracy of 0.726, all of which were higher than other scores(P<0.05). The top 10 features of the model were lactate level, vasoactive-inotropic score (VIS), malignant tumor, aspartate aminotransferase (AST), anion gap (AG), mechanical ventilation, international normalized ratio (INR), Glasgow Coma Scale (GCS), and the type of intensive care unit.
      Conclusion  The performance of the XGBoost model is superior to other commonly used clinical scores for accurate prediction of the early death risk of patients with sepsis. Application this model can assist in making clinical decision and allocating medical resources.

     

/

返回文章
返回