基于免疫炎症指标预测重症COVID-19的在线模型的开发与验证
本研究回顾性纳入2020年1月27日至3月30日中国两家医院2076例连续COVID-19患者(有明确结局:出院或死亡),以入住ICU、接受有创通气或死亡定义重症。采用LASSO筛选特征,在训练集构建LR、SVM、GBDT、KNN、NN五种机器学习模型,并在内部与外部验证集评估。最终6项特征(降钙素原、[T+B+NK细胞]计数、白介素6、C反应蛋白、白介素2受体、辅助性T细胞/抑制性T细胞)用于建模;由SVM、GBDT、NN组成的集成模型SPMCIIP表现最佳,内部验证AUC 0.991(95%CI 0.979-1.000),外部验证AUC 0.999(95%CI 0.998-1.000),可提前约20天预测重症COVID-19。作者认为该在线模型有望促进对高风险患者的密切监测和早期干预。
要点
- SPMCIIP模型由SVM、GBDT、NN三种算法集成,内部验证AUC 0.991(95%CI 0.979-1.000),外部验证AUC 0.999(95%CI 0.998-1.000)。
- 模型仅用6项入院免疫炎症指标:降钙素原、[T+B+NK细胞]计数、白介素6、C反应蛋白、白介素2受体、辅助性T细胞/抑制性T细胞。
- 重症定义:入住ICU、接受有创通气或死亡。
- SPMCIIP可提前约20天预测重症COVID-19的发生。
- 作者认为该在线模型有望促进对高风险COVID-19患者的密切监测和早期干预。
适用人群与场景
- 2020年1月27日至3月30日中国两家医院连续纳入的2076例COVID-19患者,均有明确结局(出院或死亡)。
诊断标准与关键阈值
- 重症COVID-19定义:入住重症监护室、接受有创通气或死亡。
研究设计与关键结果
- 研究类型:回顾性研究,纳入2076例连续COVID-19患者,来自中国两家医院,设训练集、内部验证集和外部验证集。
- 特征筛选:采用LASSO,最终6项特征为降钙素原、[T+B+NK细胞]计数、白介素6、C反应蛋白、白介素2受体、辅助性T细胞/抑制性T细胞。
- 建模:在训练集构建LR、SVM、GBDT、KNN、NN五种机器学习模型,五种模型预测性能各异但均有前景。
- 集成模型SPMCIIP由SVM、GBDT、NN三种算法衍生,识别重症COVID-19的内部验证AUC 0.991(95%CI 0.979-1.000),外部验证AUC 0.999(95%CI 0.998-1.000)。
- SPMCIIP可提前约20天准确、快速地预测重症COVID-19的发生。
证据类型、等级与局限
- 证据类型:回顾性研究(机器学习模型开发与验证)。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,所开发的在线预测模型SPMCIIP有望促进对COVID-19患者中高重症风险者的密切监测和早期干预。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: Immune and inflammatory dysfunction was reported to underpin critical COVID-19(coronavirus disease 2019). We aim to develop a machine learning model that enables accurate prediction of critical COVID-19 using immune-inflammatory features at admission.
METHODS: We retrospectively collected 2076 consecutive COVID-19 patients with definite outcomes (discharge or death) between January 27, 2020 and March 30, 2020 from two hospitals in China. Critical illness was defined as admission to intensive care unit, receiving invasive ventilation, or death. Least Absolute Shrinkage and Selection Operator (LASSO) was applied for feature selection. Five machine learning algorithms, including Logistic Regression (LR), Support Vector Machine (SVM), Gradient Boosted Decision Tree (GBDT), K-Nearest Neighbor (KNN), and Neural Network (NN) were built in a training dataset, and assessed in an internal validation dataset and an external validation dataset.
RESULTS: Six features (procalcitonin, [T + B + NK cell] count, interleukin 6, C reactive protein, interleukin 2 receptor, T-helper lymphocyte/T-suppressor lymphocyte) were finally used for model development. Five models displayed varying but all promising predictive performance. Notably, the ensemble model, SPMCIIP (severity prediction model for COVID-19 by immune-inflammatory parameters), derived from three contributive algorithms (SVM, GBDT, and NN) achieved the best performance with an area under the curve (AUC) of 0.991 (95% confidence interval [CI] 0.979-1.000) in internal validation cohort and 0.999 (95% CI 0.998-1.000) in external validation cohort to identify patients with critical COVID-19. SPMCIIP could accurately and expeditiously predict the occurrence of critical COVID-19 approximately 20 days in advance.
CONCLUSIONS: The developed online prediction model SPMCIIP is hopeful to facilitate intensive monitoring and early intervention of high risk of critical illness in COVID-19 patients.
TRIAL REGISTRATION: This study was retrospectively registered in the Chinese Clinical Trial Registry ( ChiCTR2000032161 ). vv.
参考来源
- Gao Y, Chen L, Chi J, et al. Development and validation of an online model to predict critical COVID-19 with immune-inflammatory parameters. J Intensive Care. 2021. PMID: 33602326. doi:10.1186/s40560-021-00531-1
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。