单位：[1]Guiqian Int Gen Hosp, Dept Crit Care Med, Guiyang, Peoples R China[2]Peoples Liberat Army Gen Hosp, Med Ctr Chinese 8, Dept Crit Care Med, Beijing 100091, Peoples R China[3]Guizhou Med Univ, Dept Intens Care Unit, Affiliated Hosp, Guiyang, Peoples R China[4]Sichuan Univ, Dept Crit Care Med, West China Hosp, Chengdu, Peoples R China四川大学华西医院[5]First Hosp Jilin Univ, Dept Intens Care Unit, Changchun, Peoples R China[6]Hebei Gen Hosp, Dept Crit Care Med, Shijiazhuang, Hebei, Peoples R China[7]Harbin Med Univ, Dept Crit Care Med, Affiliated Hosp 1, Harbin, Peoples R China[8]Fujian Med Univ, Gen Intens Care Unit Dept, Affiliated Hosp 1, Fuzhou, Peoples R China[9]Capital Med Univ, Fu Xing Hosp, Dept Crit Care Med, Beijing, Peoples R China[10]Zhejiang Univ, Gen Intens Care Unit, Affiliated Hosp 2, Hangzhou, Peoples R China[11]Capital Med Univ, Beijing Tongren Hosp, Dept Crit Care Med, Beijing, Peoples R China首都医科大学附属北京同仁医院首都医科大学附属同仁医院[12]Capital Med Univ, Beijing Friendship Hosp, Dept Crit Care Med, Beijing, Peoples R China首都医科大学附属北京友谊医院[13]Nanchang Univ, Dept Crit Care Med, Affiliated Hosp 1, Nanchang, Jiangxi, Peoples R China[14]Cent South Univ, Xiangya Hosp 3, Dept Crit Care Med, Changsha, Peoples R China[15]Chinese Peoples Liberat Army Gen Hosp, Dept Crit Care Med, Beijing, Peoples R China[16]Capital Med Univ, Beijing Chao Yang Hosp, Surg Intens Care Unit, Beijing, Peoples R China北京朝阳医院[17]Dalian Med Univ, Affiliated Hosp 1, Dalian, Peoples R China大连医科大学附属第一医院[18]Peking Univ, Dept Intens Care, Hosp 3, Beijing, Peoples R China[19]Huazhong Univ Sci & Technol, Tongji Hosp, Tongji Med Coll, Dept Emergency, Wuhan, Peoples R China急诊医学科华中科技大学同济医学院附属同济医院[20]Capital Med Univ, Beijing PingGu Hosp, Dept Crit Care, Beijing, Peoples R China[21]Hosp Shunyi Dist, Intens Care Unit, Beijing, Peoples R China[22]Peoples Liberat Army Gen Hosp, Med Ctr Chinese 4, Dept Crit Care Med, Beijing, Peoples R China[23]Shandong First Med Univ, Shandong Prov Hosp, Dept Crit Care Med, Jinan, Peoples R China[24]Capital Med Univ, Beijing Luhe Hosp, Dept Crit Care, Beijing, Peoples R China[25]Beijing Miyun Hosp, Dept Crit Care, Beijing, Peoples R China[26]Beijing Changping Dist Hosp, Intens Care Unit, Beijing, Peoples R China[27]Zhejiang Univ, Sir Run Run Shaw Hosp, Dept Emergency Med, Sch Med, Hangzhou 310016, Peoples R China
BackgroundSeptic shock comprises a heterogeneous population, and individualized resuscitation strategy is of vital importance. The study aimed to identify subclasses of septic shock with non-supervised learning algorithms, so as to tailor resuscitation strategy for each class.MethodsPatients with septic shock in 25 tertiary care teaching hospitals in China from January 2016 to December 2017 were enrolled in the study. Clinical and laboratory variables were collected on days 0, 1, 2, 3 and 7 after ICU admission. Subclasses of septic shock were identified by both finite mixture modeling and K-means clustering. Individualized fluid volume and norepinephrine dose were estimated using dynamic treatment regime (DTR) model to optimize the final mortality outcome. DTR models were validated in the eICU Collaborative Research Database (eICU-CRD) dataset.ResultsA total of 1437 patients with a mortality rate of 29% were included for analysis. The finite mixture modeling and K-means clustering robustly identified five classes of septic shock. Class 1 (baseline class) accounted for the majority of patients over all days; class 2 (critical class) had the highest severity of illness; class 3 (renal dysfunction) was characterized by renal dysfunction; class 4 (respiratory failure class) was characterized by respiratory failure; and class 5 (mild class) was characterized by the lowest mortality rate (21%). The optimal fluid infusion followed the resuscitation/de-resuscitation phases with initial large volume infusion and late restricted volume infusion. While class 1 transitioned to de-resuscitation phase on day 3, class 3 transitioned on day 1. Classes 1 and 3 might benefit from early use of norepinephrine, and class 2 can benefit from delayed use of norepinephrine while waiting for adequate fluid infusion.ConclusionsSeptic shock comprises a heterogeneous population that can be robustly classified into five phenotypes. These classes can be easily identified with routine clinical variables and can help to tailor resuscitation strategy in the context of precise medicine.
基金：
Yilu "Gexin"-Fluid Therapy Research Fund Project [YLGX-ZZ-2020005]; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [81901929]
第一作者单位：[1]Guiqian Int Gen Hosp, Dept Crit Care Med, Guiyang, Peoples R China
通讯作者：
推荐引用方式(GB/T 7714)：
Ma Penglin,Liu Jingtao,Shen Feng,et al.Individualized resuscitation strategy for septic shock formalized by finite mixture modeling and dynamic treatment regimen[J].CRITICAL CARE.2021,25(1):doi:10.1186/s13054-021-03682-7.
APA：
Ma, Penglin,Liu, Jingtao,Shen, Feng,Liao, Xuelian,Xiu, Ming...&Zhang, Zhongheng.(2021).Individualized resuscitation strategy for septic shock formalized by finite mixture modeling and dynamic treatment regimen.CRITICAL CARE,25,(1)
MLA：
Ma, Penglin,et al."Individualized resuscitation strategy for septic shock formalized by finite mixture modeling and dynamic treatment regimen".CRITICAL CARE 25..1(2021)
医学