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

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

Funds: Supported by the Special Grant for Health Care of PLA (17BJZ30)
More Information
  • Corresponding author:

    ZHOU Feihu. Email: feihuzhou301@126.com

  • Received Date: October 26, 2020
  • Available Online: October 18, 2021
  •   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.
  • [1]
    Lobo SM,Rezende E,Mendes CL,et al. Mortality due to Sepsis in Brazil in a real scenario:the Brazilian ICUs project[J]. Rev Bras Ter Intensiva,2019,31(1): 1-4.
    [2]
    Xie JF,Wang HL,Kang Y,et al. The epidemiology of Sepsis in Chinese ICUs:a national cross-sectional survey[J]. Crit Care Med,2020,48(3): e209-e218. (in Chinese) doi: 10.1097/CCM.0000000000004155
    [3]
    Rhee C,Dantes R,Epstein L,et al. Incidence and trends of Sepsis in US hospitals using clinical vs claims data,2009-2014[J]. JAMA,2017,318(13): 1241-1249. doi: 10.1001/jama.2017.13836
    [4]
    Singer M,Deutschman CS,Seymour CW,et al. The third international consensus definitions for Sepsis and septic shock(Sepsis-3)[J]. JAMA,2016,315(8): 801-810. doi: 10.1001/jama.2016.0287
    [5]
    Knaus WA,Draper EA,Wagner DP,et al. APACHE II:a severity of disease classification system[J]. Crit Care Med,1985,13(10): 818-829. doi: 10.1097/00003246-198510000-00009
    [6]
    Vellido A,Ribas V,Morales C,et al. Machine learning in critical care:state-of-the-art and a Sepsis case study[J]. Biomed Eng Online,2018,17(Suppl 1): 135.
    [7]
    Awad A,Bader-El-Den M,McNicholas J,et al. Predicting hospital mortality for intensive care unit patients:Time-series analysis[J]. Health Informatics J,2020,26(2): 1043-1059. doi: 10.1177/1460458219850323
    [8]
    Ocampo-Quintero N, Vidal-Cortés P, del Río Carbajo L, et al. Enhancing Sepsis management through machine learning techniques: a review[J/OL]. https://doi.org/10.1016/j.medin. 2020.04.003.
    [9]
    Ocampo-Quintero N, Vidal-Cortés P, Del Río Carbajo L, et al. Enhancing sepsis management through machine learning techniques: A review[J/OL]. https://doi.org/10.1016/j.medin.2020.04.003.
    [10]
    齐霜,毛智,胡新,等. 基于专科信息系统建立的重症医学数据库:大型三甲医院重症医学数据库的模式[J]. 中华危重病急救医学,2020,32(6): 743-749. doi: 10.3760/cma.j.cn121430-20200520-00393
    [11]
    Johnson AE, Pollard TJ, Shen L, et al. MIMIC-III, a freely accessible critical care database[J]. Sci Data, 2016, 3: 160035.
    [12]
    Johnson AEW,Aboab J,Raffa JD,et al. A comparative analysis of Sepsis identification methods in an electronic database[J]. Crit Care Med,2018,46(4): 494-499. doi: 10.1097/CCM.0000000000002965
    [13]
    Desautels T, Calvert J, Hoffman J, et al. Prediction of Sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach[J]. JMIR Med Inform, 2016, 4(3): e28.
    [14]
    Seymour CW,Liu VX,Iwashyna TJ,et al. Assessment of clinical criteria for sepsis:for the third international consensus definitions for Sepsis and septic shock(Sepsis-3)[J]. JAMA,2016,315(8): 762-774. doi: 10.1001/jama.2016.0288
    [15]
    齐霜,周飞虎. 电子病历数据库脓毒症病例筛选方法综述[J]. 解放军医学院学报,2020,41(9): 918-921. doi: 10.3969/j.issn.2095-5227.2020.09.016
    [16]
    Dinh A, Miertschin S, Young A, et al. A data-driven approach to predicting diabetes and cardiovascular disease with machine learning[J]. BMC Med Inform Decis Mak, 2019, 19(1): 211.
    [17]
    Vaid A, Somani S, Russak AJ, et al. Machine learning to predict mortality and critical events in a cohort of patients with COVID-19 in New York City: model development and validation[J]. J Med Internet Res, 2020, 22(11): e24018.
    [18]
    Qin XJ,Lin HY,Liu TX,et al. Evaluation value of the quick sequential organ failure assessment score on prognosis of intensive care unit adult patients with infection:a 17-year observation study from the real world[J]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue,2018,30(6): 544-548.
    [19]
    Liu ZQ, Meng ZB, Li YF, et al. Prognostic accuracy of the serum lactate level, the SOFA score and the qSOFA score for mortality among adults with Sepsis[J]. Scand J Trauma Resusc Emerg Med, 2019, 27(1): 51.
    [20]
    Lee CW, Kou HW, Chou HS, et al. A combination of SOFA score and biomarkers gives a better prediction of septic AKI and in-hospital mortality in critically ill surgical patients: a pilot study[J]. World J Emerg Surg, 2018, 13: 41.
    [21]
    Wang LL,Chen R,Mo ZX,et al. Predictive value of SOFA score combined AGI grading system in elderly patients with sepsis:a retrospective analysis with 91 patients[J]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue,2017,29(2): 145-149.
    [22]
    Ueno R, Xu LY, Uegami W, et al. Value of laboratory results in addition to vital signs in a machine learning algorithm to predict in-hospital cardiac arrest: a single-center retrospective cohort study[J]. PLoS One, 2020, 15(7): e0235835.
    [23]
    Lauritsen SM,Kalør ME,Kongsgaard EL,et al. Early detection of Sepsis utilizing deep learning on electronic health record event sequences[J]. Artif Intell Med,2020,104: 101820. doi: 10.1016/j.artmed.2020.101820
    [24]
    Scherpf M, Gräßer F, Malberg H, et al. Predicting Sepsis with a recurrent neural network using the MIMIC III database[J]. Comput Biol Med, 2019, 113: 103395.
    [25]
    虎磐,刘晓莉,毛智,等. 基于集成机器学习的ICU老年多器官功能不全早期死亡风险预测模型[J]. 解放军医学院学报,2019,40(6): 513-518. doi: 10.3969/j.issn.2095-5227.2019.06.003
    [26]
    Rojas JC,Carey KA,Edelson DP,et al. Predicting intensive care unit readmission with machine learning using electronic health record data[J]. Ann Am Thorac Soc,2018,15(7): 846-853. doi: 10.1513/AnnalsATS.201710-787OC
    [27]
    Ryoo SM,Lee J,Lee YS,et al. Lactate level versus lactate clearance for predicting mortality in patients with septic shock defined by Sepsis-3[J]. Crit Care Med,2018,46(6): e489-e495. doi: 10.1097/CCM.0000000000003030
    [28]
    Estenssoro E,Kanoore Edul VS,Loudet CI,et al. Predictive validity of Sepsis-3 definitions and Sepsis outcomes in critically ill patients:a cohort study in 49 ICUs in Argentina[J]. Crit Care Med,2018,46(8): 1276-1283. doi: 10.1097/CCM.0000000000003208
    [29]
    Mikkelsen ME,Miltiades AN,Gaieski DF,et al. Serum lactate is associated with mortality in severe Sepsis independent of organ failure and shock[J]. Crit Care Med,2009,37(5): 1670-1677. doi: 10.1097/CCM.0b013e31819fcf68
    [30]
    Pan JZ, Peng ML, Liao C, et al. Relative efficacy and safety of early lactate clearance-guided therapy resuscitation in patients with sepsis: a meta-analysis[J]. Medicine(Baltimore), 2019, 98(8): e14453.
    [31]
    Jones AE,Shapiro NI,Trzeciak S,et al. Lactate clearance vs central venous oxygen saturation as goals of early Sepsis therapy:a randomized clinical trial[J]. JAMA,2010,303(8): 739-746. doi: 10.1001/jama.2010.158
    [32]
    Gaies MG,Gurney JG,Yen AH,et al. Vasoactive-inotropic score as a predictor of morbidity and mortality in infants after cardiopulmonary bypass[J]. Pediatr Crit Care Med,2010,11(2): 234-238. doi: 10.1097/PCC.0b013e3181b806fc
    [33]
    Qin YR,Liu CJ,Xu F,et al. Association between vasoactive-inotropic score and prognosis in children with septic shock[J]. Chin J Contemp Pediatr,2018,20(2): 106-111.

Catalog

    Article Metrics

    Article views (680) PDF downloads (75) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return