Establishment and validation of the predictive model for the in-hospital death in patients with sepsis


      • Models to predict in-hospital death of sepsis patients were established.
      • The random forest model had the better predictive ability.
      • The model fit was good in the external population with SOFA score of 13-15.



      Identifying sepsis patients with risk of in-hospital death early can improve the prognosis of patients. This study aimed to develop a model to predict in-hospital death of sepsis patients based on the Medical Information Mart for Intensive Care-Ⅲ (MIMIC-Ⅲ) database, and use clinical data to externally validate the model.


      A total of 1,839 sepsis patients were used for model development, and 125 clinical cases were used for external validation. The discriminatory ability of the model was determined by calculating the area under the curve (AUC) with 95% confidence intervals (CI).


      The AUC of the random forest model and logistic regression model was 0.754 (95%CI, 0.732-0.776) and 0.703 (95%CI, 0.680-0.727), respectively, and the random forest model had higher AUC (Z = 3.070, P = .002). External validation showed that the AUC of the random forest model was 0.539 (95%CI, 0.440-0.628). Further validation was carried out according to gender and SOFA score. The AUC of the model in males and females was 0.648 and 0.412, respectively. In addition, the AUC of the model in the population with SOFA scores of 3-8, 9-12, and 13-15 were 0.705, 0.495, and 0.769, respectively.


      The random forest model had a better predictive ability and a good applicability to external populations with SOFA score of 13-15.

      Key Words

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to American Journal of Infection Control
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Cecconi M
        • Evans L
        • Levy M
        Sepsis and septic shock.
        Lancet. 2018; 392: 75-87
        • Singer M
        • Deutschman CS
        • Seymour CW
        The third international consensus definitions for sepsis and septic shock (Sepsis-3).
        JAMA. 2016; 315: 801-810
        • Reinhart K
        • Daniels R
        • Kissoon N
        Recognizing sepsis as a global health priority - A WHO resolution.
        N Engl J Med. 2017; 377: 414-417
        • Rudd KE
        • Johnson SC
        • Agesa KM
        Global, regional, and national sepsis incidence and mortality, 1990–2017: analysis for the Global Burden of Disease Study.
        Lancet. 2020; 395: 200-211
        • Venet F
        • Monneret G
        Advances in the understanding and treatment of sepsis-induced immunosuppression.
        Nat Rev Nephrol. 2018; 14: 121-137
        • Le Gall JR
        • Lemeshow S
        • Saulnier F
        A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study.
        JAMA. 1993; 270: 2957-2963
        • Zimmerman JE
        • Kramer AA
        • McNair DS
        Acute Physiology and Chronic Health Evaluation (APACHE) IV: hospital mortality assessment for today's critically ill patients.
        Crit Care Med. 2006; 34: 1297-1310
        • Zygun DA
        • Laupland KB
        • Fick GH
        Limited ability of SOFA and MOD scores to discriminate outcome: a prospective evaluation in 1,436 patients.
        Can J Anaesth. 2005; 52: 302-308
        • Khwannimit B
        • Bhurayanontachai R
        • Vattanavanit V
        Validation of the sepsis severity score compared with updated severity scores in predicting hospital mortality in sepsis patients.
        Shock. 2017; 47: 720-725
        • Mikacenic C
        • Price BL
        • Harju-Baker S
        A two-biomarker model predicts mortality in the critically Ill with sepsis.
        Am J Respir Crit Care Med. 2017; 196: 1004-1011
        • Wang AY
        • Ma HP
        • Kao WF
        Red blood cell distribution width is associated with mortality in elderly patients with sepsis.
        T Am J Emerg Med. 2018; 36: 949-953
        • Kong G
        • Lin K
        • Hu Y
        Using machine learning methods to predict in-hospital mortality of sepsis patients in the ICU.
        BMC Med Inform Decis Mak. 2020; 20: 251
        • Johnson AE
        • Pollard TJ
        • Shen L
        MIMIC-III, a freely accessible critical care database.
        Sci Data. 2016; 3160035
        • Powers DMW
        Evaluation: from precision, recall and F-measure to ROC, informedness, markedness & correlation.
        J Mach Learn Res. 2011; 2: 2229-3981
        • Vincent JL
        • Moreno R
        • Takala J
        The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure. On behalf of the Working Group on Sepsis-Related Problems of the European Society of Intensive Care Medicine.
        Intensive Care Med. 1996; 22: 707-710
        • Patel JJ
        • Taneja A
        • Niccum D
        The association of serum bilirubin levels on the outcomes of severe sepsis.
        J Intensive Care Med. 2015; 30: 23-29
        • Zhai R
        • Sheu CC
        • Su L
        Serum bilirubin levels on ICU admission are associated with ARDS development and mortality in sepsis.
        Thorax. 2009; 64: 784-790
        • Yamano S
        • Shimizu K
        • Ogura H
        Low total cholesterol and high total bilirubin are associated with prognosis in patients with prolonged sepsis.
        J Crit Care. 2016; 31: 36-40
        • Jang DH
        • Jo YH
        • Lee JH
        Moderate to severe hyperphosphataemia as an independent prognostic factor for 28-day mortality in adult patients with sepsis.
        Emerg Med J. 2020; 37: 355-361
        • Miller CJ
        • Doepker BA
        • Springer AN
        Impact of serum phosphate in mechanically ventilated patients with severe sepsis and septic shock.
        J Intensive Care Med. 2020; 35: 485-493
        • Shuto E
        • Taketani Y
        • Tanaka R
        Dietary phosphorus acutely impairs endothelial function.
        J Am Soc Nephrol. 2009; 20: 1504-1512
        • Oliveira GA
        • Kowaltowski AJ
        Phosphate increases mitochondrial reactive oxygen species release.
        Free Radic Res. 2004; 38: 1113-1118
        • Adrie C
        • Francais A
        • Alvarez-Gonzalez A
        Model for predicting short-term mortality of severe sepsis.
        Crit Care. 2009; 13: R72
        • Taylor RA
        • Pare JR
        • Venkatesh AK
        Prediction of in-hospital mortality in emergency department patients with sepsis: a local big data-driven, machine learning approach.
        Acad Emerg Med. 2016; 23: 269-278
        • Fang WF
        • Douglas IS
        • Chen YM
        Development and validation of immune dysfunction score to predict 28-day mortality of sepsis patients.
        PloS One. 2017; 12e0187088
        • Yin M
        • Liu X
        • Chen X
        Ischemia-modified albumin is a predictor of short-term mortality in patients with severe sepsis.
        J Crit Care. 2017; 37: 7-12
        • Li K
        • Shi Q
        • Liu S
        Predicting in-hospital mortality in ICU patients with sepsis using gradient boosting decision tree.
        Medicine. 2021; 100: e25813