Machine Learning for Early Outcome Prediction in Septic Patients in the Emergency Department

被引:7
作者
Greco, Massimiliano [1 ,2 ]
Caruso, Pier Francesco [1 ,2 ]
Spano, Sofia [1 ,2 ]
Citterio, Gianluigi [3 ]
Desai, Antonio [1 ,3 ]
Molteni, Alberto [4 ]
Aceto, Romina [2 ]
Costantini, Elena [2 ]
Voza, Antonio [1 ,3 ]
Cecconi, Maurizio [1 ,2 ]
机构
[1] Humanitas Univ, Dept Biomed Sci, Via R Levi Montalcini 4, I-20072 Milan, Italy
[2] IRCCS Humanitas Res Hosp, Dept Anesthesia & Intens Care, Via Manzoni 56, I-20089 Milan, Italy
[3] IRCCS Humanitas Res Hosp, Emergency Dept, Via Manzoni 56, I-20089 Milan, Italy
[4] Osped Eugenio Morelli, Gen Surg Unit, I-23035 Sondalo, Italy
关键词
sepsis; septic shock; emergency medicine; critical care; machine learning; random forest; prognostication; model; SEVERE SEPSIS; MORTALITY; SCORE; DEFINITIONS; SHOCK; ACCURACY; CRITERIA;
D O I
10.3390/a16020076
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Background: Sepsis is one of the major causes of in-hospital death, and is frequent in patients presenting to the emergency department (ED). Early identification of high-risk septic patients is critical. Machine learning (ML) techniques have been proposed for identification and prognostication of ED septic patients, but these models often lack pre-hospital data and lack validation against early sepsis identification scores (such as qSOFA) and scores for critically ill patients (SOFA, APACHE II). Methods We conducted an electronic health record (EHR) study to test whether interpretable and scalable ML models predict mortality in septic ED patients and compared their performance with clinical scores. Consecutive adult septic patients admitted to ED over 18 months were included. We built ML models, ranging from a simple-classifier model, to unbalanced and balanced logistic regression, and random forest, and compared their performance to qSOFA, SOFA, and APACHE II scores. Results: We included 425 sepsis patients after screening 38,500 EHR for sepsis criteria. Overall mortality was 15.2% and peaked in patients coming from retirement homes (38%). Random forest, like balanced (0.811) and unbalanced logistic regression (0.863), identified patients at risk of mortality (0.813). All ML models outperformed qSOFA, APACHE II, and SOFA scores. Age, mean arterial pressure, and serum sodium were major mortality predictors. Conclusions: We confirmed that random forest models outperform previous models, including qSOFA, SOFA, and APACHE II, in identifying septic patients at higher mortality risk, while maintaining good interpretability. Machine learning models may gain further adoption in the future with increasing diffusion and granularity of EHR data, yielding the advantage of increased scalability compared to standard statistical techniques.
引用
收藏
页数:12
相关论文
共 48 条
[1]  
AHRQ, 2022, AHRQ QUAL INDICATORS
[2]   Epidemiology of severe sepsis in the United States: Analysis of incidence, outcome, and associated costs of care [J].
Angus, DC ;
Linde-Zwirble, WT ;
Lidicker, J ;
Clermont, G ;
Carcillo, J ;
Pinsky, MR .
CRITICAL CARE MEDICINE, 2001, 29 (07) :1303-1310
[3]   A Framework for the Development and Interpretation of Different Sepsis Definitions and Clinical Criteria [J].
Angus, Derek C. ;
Seymour, Christopher W. ;
Coopersmith, Craig M. ;
Deutschman, Clifford S. ;
Klompas, Michael ;
Levy, Mitchell M. ;
Martin, Gregory S. ;
Osborn, Tiffany M. ;
Rhee, Chanu ;
Watson, R. Scott .
CRITICAL CARE MEDICINE, 2016, 44 (03) :E113-E121
[4]   Impact of diuretic therapy-associated electrolyte disorders present on admission to the emergency department: a cross-sectional analysis [J].
Arampatzis, Spyridon ;
Funk, Georg-Christian ;
Leichtle, Alexander Benedikt ;
Fiedler, Georg-Martin ;
Schwarz, Christoph ;
Zimmermann, Heinz ;
Exadaktylos, Aristomenis Konstantinos ;
Lindner, Gregor .
BMC MEDICINE, 2013, 11
[5]   Poor performance of quick-SOFA (qSOFA) score in predicting severe sepsis and mortality - a prospective study of patients admitted with infection to the emergency department [J].
Askim, Asa ;
Moser, Florentin ;
Gustad, Lise T. ;
Stene, Helga ;
Gundersen, Maren ;
Asvold, Bjorn Olav ;
Dale, Jostein ;
Bjornsen, Lars Petter ;
Damas, Jan Kristian ;
Solligard, Erik .
SCANDINAVIAN JOURNAL OF TRAUMA RESUSCITATION & EMERGENCY MEDICINE, 2017, 25
[6]   The SPEED (sepsis patient evaluation in the emergency department) score: a risk stratification and outcome prediction tool [J].
Bewersdorf, Jan Philipp ;
Hautmann, Oliver ;
Kofink, Daniel ;
Khalil, Alizan Abdul ;
Abidin, Imran Zainal ;
Loch, Alexander .
EUROPEAN JOURNAL OF EMERGENCY MEDICINE, 2017, 24 (03) :170-175
[7]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[8]   SMOTE: Synthetic minority over-sampling technique [J].
Chawla, Nitesh V. ;
Bowyer, Kevin W. ;
Hall, Lawrence O. ;
Kegelmeyer, W. Philip .
2002, American Association for Artificial Intelligence (16)
[9]  
Dellinger RP, 2013, INTENS CARE MED, V39, P165, DOI [10.1007/s00134-012-2769-8, 10.1097/CCM.0b013e31827e83af]
[10]   Risk factors for mortality despite early protocolized resuscitation for severe sepsis and septic shock in the emergency department [J].
Drumheller, Byron C. ;
Agarwal, Anish ;
Mikkelsen, Mark E. ;
Sante, S. Cham ;
Weber, Anita L. ;
Goyal, Munish ;
Gaieski, David F. .
JOURNAL OF CRITICAL CARE, 2016, 31 (01) :13-20