Automatic learning of mortality in a CPN model of the systemic inflammatory response syndrome.

The aim of this paper is to apply machine learning as a method to refine a manually constructed CPN for the assessment of the severity of the systemic inflammatory response syndrome (SIRS).The goal of tuning the CPN is to create a scoring system that uses only objective data, compares favourably with other severity-scoring systems and differentiates between sepsis and non-infectious SIRS. The resulting model, the Learned-Age (LA) -Sepsis CPN has good discriminatory ability for the prediction of 30-day mortality with an area under the ROC curve of 0.79. This result compares well to existing scoring systems. The LA-Sepsis CPN also has a modest ability to discriminate between sepsis and non-infectious SIRS.

[1]  S. Andreassen,et al.  Balancing the benefits and costs of antibiotic drugs: the TREAT model. , 2010, Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases.

[2]  D. Mannino,et al.  The epidemiology of sepsis in the United States from 1979 through 2000. , 2003, The New England journal of medicine.

[3]  S Andreassen,et al.  Evaluation of the diagnostic performance of the expert EMG assistant MUNIN. , 1996, Electroencephalography and clinical neurophysiology.

[4]  Leonard Leibovici,et al.  A model for diagnosis of pulmonary infections in solid-organ transplant recipients , 2011, Comput. Methods Programs Biomed..

[5]  Steen Andreassen,et al.  Improving empirical antibiotic treatment using TREAT, a computerized decision support system: cluster randomized trial. , 2006, The Journal of antimicrobial chemotherapy.

[6]  G. Clermont,et al.  Epidemiology of severe sepsis in the United States: Analysis of incidence, outcome, and associated costs of care , 2001, Critical care medicine.

[7]  J. Vincent,et al.  Hypoalbuminemia in Acute Illness: Is There a Rationale for Intervention?: A Meta-Analysis of Cohort Studies and Controlled Trials , 2003, Annals of surgery.

[8]  S. Keim,et al.  Risk stratification of the potentially septic patient in the emergency department: the Mortality in the Emergency Department Sepsis (MEDS) score. , 2009, The Journal of emergency medicine.

[9]  W. Knaus,et al.  Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. The ACCP/SCCM Consensus Conference Committee. American College of Chest Physicians/Society of Critical Care Medicine. , 1992, Chest.

[10]  Joel M. Dulhunty,et al.  Does severe non-infectious SIRS differ from severe sepsis? , 2008, Intensive Care Medicine.

[11]  Steen Andreassen,et al.  The TREAT project: decision support and prediction using causal probabilistic networks. , 2007, International journal of antimicrobial agents.

[12]  Steen Andreassen,et al.  A Causal Probabilistic Network for Optimal Treatment of Bacterial Infections , 2000, IEEE Trans. Knowl. Data Eng..

[13]  Brent King,et al.  A Bayesian model for triage decision support , 2006, Int. J. Medical Informatics.

[14]  Steen Andreassen,et al.  Performance of the TREAT decision support system in an environment with a low prevalence of resistant pathogens. , 2009, The Journal of antimicrobial chemotherapy.

[15]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[16]  S Andreassen,et al.  How do you choose antibiotic treatment? , 1999, BMJ.

[17]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[18]  M. Howell,et al.  Performance of severity of illness scoring systems in emergency department patients with infection. , 2007, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[19]  Peter J. F. Lucas,et al.  A Bayesian decision-support system for diagnosing ventilator-associated pneumonia , 2007, Intensive Care Medicine.

[20]  David W Bates,et al.  Mortality in Emergency Department Sepsis (MEDS) score: A prospectively derived and validated clinical prediction rule* , 2003, Critical care medicine.

[21]  J. Kline,et al.  Performance of the Mortality in Emergency Department Sepsis score for predicting hospital mortality among patients with severe sepsis and septic shock. , 2008, The American journal of emergency medicine.

[22]  Steen Andreassen,et al.  A Probabilistic Network for Fusion of Data and Knowledge in Clinical Microbiology , 2005 .

[23]  S. Lauritzen.  The EM algorithm for graphical association models with missing data , 1995 .

[24]  Inger,et al.  A prediction rule to identify low-risk patients with community-acquired pneumonia. , 1997, The New England journal of medicine.

[25]  Steen Andreassen,et al.  A Bayesian Approach to Model-Development: Design of Continuous Distributions for Infection Variables , 2014 .

[26]  Steen Andreassen,et al.  A Bayesian Approach to Model-Development: Automatic Learning for Tuning Predictive Performance , 2015 .

[27]  C. Sprung,et al.  Surviving Sepsis Campaign: International Guidelines for Management of Severe Sepsis and Septic Shock 2012 , 2013, Critical care medicine.

[28]  L. Lind,et al.  Rapid Emergency Medicine score: a new prognostic tool for in‐hospital mortality in nonsurgical emergency department patients , 2004, Journal of internal medicine.

[29]  C. Sprung,et al.  Sepsis in European intensive care units: Results of the SOAP study* , 2006, Critical care medicine.

[30]  H. Nguyen,et al.  Critical care in the emergency department: A physiologic assessment and outcome evaluation. , 2000, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[31]  Daniel Talmor,et al.  Occult hypoperfusion and mortality in patients with suspected infection , 2007, Intensive Care Medicine.