Chaotic nature of sepsis and multiple organ failure cannot be explained by linear statistical methods

Saliba, Sarah; Kilic, Yakup; Uranues, Selman

doi:10.1186/cc6856

Cited by 9 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Commonly used linear ML methods in sepsis predictive analytics include multivariate linear regression [32], logistic regression [6,17,33,34] and linear support vector machine (SVM) [29,35] classifiers. However, sepsis has been characterized as a "complex systems" class problem [36], with multiple organ failures that represent a "chaotic adaptation" to severe stress [37] which cannot be explained by linear statistical systems [38]. The recognized complexity of the disease where actual covariate interrelationships can be complex and non-linear may explain the modest predictive performance of tools derived using logistic regression.…”

Section: Machine Learning (Ml)mentioning

confidence: 99%

Semantically Enhanced Dynamic Bayesian Network for Detecting Sepsis Mortality Risk in ICU Patients with Infection

Wang,

Velez,

Apostolova

et al. 2018

Preprint

View full text Add to dashboard Cite

Although timely sepsis diagnosis and prompt interventions in Intensive Care Unit (ICU) patients are associated with reduced mortality, early clinical recognition is frequently impeded by non-specific signs of infection and failure to detect signs of sepsis-induced organ dysfunction in a constellation of dynamically changing physiological data. The goal of this work is to identify patient at risk of life-threatening sepsis utilizing a data-centered and machine learning-driven approach. We derive a mortality risk predictive dynamic Bayesian network (DBN) guided by a customized sepsis knowledgebase and compare the predictive accuracy of the derived DBN with the Sepsis-related Organ Failure Assessment (SOFA) score, the Quick SOFA (qSOFA) score, the Simplified Acute Physiological Score (SAPS-II) and the Modified Early Warning Score (MEWS) tools.A customized sepsis ontology was used to derive the DBN node structure and semantically characterize temporal features derived from both structured physiological data and unstructured clinical notes. We assessed the performance in predicting mortality risk of the DBN predictive model and compared performance to other models using Receiver Operating Characteristic (ROC) curves, area under curve (AUROC), calibration curves, and risk distributions.The derived dataset consists of 24,506 ICU stays from 19,623 patients with evidence of suspected infection, with 2,829 patients deceased at discharge. The DBN AUROC was found to be 0.91, which outperformed the SOFA (0.843), qSOFA (0.66), MEWS (0.729), and SAPS-II (0.766) scoring tools. Continuous Net Reclassification Index and Integrated Discrimination Improvement analysis supported the superiority DBN with respect to SOFA, qSOFA, MEWS, and SAPS-II. Compared with conventional rule-based risk scoring tools, the sepsis knowledgebase-driven DBN algorithm offers improved performance for predicting mortality of infected patients in intensive care units.

show abstract

Section: Machine Learning (Ml)mentioning

confidence: 99%

Semantically Enhanced Dynamic Bayesian Network for Detecting Sepsis Mortality Risk in ICU Patients with Infection

Wang,

Velez,

Apostolova

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…The impact of QI on sepsis resuscitation is limited by the stochastic nature of the treatment process. This characteristic cannot be elucidated based only on linear statistical analysis and QI methods (Saliba et al, 2008). The complexity of the treatment process cannot be explained and analysed only by the clinical studies and linear statistics (Kilic et al, 2009).…”

Section: Literature Reviewmentioning

confidence: 99%

System analysis and process redesign for quality improvement of sepsis resuscitation

Al-Qudah

Dong

et al. 2014

IJCENT

View full text Add to dashboard Cite

Severe sepsis and septic shock are serious medical emergencies that require timely treatment. The Sepsis Resuscitation Bundle was implemented to frame the resuscitation time within 6 h of onset. Missing this goal has a major impact on treatment outcomes and cost. This study demonstrates the potential of applying a systems engineering approach to improve resuscitation compliance. Root cause analysis, an industrial engineering tool, was used to analyse the existing process and identify sources of delay. Simulation modelling was performed to study event dynamics and propose alternatives. Sensitivity analysis was used to test the proposed alternatives. Results showed that improvements could be achieved by adopting major event adjustments. 84 S.K. Alqudah et al.Applying these adjustments is projected to increase compliance from 50% to 71% and reduce average patient cycle time by 32%, improving the quality of sepsis and septic shock resuscitation in the ICU.

show abstract

“…The nonlinear behavior of sepsis has been regarded as a complex and chaotic process by some investigators, including us [ 1 , 3 ]. There are major genetic polymorphisms that cause individual variances in the response to septic challenge.…”

mentioning

confidence: 99%

Sepsis and multiple organ failure represent a chaotic adaptation to severe stress which must be controlled at nanoscale

Kilic

Tez

2009

Critical Care

Self Cite

View full text Add to dashboard Cite

Chaotic nature of sepsis and multiple organ failure cannot be explained by linear statistical methods

Cited by 9 publications

References 3 publications

Semantically Enhanced Dynamic Bayesian Network for Detecting Sepsis Mortality Risk in ICU Patients with Infection

Semantically Enhanced Dynamic Bayesian Network for Detecting Sepsis Mortality Risk in ICU Patients with Infection

System analysis and process redesign for quality improvement of sepsis resuscitation

Sepsis and multiple organ failure represent a chaotic adaptation to severe stress which must be controlled at nanoscale

Contact Info

Product

Resources

About