Literature DB >> 31035074

Evaluation of a machine learning algorithm for up to 48-hour advance prediction of sepsis using six vital signs.

Christopher Barton1, Uli Chettipally2, Yifan Zhou3, Zirui Jiang4, Anna Lynn-Palevsky5, Sidney Le5, Jacob Calvert5, Ritankar Das6.   

Abstract

OBJECTIVE: Sepsis remains a costly and prevalent syndrome in hospitals; however, machine learning systems can increase timely sepsis detection using electronic health records. This study validates a gradient boosted ensemble machine learning tool for sepsis detection and prediction, and compares its performance to existing methods.
MATERIALS AND METHODS: Retrospective data was drawn from databases at the University of California, San Francisco (UCSF) Medical Center and the Beth Israel Deaconess Medical Center (BIDMC). Adult patient encounters without sepsis on admission, and with at least one recording of each of six vital signs (SpO2, heart rate, respiratory rate, temperature, systolic and diastolic blood pressure) were included. We compared the performance of the machine learning algorithm (MLA) to that of commonly used scoring systems. Area under the receiver operating characteristic (AUROC) curve was our primary measure of accuracy. MLA performance was measured at sepsis onset, and at 24 and 48 h prior to sepsis onset.
RESULTS: The MLA achieved an AUROC of 0.88, 0.84, and 0.83 for sepsis onset and 24 and 48 h prior to onset, respectively. These values were superior to those of SIRS (0.66), MEWS (0.61), SOFA (0.72), and qSOFA (0.60) at time of onset. When trained on UCSF data and tested on BIDMC data, sepsis onset AUROC was 0.89. DISCUSSION AND
CONCLUSION: The MLA predicts sepsis up to 48 h in advance and identifies sepsis onset more accurately than commonly used tools, maintaining high performance for sepsis detection when trained and tested on separate datasets.
Copyright © 2019 Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  Electronic health records; Machine learning; Prediction; Sepsis

Year:  2019        PMID: 31035074      PMCID: PMC6556419          DOI: 10.1016/j.compbiomed.2019.04.027

Source DB:  PubMed          Journal:  Comput Biol Med        ISSN: 0010-4825            Impact factor:   4.589


  30 in total

1.  Is the Modified Early Warning Score (MEWS) superior to clinician judgement in detecting critical illness in the pre-hospital environment?

Authors:  James N Fullerton; Charlotte L Price; Natalie E Silvey; Samantha J Brace; Gavin D Perkins
Journal:  Resuscitation       Date:  2012-01-14       Impact factor: 5.262

2.  Epidemiology of severe sepsis in the United States: analysis of incidence, outcome, and associated costs of care.

Authors:  D C Angus; W T Linde-Zwirble; J Lidicker; G Clermont; J Carcillo; M R Pinsky
Journal:  Crit Care Med       Date:  2001-07       Impact factor: 7.598

3.  Validation of physiological scoring systems in the accident and emergency department.

Authors:  C P Subbe; A Slater; D Menon; L Gemmell
Journal:  Emerg Med J       Date:  2006-11       Impact factor: 2.740

Review 4.  Improving clinical practice using clinical decision support systems: a systematic review of trials to identify features critical to success.

Authors:  Kensaku Kawamoto; Caitlin A Houlihan; E Andrew Balas; David F Lobach
Journal:  BMJ       Date:  2005-03-14

5.  Hospitalizations, costs, and outcomes of severe sepsis in the United States 2003 to 2007.

Authors:  Tara Lagu; Michael B Rothberg; Meng-Shiou Shieh; Penelope S Pekow; Jay S Steingrub; Peter K Lindenauer
Journal:  Crit Care Med       Date:  2012-03       Impact factor: 7.598

6.  Implementation of a bundle of quality indicators for the early management of severe sepsis and septic shock is associated with decreased mortality.

Authors:  H Bryant Nguyen; Stephen W Corbett; Robert Steele; Jim Banta; Robin T Clark; Sean R Hayes; Jeremy Edwards; Thomas W Cho; William A Wittlake
Journal:  Crit Care Med       Date:  2007-04       Impact factor: 7.598

Review 7.  Epidemiology of sepsis: race, sex, and chronic alcohol abuse.

Authors:  Marc Moss
Journal:  Clin Infect Dis       Date:  2005-11-15       Impact factor: 9.079

8.  The systemic inflammatory response syndrome (SIRS) to identify infected patients in the emergency room.

Authors:  Fabián Jaimes; Jenny Garcés; Jorge Cuervo; Federico Ramírez; Jorge Ramírez; Andrea Vargas; Claudia Quintero; Jorge Ochoa; Fabio Tandioy; Láder Zapata; Juan Estrada; Maria Yepes; Hiulber Leal
Journal:  Intensive Care Med       Date:  2003-06-26       Impact factor: 17.440

Review 9.  Grand challenges in clinical decision support.

Authors:  Dean F Sittig; Adam Wright; Jerome A Osheroff; Blackford Middleton; Jonathan M Teich; Joan S Ash; Emily Campbell; David W Bates
Journal:  J Biomed Inform       Date:  2007-09-21       Impact factor: 6.317

10.  Economic implications of an evidence-based sepsis protocol: can we improve outcomes and lower costs?

Authors:  Andrew F Shorr; Scott T Micek; William L Jackson; Marin H Kollef
Journal:  Crit Care Med       Date:  2007-05       Impact factor: 7.598

View more
  19 in total

1.  Mortality prediction model for the triage of COVID-19, pneumonia, and mechanically ventilated ICU patients: A retrospective study.

Authors:  Logan Ryan; Carson Lam; Samson Mataraso; Angier Allen; Abigail Green-Saxena; Emily Pellegrini; Jana Hoffman; Christopher Barton; Andrea McCoy; Ritankar Das
Journal:  Ann Med Surg (Lond)       Date:  2020-10-03

Review 2.  Sepsis 2019: What Surgeons Need to Know.

Authors:  Vanessa P Ho; Haytham Kaafarani; Rishi Rattan; Nicholas Namias; Heather Evans; Tanya L Zakrison
Journal:  Surg Infect (Larchmt)       Date:  2019-11-22       Impact factor: 2.150

3.  Predicting in-hospital mortality in ICU patients with sepsis using gradient boosting decision tree.

Authors:  Ke Li; Qinwen Shi; Siru Liu; Yilin Xie; Jialin Liu
Journal:  Medicine (Baltimore)       Date:  2021-05-14       Impact factor: 1.889

4.  Data analytics and clinical feature ranking of medical records of patients with sepsis.

Authors:  Davide Chicco; Luca Oneto
Journal:  BioData Min       Date:  2021-02-03       Impact factor: 2.522

5.  Early Detection of Sepsis With Machine Learning Techniques: A Brief Clinical Perspective.

Authors:  Daniele Roberto Giacobbe; Alessio Signori; Filippo Del Puente; Sara Mora; Luca Carmisciano; Federica Briano; Antonio Vena; Lorenzo Ball; Chiara Robba; Paolo Pelosi; Mauro Giacomini; Matteo Bassetti
Journal:  Front Med (Lausanne)       Date:  2021-02-12

6.  Ground truth labels challenge the validity of sepsis consensus definitions in critical illness.

Authors:  Holger A Lindner; Shigehiko Schamoni; Thomas Kirschning; Corinna Worm; Bianka Hahn; Franz-Simon Centner; Jochen J Schoettler; Michael Hagmann; Jörg Krebs; Dennis Mangold; Stephanie Nitsch; Stefan Riezler; Manfred Thiel; Verena Schneider-Lindner
Journal:  J Transl Med       Date:  2022-01-15       Impact factor: 5.531

7.  Evaluating machine learning models for sepsis prediction: A systematic review of methodologies.

Authors:  Hong-Fei Deng; Ming-Wei Sun; Yu Wang; Jun Zeng; Ting Yuan; Ting Li; Di-Huan Li; Wei Chen; Ping Zhou; Qi Wang; Hua Jiang
Journal:  iScience       Date:  2021-12-20

8.  The impact of recency and adequacy of historical information on sepsis predictions using machine learning.

Authors:  Manaf Zargoush; Alireza Sameh; Mahdi Javadi; Siyavash Shabani; Somayeh Ghazalbash; Dan Perri
Journal:  Sci Rep       Date:  2021-10-21       Impact factor: 4.379

Review 9.  Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy.

Authors:  Lucas M Fleuren; Thomas L T Klausch; Charlotte L Zwager; Linda J Schoonmade; Tingjie Guo; Luca F Roggeveen; Eleonora L Swart; Armand R J Girbes; Patrick Thoral; Ari Ercole; Mark Hoogendoorn; Paul W G Elbers
Journal:  Intensive Care Med       Date:  2020-01-21       Impact factor: 17.440

10.  Survival prediction of patients with sepsis from age, sex, and septic episode number alone.

Authors:  Davide Chicco; Giuseppe Jurman
Journal:  Sci Rep       Date:  2020-10-13       Impact factor: 4.379

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.