Adam Karlsson1, Willem Stassen2, Amy Loutfi3, Ulrika Wallgren4,5, Eric Larsson6, Lisa Kurland7,8,9. 1. Department of Medical Sciences, Örebro University, Örebro, Sweden. 2. Division of emergency Medicine, University of Cape Town, Cape Town, South Africa. 3. AASS Research Centre, Department of Science and Technology, Örebro university, Örebro, Sweden. 4. Department of Clinical Science and Education, Karolinska Institutet, Söderssjukhuset, Stockholm, Sweden. 5. Departmen of Emergency Medicine, Örebro University Hospital and School of Medicine, Örebro University , Örebro, Sweden. 6. Department of Infectious Diseases, Centralsjukhuset, Karlstad, Sweden. 7. Department of Medical Sciences, Örebro University, Örebro, Sweden. lisa.kurland@oru.se. 8. Departmen of Emergency Medicine, Örebro University Hospital and School of Medicine, Örebro University , Örebro, Sweden. lisa.kurland@oru.se. 9. Department of Medical Sciences, Örebro University, Södra Grev Rosengatan 30, 703 62, Örebro, Sweden. lisa.kurland@oru.se.
Abstract
BACKGROUND: Sepsis is a life-threatening condition, causing almost one fifth of all deaths worldwide. The aim of the current study was to identify variables predictive of 7- and 30-day mortality among variables reflective of the presentation of septic patients arriving to the emergency department (ED) using machine learning. METHODS: Retrospective cross-sectional design, including all patients arriving to the ED at Södersjukhuset in Sweden during 2013 and discharged with an International Classification of Diseases (ICD)-10 code corresponding to sepsis. All predictions were made using a Balanced Random Forest Classifier and 91 variables reflecting ED presentation. An exhaustive search was used to remove unnecessary variables in the final model. A 10-fold cross validation was performed and the accuracy was described using the mean value of the following: AUC, sensitivity, specificity, PPV, NPV, positive LR and negative LR. RESULTS: The study population included 445 septic patients, randomised to a training (n = 356, 80%) and a validation set (n = 89, 20%). The six most important variables for predicting 7-day mortality were: "fever", "abnormal verbal response", "low saturation", "arrival by emergency medical services (EMS)", "abnormal behaviour or level of consciousness" and "chills". The model including these variables had an AUC of 0.83 (95% CI: 0.80-0.86). The final model predicting 30-day mortality used similar six variables, however, including "breathing difficulties" instead of "abnormal behaviour or level of consciousness". This model achieved an AUC = 0.80 (CI 95%, 0.78-0.82). CONCLUSIONS: The results suggest that six specific variables were predictive of 7- and 30-day mortality with good accuracy which suggests that these symptoms, observations and mode of arrival may be important components to include along with vital signs in a future prediction tool of mortality among septic patients presenting to the ED. In addition, the Random Forests appears to be a suitable machine learning method on which to build future studies.
BACKGROUND:Sepsis is a life-threatening condition, causing almost one fifth of all deaths worldwide. The aim of the current study was to identify variables predictive of 7- and 30-day mortality among variables reflective of the presentation of septicpatients arriving to the emergency department (ED) using machine learning. METHODS: Retrospective cross-sectional design, including all patients arriving to the ED at Södersjukhuset in Sweden during 2013 and discharged with an International Classification of Diseases (ICD)-10 code corresponding to sepsis. All predictions were made using a Balanced Random Forest Classifier and 91 variables reflecting ED presentation. An exhaustive search was used to remove unnecessary variables in the final model. A 10-fold cross validation was performed and the accuracy was described using the mean value of the following: AUC, sensitivity, specificity, PPV, NPV, positive LR and negative LR. RESULTS: The study population included 445 septicpatients, randomised to a training (n = 356, 80%) and a validation set (n = 89, 20%). The six most important variables for predicting 7-day mortality were: "fever", "abnormal verbal response", "low saturation", "arrival by emergency medical services (EMS)", "abnormal behaviour or level of consciousness" and "chills". The model including these variables had an AUC of 0.83 (95% CI: 0.80-0.86). The final model predicting 30-day mortality used similar six variables, however, including "breathing difficulties" instead of "abnormal behaviour or level of consciousness". This model achieved an AUC = 0.80 (CI 95%, 0.78-0.82). CONCLUSIONS: The results suggest that six specific variables were predictive of 7- and 30-day mortality with good accuracy which suggests that these symptoms, observations and mode of arrival may be important components to include along with vital signs in a future prediction tool of mortality among septicpatients presenting to the ED. In addition, the Random Forests appears to be a suitable machine learning method on which to build future studies.
Authors: Mervyn Singer; Clifford S Deutschman; Christopher Warren Seymour; Manu Shankar-Hari; Djillali Annane; Michael Bauer; Rinaldo Bellomo; Gordon R Bernard; Jean-Daniel Chiche; Craig M Coopersmith; Richard S Hotchkiss; Mitchell M Levy; John C Marshall; Greg S Martin; Steven M Opal; Gordon D Rubenfeld; Tom van der Poll; Jean-Louis Vincent; Derek C Angus Journal: JAMA Date: 2016-02-23 Impact factor: 56.272
Authors: Ricard Ferrer; Ignacio Martin-Loeches; Gary Phillips; Tiffany M Osborn; Sean Townsend; R Phillip Dellinger; Antonio Artigas; Christa Schorr; Mitchell M Levy Journal: Crit Care Med Date: 2014-08 Impact factor: 7.598
Authors: Brian Suffoletto; Adam Frisch; Arjun Prabhu; Jeffrey Kristan; Francis X Guyette; Clifton W Callaway Journal: Prehosp Emerg Care Date: 2011-04-27 Impact factor: 3.077
Authors: Daniel E Leisman; Chananya Goldman; Martin E Doerfler; Kevin D Masick; Susan Dries; Eric Hamilton; Mangala Narasimhan; Gulrukh Zaidi; Jason A D'Amore; John K D'Angelo Journal: Crit Care Med Date: 2017-10 Impact factor: 7.598
Authors: Kristina E Rudd; Sarah Charlotte Johnson; Kareha M Agesa; Katya Anne Shackelford; Derrick Tsoi; Daniel Rhodes Kievlan; Danny V Colombara; Kevin S Ikuta; Niranjan Kissoon; Simon Finfer; Carolin Fleischmann-Struzek; Flavia R Machado; Konrad K Reinhart; Kathryn Rowan; Christopher W Seymour; R Scott Watson; T Eoin West; Fatima Marinho; Simon I Hay; Rafael Lozano; Alan D Lopez; Derek C Angus; Christopher J L Murray; Mohsen Naghavi Journal: Lancet Date: 2020-01-18 Impact factor: 202.731
Authors: Amin Naemi; Thomas Schmidt; Marjan Mansourvar; Mohammad Naghavi-Behzad; Ali Ebrahimi; Uffe Kock Wiil Journal: BMJ Open Date: 2021-11-02 Impact factor: 2.692