Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning
| dc.contributor.author | Karlsson, Adam | |
| dc.contributor.author | Stassen, Willem | |
| dc.contributor.author | Loutfi, Amy | |
| dc.contributor.author | Wallgren, Ulrika | |
| dc.contributor.author | Larsson, Eric | |
| dc.contributor.author | Kurland, Lisa | |
| dc.date.accessioned | 2021-10-11T09:20:10Z | |
| dc.date.available | 2021-10-11T09:20:10Z | |
| dc.date.issued | 2021-07-12 | |
| dc.date.updated | 2021-07-18T03:08:31Z | |
| dc.description.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. | en_US |
| dc.identifier.apacitation | Karlsson, A., Stassen, W., Loutfi, A., Wallgren, U., Larsson, E., & Kurland, L. (2021). Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning. <i>BMC Emergency Medicine</i>, 21(1), 84. http://hdl.handle.net/11427/35148 | en_ZA |
| dc.identifier.chicagocitation | Karlsson, Adam, Willem Stassen, Amy Loutfi, Ulrika Wallgren, Eric Larsson, and Lisa Kurland "Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning." <i>BMC Emergency Medicine</i> 21, 1. (2021): 84. http://hdl.handle.net/11427/35148 | en_ZA |
| dc.identifier.citation | Karlsson, A., Stassen, W., Loutfi, A., Wallgren, U., Larsson, E. & Kurland, L. 2021. Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning. <i>BMC Emergency Medicine.</i> 21(1):84. http://hdl.handle.net/11427/35148 | en_ZA |
| dc.identifier.ris | TY - Journal Article AU - Karlsson, Adam AU - Stassen, Willem AU - Loutfi, Amy AU - Wallgren, Ulrika AU - Larsson, Eric AU - Kurland, Lisa AB - 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. DA - 2021-07-12 DB - OpenUCT DP - University of Cape Town IS - 1 J1 - BMC Emergency Medicine KW - Assessment KW - Clinical assessment KW - Emergency care systems KW - Emergency department KW - Infectious diseases LK - https://open.uct.ac.za PY - 2021 T1 - Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning TI - Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning UR - http://hdl.handle.net/11427/35148 ER - | en_ZA |
| dc.identifier.uri | https://doi.org/10.1186/s12873-021-00475-7 | |
| dc.identifier.uri | http://hdl.handle.net/11427/35148 | |
| dc.identifier.vancouvercitation | Karlsson A, Stassen W, Loutfi A, Wallgren U, Larsson E, Kurland L. Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning. BMC Emergency Medicine. 2021;21(1):84. http://hdl.handle.net/11427/35148. | en_ZA |
| dc.language.rfc3066 | en | |
| dc.publisher.department | Division of Emergency Medicine | en_US |
| dc.publisher.faculty | Faculty of Health Sciences | en_US |
| dc.rights.holder | The Author(s) | |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | en_US |
| dc.source | BMC Emergency Medicine | en_US |
| dc.source.journalissue | 1 | en_US |
| dc.source.journalvolume | 21 | en_US |
| dc.source.pagination | 84 | en_US |
| dc.source.uri | https://bmcemergmed.biomedcentral.com/ | |
| dc.subject | Assessment | en_US |
| dc.subject | Clinical assessment | en_US |
| dc.subject | Emergency care systems | en_US |
| dc.subject | Emergency department | en_US |
| dc.subject | Infectious diseases | en_US |
| dc.title | Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning | en_US |
| dc.type | Journal Article | en_US |