Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning

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.

Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis

“…Among these models, 25 studies built 64 machine learning models for predicting in-hospital death [ 22 , 27 , 31 , 33 , 35 , 43 , 45 , 46 , 48 , 49 , 52 – 55 , 58 , 60 , 61 , 63 , 66 , 68 , 69 , 71 , 74 , 75 ], 21 studies built 30 machine learning models for predicting death within 1 month [ 28 – 30 , 34 , 37 – 39 , 41 , 44 , 47 , 48 , 50 , 51 , 55 , 56 , 59 , 65 , 68 , 72 , 73 ], two studies built two machine learning models for predicting death within 3 months [ 32 , 71 ], other two studies built two machine learning models for predicting death within 1 year [ 62 , 70 ], and 4 studies built 6 machine learning models that did not specifically describe the time of sepsis death [ 40 , 42 , 64 , 67 ], these models are depicted in Fig. 2 .…”

Machine learning techniques for mortality prediction in emergency departments: a systematic review

“…The percentage of target patients in the nine included studies is less than 6%. It should be noted that Liu et al 31 and Karlsson et al 32 have conducted their studies on small data sets containing 100 and 445 patients from which 40 and 63 patients died during hospitalisation, respectively. Since the outcome patients in most studies were few, large data sets should be collected to obtain enough event patients.…”