Department of Medical Sciences, Örebro University, Örebro, Sweden.
Division of emergency Medicine, University of Cape Town, Cape Town, South Africa.
BMC Emerg Med. 2021 Jul 12;21(1):84. doi: 10.1186/s12873-021-00475-7.
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.
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.
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).
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.
败血症是一种危及生命的病症，导致全球近五分之一的死亡。本研究的目的是使用机器学习识别反映败血症患者到达急诊室（ED）表现的变量中，7 天和 30 天死亡率的预测变量。
回顾性横断面设计，纳入 2013 年在瑞典 Södersjukhuset 医院 ED 就诊并出院时国际疾病分类（ICD）第 10 版编码为败血症的所有患者。所有预测均使用反映 ED 表现的 91 个变量的平衡随机森林分类器进行。使用详尽搜索从最终模型中去除不必要的变量。进行了 10 折交叉验证，并使用以下各项的平均值描述准确性：AUC、敏感性、特异性、PPV、NPV、阳性 LR 和阴性 LR。
研究人群包括 445 例败血症患者，随机分为训练组（n=356，80%）和验证组（n=89，20%）。预测 7 天死亡率的 6 个最重要变量是：“发热”、“言语反应异常”、“饱和度低”、“由紧急医疗服务（EMS）到达”、“异常行为或意识水平”和“寒战”。包含这些变量的模型 AUC 为 0.83（95%CI：0.80-0.86）。预测 30 天死亡率的最终模型使用类似的 6 个变量，但包含“呼吸困难”而不是“异常行为或意识水平”。该模型的 AUC 为 0.80（95%CI，0.78-0.82）。
结果表明，6 个特定变量可准确预测 7 天和 30 天死亡率，这表明这些症状、观察结果和到达方式可能是未来败血症患者 ED 死亡率预测工具中包含生命体征的重要组成部分。此外，随机森林似乎是构建未来研究的合适机器学习方法。
