背景:在创伤系统中,急诊科(ED)是医院的第一联系人,对于分配医疗资源至关重要。然而,关于在ED中死亡的患者的信息通常有限。
目的:本研究的目的是开发一种人工智能(AI)模型来预测创伤死亡率,并分析所有急诊就诊患者的相关死亡率因素。
方法:我们使用了韩国国家紧急事务局信息系统(NEDIS)数据集(N=6,536,306),在2016年至2019年期间合并了400多家医院。我们纳入了国际疾病分类第10版(ICD-10)代码,并选择了以下输入特征来预测ED患者的死亡率:年龄,性别,故意,损伤,紧急症状,警报/言语/疼痛/反应迟钝(AVPU)量表,韩国分诊和敏锐度量表(KTAS),和生命体征。我们比较了AI输入的三种不同特征集性能:所有特征(n=921),ICD-10功能(n=878),以及不包括ICD-10代码的功能(n=43)。我们通过5倍交叉验证设计了各种机器学习模型,并将每个模型的性能与传统预测模型的性能进行了比较。最后,我们调查了可解释的AI特征效果,并在公共网站上部署了我们最终的AI模型,在就诊的患者中提供我们的死亡率预测结果。
结果:我们提出的具有全特征集的AI模型在接收器工作特性曲线(AUROC)下实现了0.9974的最高面积(自适应增强[AdaBoost],AdaBoost+光梯度增强机[LightGBM]:合奏),优于其他最先进的机器学习和传统预测模型,包括极端梯度提升(AUROC=0.9972),LightGBM(AUROC=0.9973),基于ICD的损伤严重程度评分(包含模型的AUC=0.9328,专有模型的AUROC=0.9567),和KTAS(AUROC=0.9405)。此外,我们提出的AI模型优于为所有ED来访者设计的最先进的AI模型(AUROC=0.7675).从AI模型来看,我们还发现,年龄和无反应性(昏迷)是急诊就诊患者的前两个死亡率预测因素,其次是氧饱和度,多发性肋骨骨折(ICD-10代码S224),痛苦的反应(昏迷,分房),腰椎骨折(ICD-10代码S320)。
结论:我们提出的AI模型在预测ED死亡率方面具有显著的准确性。包括外部验证的必要性,一个庞大的全国性数据集将提供一个更准确的模型,并最大限度地减少过拟合。我们预计我们基于AI的风险计算器工具将大大帮助医疗保健提供者,特别是关于创伤患者的分诊和早期诊断。
Within the trauma system, the emergency department (ED) is the hospital\'s first contact and is vital for allocating medical resources. However, there is generally limited information about patients that die in the ED.
The aim of this study was to develop an artificial intelligence (AI) model to predict trauma mortality and analyze pertinent mortality factors for all patients visiting the ED.
We used the Korean National Emergency Department Information System (NEDIS) data set (N=6,536,306), incorporating over 400 hospitals between 2016 and 2019. We included the International Classification of Disease 10th Revision (ICD-10) codes and chose the following input features to predict ED patient mortality: age, sex, intentionality, injury, emergent symptom, Alert/Verbal/Painful/Unresponsive (AVPU) scale, Korean Triage and Acuity Scale (KTAS), and vital signs. We compared three different feature set performances for AI input: all features (n=921), ICD-10 features (n=878), and features excluding ICD-10 codes (n=43). We devised various machine learning models with an ensemble approach via 5-fold cross-validation and compared the performance of each model with that of traditional prediction models. Lastly, we investigated explainable AI feature effects and deployed our final AI model on a public website, providing access to our mortality prediction results among patients visiting the ED.
Our proposed AI model with the all-feature set achieved the highest area under the receiver operating characteristic curve (AUROC) of 0.9974 (adaptive boosting [AdaBoost], AdaBoost + light gradient boosting machine [LightGBM]: Ensemble), outperforming other state-of-the-art machine learning and traditional prediction models, including extreme gradient boosting (AUROC=0.9972), LightGBM (AUROC=0.9973), ICD-based injury severity scores (AUC=0.9328 for the inclusive model and AUROC=0.9567 for the exclusive model), and KTAS (AUROC=0.9405). In addition, our proposed AI model outperformed a cutting-edge AI model designed for in-hospital mortality prediction (AUROC=0.7675) for all ED visitors. From the AI model, we also discovered that age and unresponsiveness (coma) were the top two mortality predictors among patients visiting the ED, followed by oxygen saturation, multiple rib fractures (ICD-10 code S224), painful response (stupor, semicoma), and lumbar vertebra fracture (ICD-10 code S320).
Our proposed AI model exhibits remarkable accuracy in predicting ED mortality. Including the necessity for external validation, a large nationwide data set would provide a more accurate model and minimize overfitting. We anticipate that our AI-based risk calculator tool will substantially aid health care providers, particularly regarding triage and early diagnosis for trauma patients.