Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data-Driven, Machine Learning Approach
Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data-Driven, Machine Learning Approach
复制标题
DOI：
10.1111/acem.12876
复制
发表时间：
2016-03-01
影响因子：
4.4
通讯作者：
Hall, M. Kennedy
中科院分区：
文献类型：
--
作者：
Taylor, R. Andrew;Pare, Joseph R.;Hall, M. Kennedy
在急诊护理中的预测分析主要局限于以简单的诊断和评分系统的形式使用临床决策规则（CDR）。在CDR的开发过程中，分析方法的局限性和对可用性的关注通常将模型限制在被判定为临床相关的预选小变量集和易于计算的规则上。此外，CDR经常受到普遍性问题的困扰，需要数年时间才能开发，并且缺乏随着新信息的可用而更新的能力。新的分析和机器学习技术能够利用电子健康记录（EHR）中已经存在的大量变量，可以更好地预测患者的预后，并促进临床决策支持系统的自动化和部署。在这个概念验证的研究中，一个本地的，大数据驱动的，机器学习的方法相比，现有的CDR和传统的分析方法，使用败血症在医院死亡率的预测作为usecess.MethodsThis是一项回顾性研究的成人艾德访问入院败血症的标准，从2013年10月至2014年10月。脓毒症定义为符合全身炎症反应综合征的标准，在ED中有感染性入院诊断。艾德访视随机分为80%/20%，用于培训和验证。随机森林模型（机器学习方法）使用来自四家医院EHR内可用数据的500多个临床变量构建，以预测院内死亡率。然后将机器学习预测模型与分类和回归树（CART）模型、逻辑回归模型和先前开发的预测工具进行比较，这些预测工具使用受试者工作特征曲线（AUC）下的面积和卡方statistics.ResultsThere在4，676名符合败血症标准的独特患者中有5，278次访问。在培训组的4,222名患者中，210名（5.0%）在住院期间死亡，在验证组的1,056名患者中，50名（4.7%）在住院期间死亡。不同模型的AUC和95%置信区间（CI）如下：随机森林模型，0.86（95% CI = 0.82 - 0.90）; CART模型，0.69（95% CI = 0.62 - 0.77）; logistic回归模型，0.76（95% CI = 0.69至0.82）; CURB-65，0.73（95% CI = 0.67至0.80）; MEDS，0.71（95% CI = 0.63至0.77）;和mREMS，0.72（95% CI = 0.65至0.79）。随机森林模型AUC与所有其他模型具有统计学差异（所有比较p 0.003）。结论在这项概念验证研究中，本地大数据驱动的机器学习方法优于现有CDR以及传统分析技术，用于预测脓毒症艾德患者的住院死亡率。未来的研究应该前瞻性地评估这种方法的有效性，以及它是否能改善高危脓毒症患者的临床结局。所开发的方法可以作为紧急护理中预测分析的新模型的一个例子，该模型可以自动化，应用于其他感兴趣的临床结果，并部署在EHR中，以实现本地相关的临床预测。
ObjectivesPredictive analytics in emergency care has mostly been limited to the use of clinical decision rules (CDRs) in the form of simple heuristics and scoring systems. In the development of CDRs, limitations in analytic methods and concerns with usability have generally constrained models to a preselected small set of variables judged to be clinically relevant and to rules that are easily calculated. Furthermore, CDRs frequently suffer from questions of generalizability, take years to develop, and lack the ability to be updated as new information becomes available. Newer analytic and machine learning techniques capable of harnessing the large number of variables that are already available through electronic health records (EHRs) may better predict patient outcomes and facilitate automation and deployment within clinical decision support systems. In this proof-of-concept study, a local, big data-driven, machine learning approach is compared to existing CDRs and traditional analytic methods using the prediction of sepsis in-hospital mortality as the use case.MethodsThis was a retrospective study of adult ED visits admitted to the hospital meeting criteria for sepsis from October 2013 to October 2014. Sepsis was defined as meeting criteria for systemic inflammatory response syndrome with an infectious admitting diagnosis in the ED. ED visits were randomly partitioned into an 80%/20% split for training and validation. A random forest model (machine learning approach) was constructed using over 500 clinical variables from data available within the EHRs of four hospitals to predict in-hospital mortality. The machine learning prediction model was then compared to a classification and regression tree (CART) model, logistic regression model, and previously developed prediction tools on the validation data set using area under the receiver operating characteristic curve (AUC) and chi-square statistics.ResultsThere were 5,278 visits among 4,676 unique patients who met criteria for sepsis. Of the 4,222 patients in the training group, 210 (5.0%) died during hospitalization, and of the 1,056 patients in the validation group, 50 (4.7%) died during hospitalization. The AUCs with 95% confidence intervals (CIs) for the different models were as follows: random forest model, 0.86 (95% CI = 0.82 to 0.90); CART model, 0.69 (95% CI = 0.62 to 0.77); logistic regression model, 0.76 (95% CI = 0.69 to 0.82); CURB-65, 0.73 (95% CI = 0.67 to 0.80); MEDS, 0.71 (95% CI = 0.63 to 0.77); and mREMS, 0.72 (95% CI = 0.65 to 0.79). The random forest model AUC was statistically different from all other models (p 0.003 for all comparisons).ConclusionsIn this proof-of-concept study, a local big data-driven, machine learning approach outperformed existing CDRs as well as traditional analytic techniques for predicting in-hospital mortality of ED patients with sepsis. Future research should prospectively evaluate the effectiveness of this approach and whether it translates into improved clinical outcomes for high-risk sepsis patients. The methods developed serve as an example of a new model for predictive analytics in emergency care that can be automated, applied to other clinical outcomes of interest, and deployed in EHRs to enable locally relevant clinical predictions.