Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach.
Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach.
复制标题
DOI：
10.2196/medinform.5909
复制
发表时间：
2016-09-30
影响因子：
3.2
通讯作者：
Das R
中科院分区：
文献类型：
--
作者：
Desautels T;Calvert J;Hoffman J;Jay M;Kerem Y;Shieh L;Shimabukuro D;Chettipally U;Feldman MD;Barton C;Wales DJ;Das R
脓毒症是住院患者死亡的主要原因之一。尽管如此，预测脓毒症发病的可靠手段仍然难以捉摸。早期和准确的脓毒症发病预测可以允许更积极和有针对性的治疗，同时保持抗菌药物的管理。现有的检测方法性能低下，往往需要耗时的实验室测试结果。为了研究和验证一种脓毒症预测方法，Insight，用于回顾数据中新的Sepsis-3定义，使用电子健康记录数据中的最小变量集进行预测，将该方法的性能与现有评分系统进行比较，并调查数据稀疏性对Insight性能的影响。我们应用Insight，一种机器学习分类系统，使用容易获得的患者数据(生命体征、外周血氧饱和度、格拉斯哥昏迷评分和年龄)的多变量组合，使用回顾性多参数重症监护(MIMIC)-III数据集预测脓毒症，仅限于15岁或以上的重症监护病房(ICU)患者。根据Sepsis-3对脓毒症综合征的定义，我们比较了Insight和快速序贯器官衰竭评估(QSOFA)、修正早期预警评分(MEWS)、全身炎症反应综合征(SIRS)、简化急性生理学评分(SAPS)II和序贯器官衰竭评估(SOFA)的分类性能，以确定患者是否会在发病前的固定时间段成为败血症。我们还测试了Insight系统对随机删除单个输入观测的稳健性。在脓毒症患病率为11.3%的测试数据集中，与以接收器操作特征曲线下面积(AUROC)和精确度-召回曲线下面积(APR)衡量的替代分数相比，Insight具有更好的分类性能。在检测脓毒症发作时，SAINT的AUROC=0.880(SD 0.006)和APR=0.595(SD 0.016)，均优于同时计算的SIRS(AUROC：0.609；APR：0.160)、QSOFA(AUROC：0.772；APR：0.277)和MEWS(AUROC：0.803；APR：0.327)以及SAPS II(AUROC：0.700；APR：0.225)和SOFA(AUROC：0.725；4月：0.284)入院时计算(P<；.001用于所有比较)。在脓毒症发作前1-4小时内观察到类似的结果。在随机删除大约60%的输入数据的实验中，Insight在脓毒症发作时的AUROC为0.781(SD 0.013)，APR为0.401(SD 0.015)。即使有60%的数据缺失，Insight仍然优于相应的SIRS评分(AUROC和APR，P<；.001)，qSOFA评分(P=.0095；P<；.001)，并优于入院时计算的SOFA和SAPS II(AUROC和APR，P<；.001)，所有这些比较分数(除Insight外)都是在没有删除数据的情况下计算出来的。尽管使用的只是生命体征，但洞察力是预测脓毒症发病的有效工具，即使在随机丢失数据的情况下也表现良好。
Sepsis is one of the leading causes of mortality in hospitalized patients. Despite this fact, a reliable means of predicting sepsis onset remains elusive. Early and accurate sepsis onset predictions could allow more aggressive and targeted therapy while maintaining antimicrobial stewardship. Existing detection methods suffer from low performance and often require time-consuming laboratory test results. To study and validate a sepsis prediction method, InSight, for the new Sepsis-3 definitions in retrospective data, make predictions using a minimal set of variables from within the electronic health record data, compare the performance of this approach with existing scoring systems, and investigate the effects of data sparsity on InSight performance. We apply InSight, a machine learning classification system that uses multivariable combinations of easily obtained patient data (vitals, peripheral capillary oxygen saturation, Glasgow Coma Score, and age), to predict sepsis using the retrospective Multiparameter Intelligent Monitoring in Intensive Care (MIMIC)-III dataset, restricted to intensive care unit (ICU) patients aged 15 years or more. Following the Sepsis-3 definitions of the sepsis syndrome, we compare the classification performance of InSight versus quick sequential organ failure assessment (qSOFA), modified early warning score (MEWS), systemic inflammatory response syndrome (SIRS), simplified acute physiology score (SAPS) II, and sequential organ failure assessment (SOFA) to determine whether or not patients will become septic at a fixed period of time before onset. We also test the robustness of the InSight system to random deletion of individual input observations. In a test dataset with 11.3% sepsis prevalence, InSight produced superior classification performance compared with the alternative scores as measured by area under the receiver operating characteristic curves (AUROC) and area under precision-recall curves (APR). In detection of sepsis onset, InSight attains AUROC = 0.880 (SD 0.006) at onset time and APR = 0.595 (SD 0.016), both of which are superior to the performance attained by SIRS (AUROC: 0.609; APR: 0.160), qSOFA (AUROC: 0.772; APR: 0.277), and MEWS (AUROC: 0.803; APR: 0.327) computed concurrently, as well as SAPS II (AUROC: 0.700; APR: 0.225) and SOFA (AUROC: 0.725; APR: 0.284) computed at admission (P<.001 for all comparisons). Similar results are observed for 1-4 hours preceding sepsis onset. In experiments where approximately 60% of input data are deleted at random, InSight attains an AUROC of 0.781 (SD 0.013) and APR of 0.401 (SD 0.015) at sepsis onset time. Even with 60% of data missing, InSight remains superior to the corresponding SIRS scores (AUROC and APR, P<.001), qSOFA scores (P=.0095; P<.001) and superior to SOFA and SAPS II computed at admission (AUROC and APR, P<.001), where all of these comparison scores (except InSight) are computed without data deletion. Despite using little more than vitals, InSight is an effective tool for predicting sepsis onset and performs well even with randomly missing data.
登录
查看更多内容
DOI：
10.1001/jama.2016.0288
发表时间：
2016-02-23
期刊：
JAMA
影响因子：
--
作者：
Seymour CW;Liu VX;Iwashyna TJ;Brunkhorst FM;Rea TD;Scherag A;Rubenfeld G;Kahn JM;Shankar-Hari M;Singer M;Deutschman CS;Escobar GJ;Angus DC
通讯作者：
Angus DC
影响因子：
17.1
作者：
Henry, Katharine E.;Hager, David N.;Saria, Suchi
通讯作者：
Saria, Suchi
影响因子：
9.8
作者：
Johnson AE;Pollard TJ;Shen L;Lehman LW;Feng M;Ghassemi M;Moody B;Szolovits P;Celi LA;Mark RG
通讯作者：
Mark RG
影响因子：
120.7
作者：
LEGALL, JR;LEMESHOW, S;SAULNIER, F
通讯作者：
SAULNIER, F
影响因子：
7.7
作者：
Calvert, Jacob S.;Price, Daniel A.;Das, Ritankar
通讯作者：
Das, Ritankar