A Locally Optimized Data-Driven Tool to Predict Sepsis-Associated Vasopressor Use in the ICU.
A Locally Optimized Data-Driven Tool to Predict Sepsis-Associated Vasopressor Use in the ICU.
复制标题
DOI：
10.1097/ccm.0000000000005175
复制
发表时间：
2021-12-01
影响因子：
8.8
通讯作者：
Nemati S
中科院分区：
文献类型：
--
作者：
Holder AL;Shashikumar SP;Wardi G;Buchman TG;Nemati S
训练一个模型来预测ICU脓毒症患者中血管加压药的使用，并使用领域适应（一种迁移学习方法）优化医院系统的外部性能。观察性队列研究2014年1月至2017年6月的两个学术医疗中心。分析了14，512例患者（开发中心9，423例，验证中心5，089例）的数据，这些患者在入住重症监护室（ICU）之前或期间符合医疗保险和医疗补助服务中心（CMS）严重脓毒症的定义。如果患者从未发生脓毒症，如果ICU住院时间少于8小时或超过20天，或者如果他们在ICU入院的前4小时内发生休克，则将其排除。40个回顾性收集的功能，从电子病历（EMR）的成人ICU患者在开发网站（4家医院）被用作输入的神经网络威布尔-考克斯生存模型，以获得一个预测工具，未来的血管加压药的需求。域自适应更新了参数，以优化验证站点（2家医院）的模型性能，这是一个2,000英里以外的不同医疗保健系统。两个研究中心的队列被随机分为训练集和测试集（分别为80%和20%）。当应用于开发中心的测试集时，该模型提前4 - 24小时预测血管加压药的使用，受试者工作特征曲线下面积[AUCroc]、特异性和阳性预测值（PPV）范围分别为0.80-0.81、56.2-61.8%和5.6-12.1%。域适应改善了模型的性能，以预测验证中心4小时内血管加压药的使用（AUCroc 0.81 [CI 0.80-0.81]从0.77 [CI 0.76-0.77]，p<0.01;特异性59.7% [CI 58.9-62.5%]从49.9% [CI 49.5-50.7%]，p<0.01; PPV 8.9% [CI 8.5-9.4%]，从7.3 [7.1-7.4%]，p<0.01）。领域适应改善了预测脓毒症相关血管加压药使用模型在外部验证期间的性能。
To train a model to predict vasopressor use in ICU patients with sepsis, and optimize external performance across hospital systems using domain adaptation, a transfer learning approach. Observational cohort study Two academic medical centers from January 2014 to June 2017. Data were analyzed from 14,512 patients (9,423 at the development site, 5,089 at the validation site) who were admitted to an intensive care unit (ICU) and met Center for Medicare and Medicaid Services (CMS) definition of severe sepsis either before or during the ICU stay. Patients were excluded if they never developed sepsis, if the ICU length of stay was less than 8 hours or more than 20 days, or if they developed shock up to the first 4 hours of ICU admission. Forty retrospectively collected features from the electronic medical records (EMR) of adult ICU patients at the development site (4 hospitals) were used as inputs for a neural network Weibull-Cox survival model to derive a prediction tool for future need of vasopressors. Domain adaptation updated parameters to optimize model performance in the validation site (2 hospitals), a different healthcare system over 2,000 miles away. The cohorts at both sites were randomly split into training and testing sets (80% and 20%, respectively). When applied to the test set in the development site, the model predicted vasopressor use 4 to 24 hours in advance with an area under the receiver operator characteristic curve [AUCroc], specificity, and positive predictive value (PPV) ranging from 0.80-0.81, 56.2-61.8% and 5.6-12.1% respectively. Domain adaptation improved performance of the model to predict vasopressor use within 4 hours at the validation site (AUCroc 0.81 [CI 0.80-0.81] from 0.77 [CI 0.76-0.77], p<0.01; specificity 59.7% [CI 58.9-62.5%] from 49.9% [CI 49.5-50.7%], p<0.01; PPV 8.9% [CI 8.5-9.4%] from 7.3 [7.1-7.4%], p<0.01). Domain adaptation improved performance of a model predicting sepsis-associated vasopressor use during external validation.