Utilizing time series data embedded in electronic health records to develop continuous mortality risk prediction models using hidden Markov models: A sepsis case study
Utilizing time series data embedded in electronic health records to develop continuous mortality risk prediction models using hidden Markov models: A sepsis case study
复制标题
DOI：
10.1177/0962280220929045
复制
发表时间：
2020-06-17
影响因子：
2.3
通讯作者：
Crick, Christopher
中科院分区：
文献类型：
--
作者：
Gupta, Akash;Liu, Tieming;Crick, Christopher
持续的死亡风险监测有助于管理病人的护理和有效地利用有限的医院资源。由于电子健康记录（EHR）的不完整性和不规则性，使用EHR数据开发连续的死亡风险预测是一个挑战。在这项研究中，我们提出了一个框架，以持续监测死亡风险，并将其应用到现实世界的EHR数据。所提出的方法采用隐马尔可夫模型（时间技术），考虑到病人的健康状况和当前的临床体征的值。根据脓毒症-3定义，我们选择了3898例疑似感染患者，以比较时间和非时间方法（决策树（DT），逻辑回归（LR），朴素贝叶斯（NB），随机森林（RF）和支持向量机（SVM））的性能。以受试者工作特征曲线下面积（AUROC）、敏感性、特异性和G均值作为性能指标。在所选数据上，所提出的时间框架的AUROC（0.87）比非时间方法（DT：0.78，NB：0.79，SVM：0.79，LR：0.80和RF：0.80）高9-12%。结果还表明，与临床可接受的床旁标准（G-mean 1/40.71）相比，我们的模型（G-mean 1/40.78）在灵敏度和特异性之间提供了更好的平衡。该框架利用了EHR中可用的纵向数据，并且比非时态方法表现得更好。所提出的方法有助于与患者的健康变化的时间相关的信息，这可以帮助从业者及早计划并制定有效的治疗策略。
Continuous mortality risk monitoring is instrumental to manage a patient's care and to efficiently utilize the limited hospital resources. Due to incompleteness and irregularities of electronic health records (EHR), developing continuous mortality risk prediction using EHR data is a challenge. In this study, we propose a framework to continuously monitor mortality risk, and apply it to the real-world EHR data. The proposed method employs hidden Markov models (temporal technique) that take account of both the previous state of patient's health and the current value of clinical signs. Following the Sepsis-3 definition, we selected 3898 encounters of patients with suspected infection to compare the performance of temporal and non-temporal methods (Decision Tree (DT), Logistic Regression (LR), Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM)). The area under receiver operating characteristics (AUROC) curve, sensitivity, specificity and G-mean were used as performance measures. On the selected data, the AUROC of the proposed temporal framework (0.87) is 9-12% greater than the nontemporal methods (DT: 0.78, NB: 0.79, SVM: 0.79, LR: 0.80 and RF: 0.80). The results also show that our model (G-mean1/40.78) provides a better balance between sensitivity and specificity compared to clinically acceptable bed-side criteria (G-mean1/40.71). The proposed framework leverages the longitudinal data available in EHR and performs better than the non-temporal methods. The proposed method facilitates information related to the time of change of the patient's health that may help practitioners to plan early and develop effective treatment strategies.