Predicting COVID-19 mortality with electronic medical records.
Predicting COVID-19 mortality with electronic medical records.
复制标题
使用电子病历预测新冠肺炎死亡率。
DOI：
10.1038/s41746-021-00383-x
复制
发表时间：
2021-02-04
影响因子：
15.2
通讯作者：
Murphy SN
中科院分区：
文献类型：
--
作者：
Estiri H;Strasser ZH;Klann JG;Naseri P;Wagholikar KB;Murphy SN
这项研究的目的是只使用电子健康记录(EHR)中常规收集的过去的医疗信息来预测新冠肺炎后的死亡，并了解不同年龄组之间危险因素的差异。结合计算方法和临床专业知识，我们挑选了代表46种临床条件的集群，作为新冠肺炎感染后死亡的潜在风险因素。我们训练了年龄分层的广义线性模型(GLM)和分量梯度增强，以预测死亡的可能性，基于我们从患者感染病毒之前所知的情况。尽管只依赖于以前记录的人口统计学和合并症，但我们的模型表现出了与其他预后模型相似的性能，这些模型需要在诊断时或在疾病过程中对症状、化验值和图像进行分类。总的来说，我们发现年龄是新冠肺炎患者死亡率的最重要预测因素。肺炎病史是预测新冠肺炎死亡率的最重要的风险因素之一，典型的流行病学研究很少询问肺炎病史。糖尿病合并并发症和癌症(乳腺癌和前列腺癌)是年龄在45岁到65岁之间的患者的显著危险因素。在65-85岁的患者中，影响肺部系统的疾病，包括间质性肺疾病、慢性阻塞性肺疾病、肺癌和吸烟史，对预测死亡率是重要的。完全根据EHR计算精确的个人级别风险分数的能力对于有效分配和分配资源至关重要，例如在普通人群中确定疫苗接种的优先顺序。
This study aims to predict death after COVID-19 using only the past medical information routinely collected in electronic health records (EHRs) and to understand the differences in risk factors across age groups. Combining computational methods and clinical expertise, we curated clusters that represent 46 clinical conditions as potential risk factors for death after a COVID-19 infection. We trained age-stratified generalized linear models (GLMs) with component-wise gradient boosting to predict the probability of death based on what we know from the patients before they contracted the virus. Despite only relying on previously documented demographics and comorbidities, our models demonstrated similar performance to other prognostic models that require an assortment of symptoms, laboratory values, and images at the time of diagnosis or during the course of the illness. In general, we found age as the most important predictor of mortality in COVID-19 patients. A history of pneumonia, which is rarely asked in typical epidemiology studies, was one of the most important risk factors for predicting COVID-19 mortality. A history of diabetes with complications and cancer (breast and prostate) were notable risk factors for patients between the ages of 45 and 65 years. In patients aged 65–85 years, diseases that affect the pulmonary system, including interstitial lung disease, chronic obstructive pulmonary disease, lung cancer, and a smoking history, were important for predicting mortality. The ability to compute precise individual-level risk scores exclusively based on the EHR is crucial for effectively allocating and distributing resources, such as prioritizing vaccination among the general population.
登录
查看更多内容
DOI：
10.15585/mmwr.mm6915e3
发表时间：
2020-04-17
期刊：
MMWR. Morbidity and mortality weekly report
影响因子：
--
作者：
Garg S;Kim L;Whitaker M;O'Halloran A;Cummings C;Holstein R;Prill M;Chai SJ;Kirley PD;Alden NB;Kawasaki B;Yousey-Hindes K;Niccolai L;Anderson EJ;Openo KP;Weigel A;Monroe ML;Ryan P;Henderson J;Kim S;Como-Sabetti K;Lynfield R;Sosin D;Torres S;Muse A;Bennett NM;Billing L;Sutton M;West N;Schaffner W;Talbot HK;Aquino C;George A;Budd A;Brammer L;Langley G;Hall AJ;Fry A
通讯作者：
Fry A
影响因子：
3.7
作者：
Yuan, Mingli;Yin, Wen;Hu, Yi
通讯作者：
Hu, Yi
影响因子：
168.9
作者：
Huang, Chaolin;Wang, Yeming;Cao, Bin
通讯作者：
Cao, Bin
影响因子：
39
作者：
Wu, Chaomin;Chen, Xiaoyan;Song, Yuanlin
通讯作者：
Song, Yuanlin
影响因子：
19.6
作者：
Cheng, Yichun;Luo, Ran;Xu, Gang
通讯作者：
Xu, Gang