Development of a prognostic model for mortality in COVID-19 infection using machine learning.

Development of a prognostic model for mortality in COVID-19 infection using machine learning.
复制标题

DOI:
10.1038/s41379-020-00700-x
复制
发表时间:
2021-03
期刊:
Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc
影响因子:
--
通讯作者:
McCaffrey P
McCaffrey P
中科院分区:
其他
文献类型:
--
作者:
Booth AL;Abels E;McCaffrey P

文献摘要

参考文献

被引文献

相似文献

2019 冠状病毒病 (COVID-19) 是一种由严重急性呼吸综合征冠状病毒 2 (SARS-CoV-2) 感染引起的新型疾病,自 2020 年初以来迅速上升,成为全球大流行病。由于 COVID-19 的快速增长,医院的任务是在没有已知有效疗法、现有疫苗或完善的临床管理指南的情况下管理越来越多的此类病例。在 COVID-19 大流行期间,迫切需要可操作的知识,然而,考虑到这种疾病的紧迫性以及医疗保健人员必须尽快制定有用的管理政策,没有足够的时间等待详细、受控、前瞻性临床研究的结论。因此,我们提出了一项回顾性研究,评估 SARS-CoV-2 RT-PCR 检测结果呈阳性的患者的实验室数据和死亡率。本研究的目的是确定死亡风险最大的患者的预后血清生物标志物。为此,我们开发了一个机器学习模型,使用 398 名患者(43 名过期患者和 355 名未过期患者)的 5 个血清化学实验室参数(C 反应蛋白、血尿素氮、血清钙、血清白蛋白和乳酸)来预测患者过期前 48 小时内的死亡情况。由此产生的支持向量机模型在根据保留的测试数据预测患者过期状态方面实现了 91% 的敏感性和 91% 的特异性 (AUC 0.93)。最后,我们根据不同的模型预测检查每个特征和特征组合的影响,强调影响 SARS-CoV-2 感染结果的实验​​室值的重要模式。
Coronavirus disease 2019 (COVID-19) is a novel disease resulting from infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which has quickly risen since the beginning of 2020 to become a global pandemic. As a result of the rapid growth of COVID-19, hospitals are tasked with managing an increasing volume of these cases with neither a known effective therapy, an existing vaccine, nor well-established guidelines for clinical management. The need for actionable knowledge amidst the COVID-19 pandemic is dire and yet, given the urgency of this illness and the speed with which the healthcare workforce must devise useful policies for its management, there is insufficient time to await the conclusions of detailed, controlled, prospective clinical research. Thus, we present a retrospective study evaluating laboratory data and mortality from patients with positive RT-PCR assay results for SARS-CoV-2. The objective of this study is to identify prognostic serum biomarkers in patients at greatest risk of mortality. To this end, we develop a machine learning model using five serum chemistry laboratory parameters (c-reactive protein, blood urea nitrogen, serum calcium, serum albumin, and lactic acid) from 398 patients (43 expired and 355 non-expired) for the prediction of death up to 48 h prior to patient expiration. The resulting support vector machine model achieved 91% sensitivity and 91% specificity (AUC 0.93) for predicting patient expiration status on held-out testing data. Finally, we examine the impact of each feature and feature combination in light of different model predictions, highlighting important patterns of laboratory values that impact outcomes in SARS-CoV-2 infection.
DOI: 10.1093/ajcp/aqw064
发表时间: 2016-06-01
影响因子: 3.5
作者:
Luo, Yuan;Szolovits, Peter;Baron, Jason M.
通讯作者: Baron, Jason M.
DOI: 10.1039/c7lc00955k
发表时间: 2018-01-30
期刊: Lab on a chip
影响因子: 6.1
作者:
Ko J;Baldassano SN;Loh PL;Kording K;Litt B;Issadore D
通讯作者: Issadore D
DOI: 10.1172/jci137244
发表时间: 2020-05-01
影响因子: 15.9
作者:
Chen, Guang;Wu, Di;Ning, Qin
通讯作者: Ning, Qin
DOI: 10.1002/jmv.25871
发表时间: 2020-04-25
影响因子: 12.7
作者:
Tan, Chaochao;Huang, Ying;Li, Xiaosong
通讯作者: Li, Xiaosong
DOI: 10.4103/jpi.jpi_34_17
发表时间: 2017
影响因子: --
作者:
Korbar B;Olofson AM;Miraflor AP;Nicka CM;Suriawinata MA;Torresani L;Suriawinata AA;Hassanpour S
通讯作者: Hassanpour S