Covid-19 Automated Diagnosis and Risk Assessment through Metabolomics and Machine Learning.
Covid-19 Automated Diagnosis and Risk Assessment through Metabolomics and Machine Learning.
复制标题
DOI：
10.1021/acs.analchem.0c04497
复制
发表时间：
2021-02-02
影响因子：
7.4
通讯作者：
Catharino RR
中科院分区：
文献类型：
--
作者：
Delafiori J;Navarro LC;Siciliano RF;de Melo GC;Busanello ENB;Nicolau JC;Sales GM;de Oliveira AN;Val FFA;de Oliveira DN;Eguti A;Dos Santos LA;Dalçóquio TF;Bertolin AJ;Abreu-Netto RL;Salsoso R;Baía-da-Silva D;Marcondes-Braga FG;Sampaio VS;Judice CC;Costa FTM;Durán N;Perroud MW;Sabino EC;Lacerda MVG;Reis LO;Fávaro WJ;Monteiro WM;Rocha AR;Catharino RR
COVID-19仍给全球带来沉重的健康和财政负担。患者筛查和风险管理方面的障碍对政府和当局如何引导资源、规划重新开放以及卫生对策起着至关重要的作用，特别是在贫困是等式主要组成部分的地区。有效的诊断方法必须高度准确，同时具有成本效益。我们将基于机器学习的算法与质谱相结合，创建了一个快速平台，可以在几分钟内区分血浆样本中的COVID-19，同时还提供了风险评估工具，以协助医疗保健专业人员进行患者管理和决策。一项横断面研究于2020年4月至7月从巴西三个震中招募了815名患者（442名COVID-19患者，350名对照患者和23名COVID-19可疑患者）。我们能够选择和鉴定19种与疾病的病理生理学相关的分子，以及与患者健康相关结果的几个区别特征。应用于COVID-19诊断的方法显示特异性>96%，敏感性> 83%，风险评估期间特异性>80%，敏感性>85%，均来自盲法数据。我们的方法为COVID-19筛查引入了一种新方法，通过代谢物间接检测感染，并将结果与疾病的病理生理学联系起来。生物标志物的成对分析为使用机器学习算法开发的模型带来了鲁棒性，将这种筛选方法转化为具有巨大现实应用潜力的工具。
COVID-19 is still placing a heavy health and financial burden worldwide. Impairment in patient screening and risk management plays a fundamental role on how governments and authorities are directing resources, planning reopening, as well as sanitary countermeasures, especially in regions where poverty is a major component in the equation. An efficient diagnostic method must be highly accurate, while having a cost-effective profile. We combined a machine learning-based algorithm with mass spectrometry to create an expeditious platform that discriminate COVID-19 in plasma samples within minutes, while also providing tools for risk assessment, to assist healthcare professionals in patient management and decision-making. A cross-sectional study enrolled 815 patients (442 COVID-19, 350 controls and 23 COVID-19 suspicious) from three Brazilian epicenters from April to July 2020. We were able to elect and identify 19 molecules related to the disease’s pathophysiology and several discriminating features to patient’s health-related outcomes. The method applied for COVID-19 diagnosis showed specificity >96% and sensitivity >83%, and specificity >80% and sensitivity >85% during risk assessment, both from blinded data. Our method introduced a new approach for COVID-19 screening, providing the indirect detection of infection through metabolites and contextualizing the findings with the disease’s pathophysiology. The pairwise analysis of biomarkers brought robustness to the model developed using machine learning algorithms, transforming this screening approach in a tool with great potential for real-world application.
登录
查看更多内容
影响因子：
5
作者：
Kumar, KV;Rao, SM;Naidu, MUR
通讯作者：
Naidu, MUR
影响因子：
3.2
作者：
Carbonare, M. Dalle;Del Giudice, E.;Leon, A.
通讯作者：
Leon, A.
影响因子：
5.2
作者：
Doehla, M.;Boesecke, C.;Streeck, H.
通讯作者：
Streeck, H.
影响因子：
6.5
作者：
Ivanova, Pavlina T.;Milne, Stephen B.;Brown, H. Alex
通讯作者：
Brown, H. Alex
影响因子：
5.4
作者：
Davenne, Tamara;Bridgeman, Anne;Rehwinkel, Jan
通讯作者：
Rehwinkel, Jan