An AI-powered patient triage platform for future viral outbreaks using COVID-19 as a disease model.
An AI-powered patient triage platform for future viral outbreaks using COVID-19 as a disease model.
复制标题
DOI：
10.1186/s40246-023-00521-4
复制
发表时间：
2023-08-29
期刊：
影响因子：
4.5
通讯作者：
中科院分区：
文献类型：
--
作者：
在上个世纪，疾病爆发和大流行病的发生具有令人不安的规律性，因此必须提前做好准备，采取大规模协调一致的应对措施。在这里，我们开发了一个机器学习预测模型，用于预测COVID-19的疾病严重程度和住院时间，该模型可用作未来未知病毒爆发的平台。我们结合了从住院期间的COVID-19患者（n = 111）和健康对照（n = 342）获得的血浆数据的非靶向代谢组学，临床和合并症数据（n = 508），以构建此患者分诊平台，该平台由三个部分组成：（i）临床决策树，在其他生物标志物中，其显示嗜酸性粒细胞增加的患者具有更差的疾病预后，并且可以作为具有高准确性的新的潜在生物标志物（AUC = 0.974），（ii）估计患者住院时间，误差± 5天（R2 = 0.9765）和（iii）预测疾病严重程度和患者转移到重症监护室的需要。我们报告了一个显着降低血清素水平的患者谁需要气道正压氧气和/或插管。此外，5-羟基色氨酸、尿囊素和葡萄糖醛酸代谢产物在COVID-19患者中增加，它们共同可作为预测疾病进展的生物标志物。如果能够迅速确定哪些患者将出现危及生命的疾病，就可以有效地分配医疗资源，实施最有效的医疗干预措施。我们主张在未来的病毒爆发中可以使用相同的方法，以帮助医院更有效地分流患者，改善患者的治疗效果，同时优化医疗资源。在线版本包含补充材料，可通过10.1186/s40246-023-00521-4获得。
Over the last century, outbreaks and pandemics have occurred with disturbing regularity, necessitating advance preparation and large-scale, coordinated response. Here, we developed a machine learning predictive model of disease severity and length of hospitalization for COVID-19, which can be utilized as a platform for future unknown viral outbreaks. We combined untargeted metabolomics on plasma data obtained from COVID-19 patients (n = 111) during hospitalization and healthy controls (n = 342), clinical and comorbidity data (n = 508) to build this patient triage platform, which consists of three parts: (i) the clinical decision tree, which amongst other biomarkers showed that patients with increased eosinophils have worse disease prognosis and can serve as a new potential biomarker with high accuracy (AUC = 0.974), (ii) the estimation of patient hospitalization length with ± 5 days error (R2 = 0.9765) and (iii) the prediction of the disease severity and the need of patient transfer to the intensive care unit. We report a significant decrease in serotonin levels in patients who needed positive airway pressure oxygen and/or were intubated. Furthermore, 5-hydroxy tryptophan, allantoin, and glucuronic acid metabolites were increased in COVID-19 patients and collectively they can serve as biomarkers to predict disease progression. The ability to quickly identify which patients will develop life-threatening illness would allow the efficient allocation of medical resources and implementation of the most effective medical interventions. We would advocate that the same approach could be utilized in future viral outbreaks to help hospitals triage patients more effectively and improve patient outcomes while optimizing healthcare resources. The online version contains supplementary material available at 10.1186/s40246-023-00521-4.
登录
查看更多内容
影响因子：
5.2
作者：
Dickerhof, Nina;Turner, Rufus;Kettle, Anthony J.
通讯作者：
Kettle, Anthony J.
DOI：
10.1016/s1473-3099(21)00019-0
发表时间：
2021-06
期刊：
The Lancet. Infectious diseases
影响因子：
--
作者：
Gutiérrez-Gutiérrez B;Del Toro MD;Borobia AM;Carcas A;Jarrín I;Yllescas M;Ryan P;Pachón J;Carratalà J;Berenguer J;Arribas JR;Rodríguez-Baño J;REIPI-SEIMC COVID-19 group and COVID@HULP groups
通讯作者：
REIPI-SEIMC COVID-19 group and COVID@HULP groups
影响因子：
2.9
作者：
Kozlik, Petr;Hasikova, Lenka;Kalikova, Kveta
通讯作者：
Kalikova, Kveta
影响因子：
2.1
作者：
Fujiwara R;Yoda E;Tukey RH
通讯作者：
Tukey RH
影响因子：
8.1
作者：
Bruno RR;Wernly B;Flaatten H;Fjølner J;Artigas A;Bollen Pinto B;Schefold JC;Binnebössel S;Baldia PH;Kelm M;Beil M;Sigal S;van Heerden PV;Szczeklik W;Elhadi M;Joannidis M;Oeyen S;Zafeiridis T;Wollborn J;Arche Banzo MJ;Fuest K;Marsh B;Andersen FH;Moreno R;Leaver S;Boumendil A;De Lange DW;Guidet B;Jung C;COVIP Study Group
通讯作者：
COVIP Study Group