A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers. / Chen, Xin; Gao, Wei; Li, Jie; You, Dongfang; Yu, Zhaolei; Zhang, Mingzhi; Shao, Fang; Wei, Yongyue; Zhang, Ruyang; Lange, Theis; Wang, Qianghu; Chen, Feng; Lu, Xiang; Zhao, Yang.

I: Briefings in Bioinformatics, Bind 22, Nr. 6, 2021.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Chen, X, Gao, W, Li, J, You, D, Yu, Z, Zhang, M, Shao, F, Wei, Y, Zhang, R, Lange, T, Wang, Q, Chen, F, Lu, X & Zhao, Y 2021, 'A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers', Briefings in Bioinformatics, bind 22, nr. 6. https://doi.org/10.1093/bib/bbab206

APA

Chen, X., Gao, W., Li, J., You, D., Yu, Z., Zhang, M., Shao, F., Wei, Y., Zhang, R., Lange, T., Wang, Q., Chen, F., Lu, X., & Zhao, Y. (2021). A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers. Briefings in Bioinformatics, 22(6). https://doi.org/10.1093/bib/bbab206

Vancouver

Chen X, Gao W, Li J, You D, Yu Z, Zhang M o.a. A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers. Briefings in Bioinformatics. 2021;22(6). https://doi.org/10.1093/bib/bbab206

Author

Chen, Xin ; Gao, Wei ; Li, Jie ; You, Dongfang ; Yu, Zhaolei ; Zhang, Mingzhi ; Shao, Fang ; Wei, Yongyue ; Zhang, Ruyang ; Lange, Theis ; Wang, Qianghu ; Chen, Feng ; Lu, Xiang ; Zhao, Yang. / A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers. I: Briefings in Bioinformatics. 2021 ; Bind 22, Nr. 6.

Bibtex

@article{fefe9672f7ca4aba8f5c82316db235b5,

title = "A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers",

abstract = "Novel coronavirus disease 2019 (COVID-19) is an emerging, rapidly evolving crisis, and the ability to predict prognosis for individual COVID-19 patient is important for guiding treatment. Laboratory examinations were repeatedly measured during hospitalization for COVID-19 patients, which provide the possibility for the individualized early prediction of prognosis. However, previous studies mainly focused on risk prediction based on laboratory measurements at one time point, ignoring disease progression and changes of biomarkers over time. By using historical regression trees (HTREEs), a novel machine learning method, and joint modeling technique, we modeled the longitudinal trajectories of laboratory biomarkers and made dynamically predictions on individual prognosis for 1997 COVID-19 patients. In the discovery phase, based on 358 COVID-19 patients admitted between 10 January and 18 February 2020 from Tongji Hospital, HTREE model identified a set of important variables including 14 prognostic biomarkers. With the trajectories of those biomarkers through 5-day, 10-day and 15-day, the joint model had a good performance in discriminating the survived and deceased COVID-19 patients (mean AUCs of 88.81, 84.81 and 85.62% for the discovery set). The predictive model was successfully validated in two independent datasets (mean AUCs of 87.61, 87.55 and 87.03% for validation the first dataset including 112 patients, 94.97, 95.78 and 94.63% for the second validation dataset including 1527 patients, respectively). In conclusion, our study identified important biomarkers associated with the prognosis of COVID-19 patients, characterized the time-to-event process and obtained dynamic predictions at the individual level.",

keywords = "COVID-19, dynamic risk prediction, longitudinal data, time-to-event",

author = "Xin Chen and Wei Gao and Jie Li and Dongfang You and Zhaolei Yu and Mingzhi Zhang and Fang Shao and Yongyue Wei and Ruyang Zhang and Theis Lange and Qianghu Wang and Feng Chen and Xiang Lu and Yang Zhao",

year = "2021",

doi = "10.1093/bib/bbab206",

language = "English",

volume = "22",

journal = "Briefings in Bioinformatics",

issn = "1467-5463",

publisher = "Oxford University Press",

number = "6",

}

RIS

TY - JOUR

T1 - A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers

AU - Chen, Xin

AU - Gao, Wei

AU - Li, Jie

AU - You, Dongfang

AU - Yu, Zhaolei

AU - Zhang, Mingzhi

AU - Shao, Fang

AU - Wei, Yongyue

AU - Zhang, Ruyang

AU - Lange, Theis

AU - Wang, Qianghu

AU - Chen, Feng

AU - Lu, Xiang

AU - Zhao, Yang

PY - 2021

Y1 - 2021

N2 - Novel coronavirus disease 2019 (COVID-19) is an emerging, rapidly evolving crisis, and the ability to predict prognosis for individual COVID-19 patient is important for guiding treatment. Laboratory examinations were repeatedly measured during hospitalization for COVID-19 patients, which provide the possibility for the individualized early prediction of prognosis. However, previous studies mainly focused on risk prediction based on laboratory measurements at one time point, ignoring disease progression and changes of biomarkers over time. By using historical regression trees (HTREEs), a novel machine learning method, and joint modeling technique, we modeled the longitudinal trajectories of laboratory biomarkers and made dynamically predictions on individual prognosis for 1997 COVID-19 patients. In the discovery phase, based on 358 COVID-19 patients admitted between 10 January and 18 February 2020 from Tongji Hospital, HTREE model identified a set of important variables including 14 prognostic biomarkers. With the trajectories of those biomarkers through 5-day, 10-day and 15-day, the joint model had a good performance in discriminating the survived and deceased COVID-19 patients (mean AUCs of 88.81, 84.81 and 85.62% for the discovery set). The predictive model was successfully validated in two independent datasets (mean AUCs of 87.61, 87.55 and 87.03% for validation the first dataset including 112 patients, 94.97, 95.78 and 94.63% for the second validation dataset including 1527 patients, respectively). In conclusion, our study identified important biomarkers associated with the prognosis of COVID-19 patients, characterized the time-to-event process and obtained dynamic predictions at the individual level.

AB - Novel coronavirus disease 2019 (COVID-19) is an emerging, rapidly evolving crisis, and the ability to predict prognosis for individual COVID-19 patient is important for guiding treatment. Laboratory examinations were repeatedly measured during hospitalization for COVID-19 patients, which provide the possibility for the individualized early prediction of prognosis. However, previous studies mainly focused on risk prediction based on laboratory measurements at one time point, ignoring disease progression and changes of biomarkers over time. By using historical regression trees (HTREEs), a novel machine learning method, and joint modeling technique, we modeled the longitudinal trajectories of laboratory biomarkers and made dynamically predictions on individual prognosis for 1997 COVID-19 patients. In the discovery phase, based on 358 COVID-19 patients admitted between 10 January and 18 February 2020 from Tongji Hospital, HTREE model identified a set of important variables including 14 prognostic biomarkers. With the trajectories of those biomarkers through 5-day, 10-day and 15-day, the joint model had a good performance in discriminating the survived and deceased COVID-19 patients (mean AUCs of 88.81, 84.81 and 85.62% for the discovery set). The predictive model was successfully validated in two independent datasets (mean AUCs of 87.61, 87.55 and 87.03% for validation the first dataset including 112 patients, 94.97, 95.78 and 94.63% for the second validation dataset including 1527 patients, respectively). In conclusion, our study identified important biomarkers associated with the prognosis of COVID-19 patients, characterized the time-to-event process and obtained dynamic predictions at the individual level.

KW - COVID-19

KW - dynamic risk prediction

KW - longitudinal data

KW - time-to-event

U2 - 10.1093/bib/bbab206

DO - 10.1093/bib/bbab206

M3 - Journal article

C2 - 34081102

AN - SCOPUS:85117793319

VL - 22

JO - Briefings in Bioinformatics

JF - Briefings in Bioinformatics

SN - 1467-5463

IS - 6

ER -

ID: 288667375