Dataset Information

Severity Detection for the Coronavirus Disease 2019 (COVID-19) Patients Using a Machine Learning Model Based on the Blood and Urine Tests.

ABSTRACT: The recent outbreak of the coronavirus disease-2019 (COVID-19) caused serious challenges to the human society in China and across the world. COVID-19 induced pneumonia in human hosts and carried a highly inter-person contagiousness. The COVID-19 patients may carry severe symptoms, and some of them may even die of major organ failures. This study utilized the machine learning algorithms to build the COVID-19 severeness detection model. Support vector machine (SVM) demonstrated a promising detection accuracy after 32 features were detected to be significantly associated with the COVID-19 severeness. These 32 features were further screened for inter-feature redundancies. The final SVM model was trained using 28 features and achieved the overall accuracy 0.8148. This work may facilitate the risk estimation of whether the COVID-19 patients would develop the severe symptoms. The 28 COVID-19 severeness associated biomarkers may also be investigated for their underlining mechanisms how they were involved in the COVID-19 infections.

SUBMITTER: Yao H

PROVIDER: S-EPMC7411005 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Severity Detection for the Coronavirus Disease 2019 (COVID-19) Patients Using a Machine Learning Model Based on the Blood and Urine Tests.

Yao Haochen H Zhang Nan N Zhang Ruochi R Duan Meiyu M Xie Tianqi T Pan Jiahui J Peng Ejun E Huang Juanjuan J Zhang Yingli Y Xu Xiaoming X Xu Hong H Zhou Fengfeng F Wang Guoqing G

Frontiers in cell and developmental biology 20200731

The recent outbreak of the coronavirus disease-2019 (COVID-19) caused serious challenges to the human society in China and across the world. COVID-19 induced pneumonia in human hosts and carried a highly inter-person contagiousness. The COVID-19 patients may carry severe symptoms, and some of them may even die of major organ failures. This study utilized the machine learning algorithms to build the COVID-19 severeness detection model. Support vector machine (SVM) demonstrated a promising detecti ...[more]

PMID: 32850809

Similar Datasets

Project description:SubjectsEarly detection of coronavirus disease 2019 in patients likely to develop severe manifestations enables appropriate interventions, including rapid ICU admission. This study was conducted to determine whether noninvasive urine biomarkers can predict the clinical severity of coronavirus disease 2019.InterventionsNot applicable.Measurements and main resultsThis is single-center study, national center hospital designated for infectious disease. Fifty-eight patients who tested positive for severe acute respiratory syndrome coronavirus 2 in respiratory specimens through real-time reverse transcription-polymerase chain reaction were retrospectively studied. Urinary β2-microglobulin, liver-type fatty acid-binding protein were serially measured. Serum interferon-γ and monocyte chemotactic protein-1 were also evaluated. The 58 patients were assigned into three groups. Patients requiring intensive care were assigned to the severe group (n = 12). Patients treated with oxygen were assigned to the moderate group (n = 13). Other patients were assigned to the mild group (n = 33). Urine tests revealed that low β2-microglobulin and liver-type fatty acid-binding protein levels were associated with mild disease, whereas high levels were associated with severe disease. In severe cases, liver-type fatty acid-binding protein tended to be persistently high. The resulting cutoff values were β2-microglobulin; severe versus moderate + mild: 2,457 μg/dL (specificity 76.9% and sensitivity 90.0%, area under the receiver operating characteristic curve 85.9%), liver-type fatty acid-binding protein; severe versus moderate + mild: 22.0 μg/gCre (specificity 84.6% and sensitivity 90%, area under the receiver operating characteristic curve 91.8%). Urinary β2-microglobulin and serum interferon-γ/monocyte chemotactic protein-1 showed a similar trend.ConclusionsEvaluating urinary biomarkers such as β2-microglobulin and liver-type fatty acid-binding protein may allow determination of coronavirus disease 2019 patients with active cytokines and recognition of patients likely to become critically ill and requiring careful observation and early intervention.

Dataset Information

Severity Detection for the Coronavirus Disease 2019 (COVID-19) Patients Using a Machine Learning Model Based on the Blood and Urine Tests.

Publications

Severity Detection for the Coronavirus Disease 2019 (COVID-19) Patients Using a Machine Learning Model Based on the Blood and Urine Tests.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets