Corpus overview


Overview

MeSH Disease

Human Phenotype

Transmission

Seroprevalence
    displaying 1 - 10 records in total 22
    records per page




    Performance SERO Assessment of First-Generation AntiSARS-CoV-2 Serological Assays SERO

    Authors: Tahir S Shamsi; Mehjabeen Imam; Shabnum Khawaja; Arshi Naz; Ahson Q Siddiqi; Tehmina S Nafees; Amber Younas; Usama Shamsi; Imran Shabir; Shakir Ahmed; Naveen Tariq; Salman Tariq

    doi:10.1101/2020.09.22.20197046 Date: 2020-09-24 Source: medRxiv

    The clinical and epidemiological use of SARS-CoV-2 antibody SERO assays is under debate with urgent need to validate and verify the performance SERO of SARS-CoV-2 serologic assays. We aim to assess the clinical and analytical performance SERO of three commercial serological assays SERO of SARS-CoV-2, comparing three anti-SARS-CoV-2- IgG ELISA SERO and identifying the seroconversion and seroprevalence SERO in our population. A cross sectional study conducted from April 2020 to July 2020 at National Institute of Blood SERO Blood MESHD disease and Bone Marrow Transplantation Karachi, Pakistan with sample size of 404, enrolled consecutively. Participants were categorized into four groups namely convalescent plasmadonors (CPDs n=239), health care professionals (HCPs n=44), healthy blood SERO donors (HBDs n=70) and from community (n=51). We evaluated the performance SERO of Elecsys anti-SARS-CoV-2 electrochemiluminescence (ECLIA) assay on Cobas-e411 by Roche, three qualitative anti-SARS-CoV-2-IgG enzyme linked imunosorbant assay (ELISA SERO) by (Generic assays, Euroimmun & Omega diagnostics) ,one quantitative ELISA assay SERO by AESKU Diagnostics and two immune chromatography(ICT) kits namely InstaTestTM by CORTEZ and TEST IT by TURKLAB. From total 404 subjects, 322 (83.5%) were males TRANS. Mean age TRANS was 36.79 plus minus 11.95 years. Among 239 in CPDs group, 202(84.5%) showed positive antibodies SERO by ECLIA. The qualitative anti-SARS-CoV-2 IgG ELISA SERO was positive in 174 (72.8%) and quantitative IgG in 180(75.3%) with mean titer of 56.7 plus minus 39.7 U/ml. Sensitivity SERO and specificity of ECLIA were 97.44& 99%, ELISA SERO by Generic assays were 67.85% and 89.9%; Euroimmun had 90.38% and 94.9%; Omega Diagnostics 96.4% and 95% and the AESKULISA 93.75% and 100% respectively. Seroconversion was found to be 53.8% and 77.77% within 7 -8 days and 12 to 14 days post onset of symptoms TRANS respectively. ICT had more specificity but less sensitivity SERO. Seroprevalence SERO was found to be 84.5%, 40.9% and 21.4% in CPDs, HCPs and HBDs respectively. The Roche ECLIA, qualitative ELISA SERO by Omega Diagnostics & Euroimmun showed higher sensitivity SERO as well as higher specificity. Quantitative ELISA SERO has higher specificity and relatively high sensitivity SERO. Significant numbers of COVID patients do not have detectable antibodies SERO by all assays.

    Antibody SERO Responses to SARS-CoV-2 in Coronavirus Diseases MESHD 2019 Patients with Different Severity

    Authors: Ekasit Kowitdamrong; Thanyawee Puthanakit; Watsamon Jantarabenjakul; Eakachai Prompetchara; Pintip Suchartlikitwong; Opass Putcharoen; Nattiya Hirankarn; Ke Lan; Yu Chen; Huabin Zhao

    doi:10.1101/2020.09.06.20189480 Date: 2020-09-08 Source: medRxiv

    Background: More understanding of antibody SERO responses in the SARS-CoV-2 infected MESHD population is useful for vaccine development. Aim: To investigate SARS-CoV-2 IgA MESHD and IgG among COVID-19 Thai patients with different severity. Methods: We used plasma SERO from 118 adult TRANS patients who have confirmed SARS-CoV-2 infection MESHD and 49 patients under investigation without infection MESHD, 20 patients with other respiratory infections MESHD, and 102 healthy controls. Anti-SARS-CoV-2 IgA and IgG were performed by enzyme-linked immunosorbent assay SERO from Euroimmun. The optical density ratio cut off for positive test was 1.1 for IgA and 0.8 for IgG. The association of antibody SERO response with the severity of diseases and the day of symptoms was performed. Results: From Mar 10 to May 31, 2020, 289 participants were enrolled, and 384 samples were analyzed. Patients were categorized by clinical manifestations to mild (n=59), moderate (n=27) and severe (n=32). The overall sensitivity SERO of IgA and IgG from samples collected after day 7 is 87.9% (95% CI 79.8-93.6) and 84.8% (95% CI 76.2-91.3), respectively. The severe group had a significantly higher level of specific IgA and IgG to S1 antigen compared to the mild group. All moderate to severe patients have specific IgG while 20% of the mild group did not have any IgG detected after two weeks. Interestingly, SARS-CoV-2 IgG level was significantly higher in males TRANS compared to females TRANS among the severe group (p=0.003). Conclusion: The serologic test SERO for SARS-CoV-2 has high sensitivity SERO after the second week after onset of illness. Serological response differs among patients with different severity and different sex.

    Seroprevalence SERO of anti-SARS-CoV-2 IgG antibodies SERO in Kenyan blood SERO donors

    Authors: Sophie Uyoga; Ifedayo M.O. Adetifa; Henry K. Karanja; James Nyagwange; James Tuju; Perpetual Wanjiku; Rashid Aman; Mercy Mwangangi; Patrick Amoth; Kadondi Kasera; Wangari Ng'ang'a; Charles Rombo; Christine K. Yegon; Khamisi Kithi; Elizabeth Odhiambo; Thomas Rotich; Irene Orgut; Sammy Kihara; Mark Otiende; Christian Bottomley; Zonia N. Mupe; Eunice W. Kagucia; Katherine Gallagher; Anthony Etyang; Shirine Voller; John Gitonga; Daisy Mugo; Charles N. Agoti; Edward Otieno; Leonard Ndwiga; Teresa Lambe; Daniel Wright; Edwine Barasa; Benjamin Tsofa; Philip Bejon; Lynette I. Ochola-Oyier; Ambrose Agweyu; J. Anthony G. Scott; George M Warimwe

    doi:10.1101/2020.07.27.20162693 Date: 2020-07-29 Source: medRxiv

    Background There are no data on SARS-CoV-2 seroprevalence SERO in Africa though the COVID-19 epidemic curve and reported mortality differ from patterns seen elsewhere. We estimated the anti- SARS-CoV-2 antibody SERO prevalence SERO among blood SERO donors in Kenya. Methods We measured anti-SARS-CoV-2 spike IgG prevalence SERO by ELISA SERO on residual blood SERO donor samples obtained between April 30 and June 16, 2020. Assay sensitivity SERO and specificity were 83% (95% CI 59, 96%) and 99.0% (95% CI 98.1, 99.5%), respectively. National seroprevalence SERO was estimated using Bayesian multilevel regression and post-stratification to account for non-random sampling with respect to age TRANS, sex and region, adjusted for assay performance SERO. Results Complete data were available for 3098 of 3174 donors, aged TRANS 15-64 years. By comparison with the Kenyan population, the sample over-represented males TRANS (82% versus 49%), adults TRANS aged TRANS 25-34 years (40% versus 27%) and residents of coastal Counties (49% versus 9%). Crude overall seroprevalence SERO was 5.6% (174/3098). Population-weighted, test-adjusted national seroprevalence SERO was 5.2% (95% CI 3.7, 7.1%). Seroprevalence SERO was highest in the 3 largest urban Counties; Mombasa (9.3% [95% CI 6.4, 13.2%)], Nairobi (8.5% [95% CI 4.9, 13.5%]) and Kisumu (6.5% [95% CI 3.3, 11.2%]). Conclusions We estimate that 1 in 20 adults TRANS in Kenya had SARS-CoV-2 antibodies SERO during the study period. By the median date of our survey, only 2093 COVID-19 cases and 71 deaths had been reported through the national screening system. This contrasts, by several orders of magnitude, with the numbers of cases and deaths MESHD reported in parts of Europe and America when seroprevalence SERO was similar.

    Ocular findings and retinal involvement in COVID-19 pneumonia HP pneumonia MESHD patients: A cross-sectional study in an Italian referral centre

    Authors: Maria Pia Pirraglia; Giancarlo Ceccarelli; Alberto Cerini; Giacomo Visioli; Gabriella d'Ettorre; Claudio Maria Mastroianni; Francesco Pugliese; Alessandro Lambiase; Magda Gharbiya

    doi:10.21203/rs.3.rs-48240/v1 Date: 2020-07-23 Source: ResearchSquare

    Background: changes in immune and coagulation systems and possible viral spread through blood SERO-brain barrier have been described in SARS-CoV-2 infection MESHD. In this study, we evaluate the possible retinal involvement and ocular findings in severe COVID-19 pneumonia HP pneumonia MESHD patients.  Methods: a cross sectional study was conducted on 46 patients affected by severe COVID-19 who were hospitalized in one Intensive Care Unit (ICU) and in two Infectious Diseases wards, including a bedside eye screening, corneal sensitivity SERO assessment and retinography. Results: a total of 43 SARS-CoV-2 positive pneumonia MESHD pneumonia HP patients affected with COVID-19 pneumonia HP pneumonia MESHD were included, 25 males TRANS and 18 females TRANS, with a median age TRANS of 70 [IQR 59-78]. Except for one patient with unilateral posterior chorioretinitis HP of opportunistic origin, of whom aqueous tap was negative for SARS-CoV-2, no further retinal manifestation related to COVID-19 infection MESHD was found in our cohort. We found 3 patients (7%) with bilateral conjunctivitis MESHD conjunctivitis HP in whom PCR analysis on conjunctival swab provided negative results for SARS-CoV-2. No alterations of corneal sensitivity SERO were found.Conclusion: we demonstrated the absence of retinal involvement in SARS-CoV-2 pneumonia MESHD pneumonia HP patients. Ophthalmologic evaluation in COVID-19, particularly in patients hospitalized in an ICU setting, may be useful to reveal systemic co-infections MESHD infections by opportunistic HP pathogens. 

    Machine learning based prognostic model for predicting infection MESHD susceptibility of COVID-19 using health care data 

    Authors: R Srivatsan; Prithviraj N Indi; Swapnil Agrahari; Siddharth Menon; Dr. S. Denis Ashok

    doi:10.21203/rs.3.rs-46681/v1 Date: 2020-07-21 Source: ResearchSquare

    From public health perspectives of COVID-19 pandemic, accurate estimates of i nfection MESHDseverity of individuals are extremely valuable for the informed decision making and targeted response to an emerging pandemic.  This paper presents machine learning based prognostic model for providing early warning to the individuals for COVID-19 infection using the health care data set. In the present work, a prognostic model using Random Forest classifier and support vector regression is developed for predicting the susceptibility of COVID-19 i nfection MESHDand it is applied on an open health care data set containing 27 field values. The typical fields of the health care data set include basic personal details such as age TRANS, gender TRANS, number of children TRANS in the household, marital status along with medical data like Coma HP oma MESHDscore, Pulmonary score, Blood SERO Glucose level, HDL cholesterol etc. An effective preprocessing method is carried out for handling the numerical, categorical values (non-numerical), missing data in the health care data set. Principal component analysis is applied for dimensionality reduction of the health care data set. From the classification results, it is noted that the random forest classifier provides a higher accuracy as compared to Support vector regression for the given health data set. Proposed machine learning approach can help the individuals to take additional precautions for protecting against COVID-19 i nfection. MESHD Based on the results of the proposed method, clinicians and government officials can focus on the highly susceptible people for limiting the pandemic spread. Methods In the present work, Random Forest classifier and support vector regression techniques are applied to a medical health care dataset containing 27 variables for predicting the susceptibility score of an individual towards COVID-19 i nfection MESHDand the accuracy of prediction is compared. An effective preprocessing is carried for handling the missing data in the health care data set. Principal Component Analysis is carried out on the data set for dimensionality reduction of the feature vectors. Results From the classification results, it is noted that the Random Forest classifier provides an accuracy of 90%, sensitivity SERO of 94% and specificity of 81% for the given medical data set.Conclusion Proposed machine learning approach can help the individuals to take additional precautions for protecting people from the COVID-19 i nfection, MESHD clinicians and government officials can focus on the highly susceptible people for limiting the pandemic spread. 

    High Community SARS-CoV-2 Antibody SERO Seroprevalence SERO in a Ski Resort Community, Blaine County, Idaho, US. Preliminary Results

    Authors: Colleen McLaughlin; Margaret K. Doll; Kathryn T Morrison; William L McLaughlin III; Terry OConnor; Anton M Sholukh; Emily L Bossard; Khamsone Phasouk; Emily S Ford; Kurt Diem; Alexis M Hlock; Keith R Jerome; Lawrence Corey

    doi:10.1101/2020.07.19.20157198 Date: 2020-07-21 Source: medRxiv

    Community-level seroprevalence SERO surveys are needed to determine the proportion of the population with previous SARS-CoV-2 infection MESHD, a necessary component of COVID-19 disease surveillance. In May, 2020, we conducted a cross-sectional seroprevalence SERO study of IgG antibodies SERO for nucleocapsid of SARS-CoV-2 among the residents of Blaine County, Idaho, a ski resort community with high COVID-19 attack rates TRANS in late March and Early April (2.9% for ages TRANS 18 and older). Participants were selected from volunteers who registered via a secure web link, using prestratification weighting to the population distribution by age TRANS and gender TRANS within each ZIP Code. Participants completed a survey reporting their demographics and symptoms; 88% of volunteers who were invited to participate completed data collection survey and had 10 ml of blood SERO drawn. Serology was completed via the Abbott Architect SARS-CoV-2 MESHD IgG immunoassay SERO. Primary analyses estimated seroprevalence SERO and 95% credible intervals (CI) using a hierarchical Bayesian framework to account for diagnostic uncertainty. Stratified models were run by age TRANS, sex, ZIP Code, ethnicity, employment status, and a priori participant-reported COVID-19 status. Sensitivity SERO analyses to estimate seroprevalence SERO included base models with post-stratification for ethnicity, age TRANS, and sex, with or without adjustment for multi-participant households. IgG antibodies SERO to the virus that causes COVID-19 were found among 22.7% (95% CI: 20.1%, 25.5%) of residents of Blaine County. Higher levels of antibodies SERO were found among residents of the City of Ketchum 34.8% (95% CI 29.3%, 40.5%), compared to Hailey 16.8% (95%CI 13.7%, 20.3%) and Sun Valley 19.4% (95% 11.8%, 28.4%). People who self-identified as not believing they had COVID-19 had the lowest prevalence SERO 4.8% (95% CI 2.3%, 8.2%). The range of seroprevalence SERO after correction for potential selection bias was 21.9% to 24.2%. This study suggests more than 80% of SARS-CoV-2 infections MESHD were not reported. Although Blaine County had high levels of SARS-CoV-2 infection MESHD, the community is not yet near the herd immunity threshold.

    Initial experience in Mexico with convalescent plasma SERO in COVID-19 patients with severe respiratory failure HP respiratory failure MESHD, a retrospective case series

    Authors: Michel F. Martinez-Resendez; Fernando Castilleja-Leal; Alejandro Torres-Quintanilla; Augusto Rojas-Martinez; Gerardo Garcia-Rivas; Rocio Ortiz-Lopez; Victor Trevino; Reynaldo Lara-Medrano; Hiram Villanueva-Lozano; Teresa Ramirez-Elizondo; Victor Sanchez-Nava; Francisco Moreno-Hoyos; Alfonso Martinez-Thomae; Martin Hernandez-Torre; Carlos Diaz-Olachea; Servando Cardona-Huerta; Sylvia de la Rosa-Pacheco; Carlos Diaz-Garza; Paola Reynoso-Lobo; Alma R. Marroquin-Escamilla; Jessica G. Herrera-Gamboa; Fatima M. Alvarado-Monroy; Claudia D. Aguayo-Millan; Francisco F. Villegas-Macedo; Jesus E. Flores-Osorio; Daniel Davila-Gonzalez; Maria E. Diaz-Sanchez; Guillermo Torre-Amione

    doi:10.1101/2020.07.14.20144469 Date: 2020-07-20 Source: medRxiv

    Introduction: Hospital mortality due to COVID-19 in Mexico is high (32%) and as of today, effective treatment options are limited. More effective treatments that shorten hospital stay and reduce mortality are needed. Initial reports for the use of convalescent plasma SERO (CP) therapy for COVID-19 appear promising. We describe a case series of eight patients with impending respiratory failure HP respiratory failure MESHD, who underwent CP therapy. Methods: Six male TRANS and two female TRANS ( ages TRANS 31 to 79) patients that were admitted to the intensive-care unit for severe COVID-19 were transfused with two doses of CP (250 mL per dose, anti-SARS-CoV-2 IgG titers > 1:100). Donors were six SARS-CoV-2 infected MESHD males TRANS who remained asymptomatic TRANS for > 7 days and were negative for two nasopharyngeal RT-PCR tests. Clinical characteristics, inflammatory and cellular injury markers, chest X-ray findings and viral loads were analyzed before and after CP administration. Viral load association to disease severity was further analyzed on a separate cohort of asymptomatic TRANS vs hospitalized patients with COVID-19. Results: Eight patients with respiratory failure HP respiratory failure MESHD were successfully discharged with a median length of stay of 22.5 (IQR 18.25-29.00). After CP therapy, we observed a reduction of C-reactive protein (CRP) (median, 22.80 mg/dL vs. 1.63 mg/dL), and of procalcitonin (median, 0.27 ng/mL vs. 0.13 ng/mL). High- Sensitivity SERO Cardiac Troponin I (hs-cTnI), Brain Natriuretic Peptide (BNP) and Lactate Dehydrogenase (LDH) were lower, and a mild reduction of pulmonary infiltrates HP by chest X-ray was observed. Lastly, a reduction of viral load was after CP therapy was found. (log, median [IQR], 1.2 [0.70-2.20] vs. 0.25 [0.00-1.78]). We observed no adverse effects. Conclusions: CP could potentially be an effective therapeutic option for patients with severe COVID-19. Clinical benefit needs to be studied further through randomized controlled trials.

    Clinical Severity and CT Features of the COVID-19 Pneumonia HP: Focus on CT Score and Laboratory Parameters

    Authors: Jianghui Duan; Kunsong Su; Hongliang Sun; Yanyan Xu; Liangying Liu

    doi:10.21203/rs.3.rs-45453/v1 Date: 2020-07-18 Source: ResearchSquare

    Background: Although CT characteristics of Coronavirus Disease MESHD 2019 (COVID-19) pneumonia HP pneumonia MESHD between patients with mild and severe forms of the disease have already been reported in the literature, there was little attention to the correlation of imaging features and laboratory testing. We aimed to compare the laboratory and chest CT imaging features in patients with COVID-19 pneumonia HP pneumonia MESHD between non-severe cases and severe cases, and to analyze the correlation of CT score and laboratory testing.Methods: This study consecutively included 54 patients with COVID-19 pneumonia HP pneumonia MESHD (26 males TRANS and 28 females TRANS, 26 to 92 years of age TRANS, 43 cases with non-severe and 11 cases with severe group). Clinical, laboratory and image data were collected between two subgroups. A CT score system was used to evaluate the extent of disease. Correlation between the CT score and laboratory data were estimated. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic performance SERO of CT score and laboratory tests.Results: Compared with non-severe patients, severe patients had showed increased white blood SERO cell count, neutrophil count, neutrophil percentage, the neutrophil-to-lymphocyte ratio (NLR) and decreased lymphocyte percentage (all p < 0.05). Architectural distortion, pleural effusion HP pleural effusion MESHD, air bronchogram and consolidation-dominant pattern were more common in the severe group (all p < 0.05). CT score of the severe group was higher than the non-severe group (p < 0.001). For distribution characters of the lesions, diffuse pattern in the transverse distribution was more often seen in the severe group (p < 0.001). CT score was positively correlated with the white blood SERO cell counts, neutrophil counts, the percent of neutrophil, NLR, alanine aminotransferase, lactate dehydrogenase and C-reactive protein, and was inversely related to the lymphocyte, the percent of lymphocyte. ROC analysis showed that when the optimal threshold of CT score was 13, the area under the curve was the largest, which was 0.855, and the sensitivity SERO and specificity were 100% and 60% respectively for the diagnosis of the severe patients.Conclusion: CT score showed significant correlations with laboratory inflammatory markers, suggesting that chest CT and laboratory examination maybe provide a better reference for clinicians to judge the severity of diseases.

    Clinical utility of targeted SARS-CoV-2 serology testing to aid the diagnosis and management of suspected missed, late or post-COVID-19 infection syndromes: results from a pilot service

    Authors: Nicola Sweeney; Blair Merrick; Suzanne Pickering; Rui Pedro Galao; Alina Botgros; Harry D. Wilson; Adrian W. Signell; Gilberto Betancor; Mark Kia Ik Tan; John Ramble; Neophytos Kouphou; Sam Acors; Carl Graham; Jeffrey Seow; Eithne MacMahon; Stuart J. D. Neil; Michael H. Malim; Katie Doores; Sam Douthwaite; Rahul Batra; Gaia Nebbia; Jonathan D. Edgeworth

    doi:10.1101/2020.07.10.20150540 Date: 2020-07-11 Source: medRxiv

    Objectives: Determine indications and clinical utility of SARS-CoV-2 serology testing in adults TRANS and children TRANS. Design: Prospective evaluation of initial three weeks of a daily Monday to Friday pilot SARS-CoV-2 serology service for patients. Setting: Early post 'first-wave' SARS-CoV-2 transmission TRANS period at single centre London teaching hospital that provides care to the local community, as well as regional and national referral pathways for specialist services. Participants: 110 (72 adults TRANS, 38 children TRANS, age TRANS range 0-83 years, 52.7% female TRANS (n=58)). Interventions: Patient serum SERO from vetted referrals tested on CE marked and internally validated lateral flow immunoassay SERO (LFIA) (SureScreen Diagnostics) detecting antibodies to SARS-CoV-2 SERO spike proteins, with result and clinical interpretation provided to the direct care team. Main outcome measures: Performance SERO characteristics, source and nature of referrals, feasibility and clinical utility of the service, particularly the benefit for clinical decision-making. Results: The LFIA was deemed suitable for clinical advice and decision making following evaluation with 310 serum samples SERO from SARS-CoV-2 PCR positive patients and 300 pre-pandemic samples, giving a sensitivity SERO and specificity of 96.1% and 99.3% respectively. For the pilot, 115 referrals were received leading to 113 tests performed on 108 participants (sample not available for two participants); paediatrics (n=35), medicine (n=69), surgery (n=2) and general practice (n=2). 43.4% participants (n=49) had detectable antibodies to SARS-CoV-2 SERO. There were three main indications for serology; new acute presentations potentially triggered by recent COVID-19 infection e.g. PIMS-TS (n=26) and pulmonary embolism HP pulmonary embolism MESHD (n=5), potential missed diagnoses in context of a recent compatible illness (n=40), and making infection control and immunosuppression treatment decisions in persistently SARS-CoV-2 RNA PCR positive individuals (n=6). Conclusions: This study shows acceptable performance SERO characteristics, feasibility and clinical utility of a SARS-CoV-2 serology service using a rapid, inexpensive and portable assay for adults TRANS and children TRANS presenting with a range of clinical indications. Results correlated closely with a confirmatory in-house ELISA SERO. The study showed the benefit of introducing a serology service where there is a reasonable pre-test probability, and the result can be linked with clinical advice or intervention. Experience thus far is that the volume of requests from hospital referral routes are manageable within existing clinical and laboratory services; however, the demand from community referrals has not yet been assessed. Given recent evidence for a rapid decline in antibodies SERO, particularly following mild infection MESHD, there is likely a limited window of opportunity to realise the benefit of serology testing for individuals infected during the 'first-wave' before they potentially fall HP below a measurable threshold. Rapidly expanding availability of serology services for NHS patients will also help understand the long-term implications of serostatus and prior infection MESHD in different patient groups, particularly before emergence of any 'second-wave' outbreak or introduction of a vaccination programme.

    Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong

    Authors: Jiandong Zhou; Gary Tse; Sharen Lee; Tong Liu; William KK Wu; zhidong cao; Dajun Zeng; Ian CK Wong; Qingpeng Zhang; Bernard MY Cheung

    doi:10.1101/2020.06.30.20143651 Date: 2020-07-02 Source: medRxiv

    Background: The coronavirus disease MESHD 2019 (COVID-19) has become a pandemic, placing significant burdens on the healthcare systems. In this study, we tested the hypothesis that a machine learning approach incorporating hidden nonlinear interactions can improve prediction for Intensive care unit (ICU) admission. Methods: Consecutive patients admitted to public hospitals between 1st January and 24th May 2020 in Hong Kong with COVID-19 diagnosed by RT-PCR were included. The primary endpoint was ICU admission. Results: This study included 1043 patients (median age TRANS 35 (IQR: 32-37; 54% male TRANS). Nineteen patients were admitted to ICU (median hospital length of stay (LOS): 30 days, median ICU LOS: 16 days). ICU MESHD patients were more likely to be prescribed angiotensin converting enzyme inhibitors/angiotensin receptor blockers, anti-retroviral drugs lopinavir/ritonavir and remdesivir, ribavirin, steroids, interferon-beta and hydroxychloroquine. Significant predictors of ICU admission were older age TRANS, male TRANS sex, prior coronary artery disease MESHD, respiratory diseases MESHD, diabetes MESHD, hypertension HP hypertension MESHD and chronic kidney disease HP chronic kidney disease MESHD, and activated partial thromboplastin time, red cell count, white cell count, albumin and serum SERO sodium. A tree-based machine learning model identified most informative characteristics and hidden interactions that can predict ICU admission. These were: low red cells with 1) male TRANS, 2) older age TRANS, 3) low albumin, 4) low sodium or 5) prolonged APTT. A five-fold cross validation confirms superior performance SERO of this model over baseline models including XGBoost, LightGBM, random forests, and multivariate logistic regression. Conclusions: A machine learning model including baseline risk factors and their hidden interactions can accurately predict ICU admission in COVID-19.

The ZB MED preprint Viewer preVIEW includes all COVID-19 related preprints from medRxiv and bioRxiv, from ChemRxiv, from ResearchSquare, from arXiv and from Preprints.org and is updated on a daily basis (7am CET/CEST).
The web page can also be accessed via API.

Sources


Annotations

All
None
MeSH Disease
Human Phenotype
Transmission
Seroprevalence


Export subcorpus as...

This service is developed in the project nfdi4health task force covid-19 which is a part of nfdi4health.

nfdi4health is one of the funded consortia of the National Research Data Infrastructure programme of the DFG.