Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal

BMJ, The - Trang m1328
Laure Wynants1,2, Ben Van Calster3,1, Gary S. Collins4,5, Richard D Riley6, Georg Heinze7, Ewoud Schuit8,9, Elena Albu1, Banafsheh Arshi2, Vanesa Bellou10, Marc J. M. Bonten11,9, Darren Dahly12,13, Johanna AAG Damen8,9, Thomas P. A. Debray9,14, Valentijn M. T. de Jong8,9, Maarten De Vos1,15, Paula Dhiman4,5, Joie Ensor6, Shan Gao1, Maria Haller16,7, Michael O. Harhay17,18, Liesbet Henckaerts19,20, Pauline Heus8,9, Jeroen Hoogland9, Mohammed T Hudda21, Kevin Jenniskens8,9, Michael Kammer22,7, Nina Kreuzberger23, Anna Lohmann24, Kim Luijken24, Jie Ma5, Glen P. Martin25, David J. McLernon26, Constanza L. Andaur Navarro8,9, Johannes B. Reitsma8,9, Jamie C. Sergeant27,28, Chunhu Shi29, Nicole Skoetz22, Luc Smits2, Kym I E Snell6, Matthew Sperrin30, René Spijker31,8,9, Ewout W. Steyerberg3, Toshihiko Takada32,9, Ioanna Tzoulaki33,10, Sander M. J. van Kuijk34, Bas C. T. van Bussel2,35, Iwan C. C. van der Horst35, Kelly Reeve36, Florien S. van Royen9, Jan Y Verbakel37,38, Christine Wallisch39,40,7, Jack Wilkinson24, Robert Wolff41, Lotty Hooft8,9, Karel G.M. Moons8,9, Maarten van Smeden9
1Department of Development and Regeneration, KU Leuven, Leuven, Belgium
2Department of Epidemiology, CAPHRI Care and Public Health Research Institute, Maastricht University, Maastricht, Netherlands
3Department of Biomedical Data Sciences, Leiden University Medical Centre, Leiden, Netherlands
4Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Musculoskeletal Sciences, University of Oxford, Oxford, UK
5NIHR Oxford Biomedical Research Centre, John Radcliffe Hospital, Oxford, UK
6Centre for Prognosis Research, School of Medicine, Keele University, Keele, UK
7Section for Clinical Biometrics, Centre for Medical Statistics, Informatics, and Intelligent Systems, Medical University of Vienna, Vienna, Austria
8Cochrane Netherlands, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
9Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
10Department of Hygiene and Epidemiology, University of Ioannina Medical School, Ioannina, Greece
11Department of Medical Microbiology, University Medical Centre Utrecht, Utrecht, Netherlands
12HRB Clinical Research Facility, Cork, Ireland
13School of Public Health, University College Cork, Cork, Ireland
14Smart Data Analysis and Statistics BV, Utrecht, Netherlands
15Department of Electrical Engineering (ESAT/STADIUS), KU Leuven, Leuven, Belgium
16Ordensklinikum Linz, Hospital Elisabethinen, Department of Nephrology, Linz, Austria
17Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
18Palliative and Advanced Illness Research Center and Division of Pulmonary and Critical Care Medicine, Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
19Department of General Internal Medicine, KU Leuven-University Hospitals Leuven, Leuven, Belgium
20Department of Microbiology, Immunology and Transplantation, KU Leuven-University of Leuven, Leuven, Belgium
21Population Health Research Institute, St George’s University of London, Cranmer Terrace, London, UK
22Department of Nephrology, Medical University of Vienna, Vienna, Austria
23Evidence-Based Oncology, Department I of Internal Medicine and Centre for Integrated Oncology Aachen Bonn Cologne Dusseldorf, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany
24Department of Clinical Epidemiology, Leiden University Medical Centre, Leiden, Netherlands
25Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, Manchester Academic Health Science Centre, University of Manchester, Manchester, UK
26Institute of Applied Health Sciences, University of Aberdeen, Aberdeen, UK
27Centre for Biostatistics, University of Manchester, Manchester Academic Health Science Centre, Manchester, UK
28Centre for Epidemiology Versus Arthritis, Centre for Musculoskeletal Research, University of Manchester, Manchester Academic Health Science Centre, Manchester, UK
29Division of Nursing, Midwifery and Social work, School of Health Sciences, University of Manchester, Manchester, UK
30Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
31Amsterdam UMC, University of Amsterdam, Amsterdam Public Health, Medical Library, Netherlands
32Department of General Medicine, Shirakawa Satellite for Teaching And Research, Fukushima Medical University, Fukushima, Japan
33Department of Epidemiology and Biostatistics, Imperial College London School of Public Health, London, UK
34Department of Clinical Epidemiology and Medical Technology Assessment, Maastricht University Medical Centre, Maastricht, Netherlands
35Department of Intensive Care Medicine, Maastricht University Medical Centre+, Maastricht University, Maastricht, Netherlands
36Epidemiology, Biostatistics and Prevention Institute, University of Zurich, Zurich, CH
37EPI-Centre, Department of Public Health and Primary Care, KU Leuven, Leuven, Belgium
38NIHR Community Healthcare Medtech and IVD Cooperative, Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, UK
39Berlin Institute of Health, Berlin, Germany
40Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
41Kleijnen Systematic Reviews, York, UK

Tóm tắt

Abstract Objective To review and appraise the validity and usefulness of published and preprint reports of prediction models for prognosis of patients with covid-19, and for detecting people in the general population at increased risk of covid-19 infection or being admitted to hospital or dying with the disease. Design Living systematic review and critical appraisal by the covid-PRECISE (Precise Risk Estimation to optimise covid-19 Care for Infected or Suspected patients in diverse sEttings) group. Data sources PubMed and Embase through Ovid, up to 17 February 2021, supplemented with arXiv, medRxiv, and bioRxiv up to 5 May 2020. Study selection Studies that developed or validated a multivariable covid-19 related prediction model. Data extraction At least two authors independently extracted data using the CHARMS (critical appraisal and data extraction for systematic reviews of prediction modelling studies) checklist; risk of bias was assessed using PROBAST (prediction model risk of bias assessment tool). Results 126 978 titles were screened, and 412 studies describing 731 new prediction models or validations were included. Of these 731, 125 were diagnostic models (including 75 based on medical imaging) and the remaining 606 were prognostic models for either identifying those at risk of covid-19 in the general population (13 models) or predicting diverse outcomes in those individuals with confirmed covid-19 (593 models). Owing to the widespread availability of diagnostic testing capacity after the summer of 2020, this living review has now focused on the prognostic models. Of these, 29 had low risk of bias, 32 had unclear risk of bias, and 545 had high risk of bias. The most common causes for high risk of bias were inadequate sample sizes (n=408, 67%) and inappropriate or incomplete evaluation of model performance (n=338, 56%). 381 models were newly developed, and 225 were external validations of existing models. The reported C indexes varied between 0.77 and 0.93 in development studies with low risk of bias, and between 0.56 and 0.78 in external validations with low risk of bias. The Qcovid models, the PRIEST score, Carr’s model, the ISARIC4C Deterioration model, and the Xie model showed adequate predictive performance in studies at low risk of bias. Details on all reviewed models are publicly available at https://www.covprecise.org/ . Conclusion Prediction models for covid-19 entered the academic literature to support medical decision making at unprecedented speed and in large numbers. Most published prediction model studies were poorly reported and at high risk of bias such that their reported predictive performances are probably optimistic. Models with low risk of bias should be validated before clinical implementation, preferably through collaborative efforts to also allow an investigation of the heterogeneity in their performance across various populations and settings. Methodological guidance, as provided in this paper, should be followed because unreliable predictions could cause more harm than benefit in guiding clinical decisions. Finally, prediction modellers should adhere to the TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) reporting guideline. Systematic review registration Protocol https://osf.io/ehc47/ , registration https://osf.io/wy245 . Readers’ note This article is the final version of a living systematic review that has been updated over the past two years to reflect emerging evidence. This version is update 4 of the original article published on 7 April 2020 ( BMJ 2020;369:m1328). Previous updates can be found as data supplements ( https://www.bmj.com/content/369/bmj.m1328/related#datasupp ). When citing this paper please consider adding the update number and date of access for clarity.

Từ khóa


Tài liệu tham khảo

10.1016/S1473-3099(20)30120-1

10.1007/s00134-020-05955-1

10.1001/jama.2020.4031

10.1007/s00134-020-05979-7

World Health Organization. Essential health services face continued disruption during COVID-19 pandemic 2022. https://www.who.int/news/item/07-02-2022-essential-health-services-face-continued-disruption-during-covid-19-pandemic.

Ritchie H, Mathieu E, Rodés-Guirao L, et al. Coronavirus Pandemic (COVID-19) 2020. https://ourworldindata.org/coronavirus accessed 07/03/2022.

10.1101/2020.03.28.20045997

10.1038/d41586-022-00155-x

10.1101/2020.03.20.20037325

Institute of Social and Preventive Medicine. Living evidence on covid-19 2020. https://ispmbern.github.io/covid-19/living-review/index.html.

Thomas J, Brunton J, Graziosi S. EPPI-Reviewer 4.0: software for research synthesis [program]. EPPI-Centre Software. London: Social Science Research Unit, Institute of Education, University of London, 2010.

10.1101/2020.03.18.20035816

10.1371/journal.pmed.1001744

10.7326/M18-1377

10.7326/M14-0698

10.1007/978-3-030-16399-0

10.1371/journal.pmed.1000100

10.1101/2020.02.24.20027268

10.1101/2020.02.20.20025510

10.1101/2020.02.29.20029603

10.1101/2020.02.27.20028027

10.1371/journal.pone.0230548

10.1101/2020.02.23.20026930

10.1101/2020.03.09.20032219

10.1371/journal.pone.0230548

10.1101/2020.02.25.20021568

10.1101/2020.02.29.20029603

10.1101/2020.02.27.20028027

10.1101/2020.02.14.20023028

10.1101/2020.03.05.20031906

10.1101/2020.03.09.20032219

Gozes O, Frid-Adar M, Greenspan H, et al. Rapid AI development cycle for the coronavirus (covid-19) pandemic: initial results for automated detection & patient monitoring using deep learning CT image analysis. arXiv e-prints [Preprint] 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200305037G

10.1101/2020.03.19.20039354

Xu X, Jiang X, Ma C, et al. Deep learning system to screen coronavirus disease 2019 pneumonia. arXiv e-prints [Preprint] 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200209334X

Shan F, Gao Y, Wang J, et al. Lung infection quantification of covid-19 in CT images with deep learning. arXiv e-prints 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200304655S

10.1148/radiol.2020200905

10.1186/s13054-020-2833-7

Barstugan M, Ozkaya U, Ozturk S. Coronavirus (covid-19) classification using CT images by machine learning methods. arXiv e-prints [Preprint] 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200309424B

10.1186/s13054-020-2833-7

10.1093/cid/ciaa322

10.1101/2020.03.13.990242

Shi F, Xia L, Shan F, et al. Large-scale screening of covid-19 from community acquired pneumonia using infection size-aware classification. arXiv [Preprint] 2020. https://arxiv.org/abs/2003.09860

10.1186/s13054-020-2833-7

10.1136/bmj.m441

Chowdhury MEH, Rahman T, Khandakar A, et al. Can AI help in screening Viral and covid-19 pneumonia? arXiv e-prints [Preprint] 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200313145C.

10.1007/978-0-387-77244-8

10.1161/CIRCULATIONAHA.115.017719

10.1136/bmj.i3140

10.1371/journal.pmed.1001886

10.1016/j.jclinepi.2015.04.005

10.1186/s41512-019-0046-9

10.1002/sim.7653

10.1016/S0140-6736(20)30566-3

10.1097/RLI.0000000000000672

10.1007/s00392-020-01626-9

Chaganti S, Balachandran A, Chabin G, et al. Quantification of tomographic patterns associated with covid-19 from chest CT. arXiv e-prints [Preprint] 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200401279C.

10.1016/j.tmaid.2020.101623

Gozes O, Frid-Adar M, Sagie N, et al. Coronavirus detection and analysis on chest CT with deep learning. arXiv e-prints [Preprint] 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200402640G.

Imran A, Posokhova I, Qureshi HN, et al. AI4covid-19: AI enabled preliminary diagnosis for covid-19 from cough samples via an app. arXiv e-prints [Preprint] 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200401275I.

10.1038/d41586-020-00613-4

Li X, Li C, Zhu D. covid-MobileXpert: on-device covid-19 screening using snapshots of chest x-ray. arXiv e-prints [Preprint] 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200403042L.

10.1101/2020.03.30.20047787

Tang Z, Zhao W, Xie X, et al. Severity assessment of coronavirus disease 2019 (covid-19) using quantitative features from chest CT images. arXiv e-prints [Preprint] 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200311988T.

Zhang J, Xie Y, Li Y, et al. covid-19 Screening on Chest X-ray Images Using Deep Learning based Anomaly Detection. arXiv e-prints 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200312338Z.

10.1101/2020.03.24.20043117

10.1148/radiol.2020201491

10.1101/2020.04.23.20076976

10.1101/2020.03.25.20043166

10.1378/chest.1118087

10.1177/0272989X14547233

Arpan M, Surya K, Harish R, et al. CovidAID: covid-19 Detection Using Chest X-Ray. ArXiv e-prints [Preprint] 2020

10.1161/CIRCULATIONAHA.115.017719

10.1136/bmj.i3140

Bassi PRAS, Attux R. A deep convolutional neural network for covid-19 detection using chest x-rays. ArXiv e-prints [Preprint] 2020

10.1016/j.jclinepi.2015.04.005

10.1186/s41512-019-0046-9

10.1002/sim.7653

10.1016/S0140-6736(20)30566-3

Born J, Brandle G, Cossio M, et al. Pocovid-Net: Automatic detection of covid-19 from a new lung ultrasound imaging dataset (POCUS). ArXiv e-prints [Preprint] 2020.

10.1007/s00392-020-01626-9

10.1101/2020.04.05.20047944

10.1016/j.tmaid.2020.101623

10.1016/j.cca.2020.03.022

10.1101/2020.04.13.20064329

10.1038/d41586-020-00613-4

10.1016/s1473-3099(20)30119-5

10.1101/2020.04.27.20081984

10.1093/cid/ciaa414

10.32604/cmc.2020.010691

10.1093/cid/ciaa414

10.1101/2020.04.21.20063263

10.1378/chest.1118087

10.1177/0272989X14547233

10.1177/962280218784726

10.1101/2020.04.20.20067512

Jiang Z, Hu M, Fan L, et al. Combining visible light and infrared imaging for efficient detection of respiratory infections such as covid-19 on portable device. ArXiv e-prints [Preprint] 2020.

10.1101/2020.04.17.20070219

Rezaul KM, Döhmen T, Rebholz-Schuhmann D, et al. DeepcovidExplainer: explainable covid-19 predictions based on chest x-ray images. ArXiv e-prints [Preprint] 2020.

10.1097/RLI.0000000000000689

10.1101/2020.04.16.20068411

10.1101/2020.04.12.20062661

10.1101/2020.04.05.20048421

10.1038/s41591-020-0931-3

10.1016/j.compbiomed.2020.103792

10.1097/RLI.0000000000000689

10.1101/2020.04.11.20054643

10.1007/s10096-020-03901-z

10.1101/2020.04.24.20079012

Moutounet-Cartan PGB. Deep convolutional neural networks to diagnose covid-19 and other pneumonia diseases from posteroanterior chest x-rays. ArXiv e-prints [Preprint] 2020

10.1101/2020.04.28.20081687

10.1016/j.mehy.2020.109761

10.1101/2020.04.26.20073411

10.1101/2020.04.15.20066860

10.1101/2020.04.09.20058594

10.1101/2020.04.15.20066860

10.1101/2020.04.28.20082222

10.1101/2020.04.18.20071019

10.1016/j.ijid.2020.04.041

10.1093/cid/ciaa443

10.1016/j.ijid.2020.04.041

Wu Y-H, Gao S-H, Mei J, et al. JCS: an explainable covid-19 diagnosis system by joint classification and segmentation. ArXiv e-prints [Preprint] 2020.

10.1007/s40846-020-00529-4

10.1016/j.compbiomed.2020.103795

10.1111/anae.15175

10.1080/09537104.2020.1760230

10.1016/j.ijid.2020.05.021

10.3390/jcm9051514

10.3390/jcm9051548

10.3390/jcm9061668

10.3390/jcm9061959

10.1111/acem.14009

10.1111/tbed.13651

10.1080/07391102.2020.1767212

10.1097/RTI.0000000000000544

10.1016/j.jinf.2020.05.064

10.5152/dir.2020.20351

10.1002/sim.6787

10.1016/j.jclinepi.2004.06.017

10.1136/bmj.m441

10.1161/CIRCULATIONAHA.115.017719

10.1186/s12916-019-1466-7

10.1136/bmj.i3140

10.1371/journal.pmed.1001886

10.1016/j.jclinepi.2015.04.005

10.1186/s41512-019-0046-9

10.1002/sim.7653

10.1016/S0140-6736(20)30566-3

10.1097/RLI.0000000000000672

10.1007/s00392-020-01626-9

10.7883/yoken.JJID.2020.194

10.1016/j.tmaid.2020.101623

10.1016/j.cca.2020.03.022

10.7150/thno.45985

10.1038/d41586-020-00613-4

10.1016/s1473-3099(20)30119-5

10.1016/j.ijid.2020.04.078

10.1186/s41747-020-00167-0

10.3390/jcm9061781

10.1148/radiol.2020201874

10.1093/jamia/ocaa105

10.1093/jamia/ocz130

10.1378/chest.1118087

10.1177/0272989X14547233

10.1177/962280218784726

10.1007/s00259-020-04929-1

10.1016/j.jcv.2020.104431

10.1002/jmv.26166

10.1016/j.chemolab.2020.104054

10.1007/s00264-020-04609-7

10.1016/j.jaip.2020.06.013

10.1016/j.tmaid.2020.101782

10.1093/cid/ciaa538

10.1093/ofid/ofaa169

10.1093/cid/ciaa793

10.1016/j.ejrad.2020.109041

10.1002/jmv.26022

10.1016/j.jaci.2020.04.027

10.1016/j.amepre.2020.05.002

10.3389/fcimb.2020.00318

10.1016/j.cell.2020.04.045

10.1017/dmp.2020.214

10.1371/journal.pone.0233328

10.1097/CCM.0000000000004411

10.1016/j.cell.2020.04.045

10.1017/dmp.2020.214

10.1183/13993003.00775-2020

10.1002/sim.6787

10.1016/j.jclinepi.2004.06.017

10.1101/2020.04.22.20075416

10.1136/bmj.m441

10.1161/CIRCULATIONAHA.115.017719

10.1097/CCE.0000000000000253

10.1186/s12916-019-1466-7

10.1136/bmj.i3140

10.1371/journal.pmed.1001886

10.1016/j.jclinepi.2015.04.005

10.1186/s41512-019-0046-9

10.1002/sim.7653

10.1111/crj.13326

10.1007/s11606-021-06626-7

10.1093/jamia/ocz130

10.1378/chest.1118087

10.1177/0272989X14547233

10.1136/bmj.m3731

10.1136/bmj.m2815

10.1183/13993003.01494-2020

10.1177/962280218784726

10.1016/j.archger.2020.104240

10.1371/journal.pone.0243262

10.1136/bmjopen-2020-041983

10.1111/echo.14962

10.2196/24246

10.1038/s41379-020-00700-x

10.1136/bmjresp-2020-000729

10.1016/j.compbiomed.2020.103949

10.1186/s12931-020-01511-z

10.3389/fmed.2020.556886

10.21037/atm-20-7447

10.1093/europace/euab015

10.1016/j.amjcard.2020.08.040

10.1016/j.media.2020.101844

10.1002/jmv.26713

10.1259/bjr.20200634

10.18632/aging.202261

10.1002/jmv.26572

10.1016/j.ijantimicag.2020.106110

10.1186/s12985-021-01502-6

10.2196/26257

10.1371/journal.pone.0242953

10.1016/j.hrtlng.2021.01.006

10.1136/bmj.m3731

10.1111/jgs.16956

10.1016/j.resuscitation.2020.08.124

10.3389/fpubh.2020.574915

10.26355/eurrev_202010_23250

10.1016/j.jhep.2020.12.012

10.26355/eurrev_202010_23249

10.1093/cid/ciaa963

10.1016/j.bja.2020.11.034

10.1016/j.thromres.2020.09.017

10.1038/s41598-020-79470-0

10.1371/journal.pone.0244629

10.1007/s11739-020-02594-8

10.1007/s00330-020-07622-x

10.1183/13993003.02113-2020

10.1002/ehf2.13022

10.2196/19588

10.1038/s41467-020-18786-x

10.1038/s41598-021-82885-y

10.1111/ijcp.13974

10.1371/journal.pone.0239172

10.1093/ofid/ofaa463

10.21203/rs.3.rs-126892/v1

10.1007/s11739-020-02480-3

10.1136/bmjopen-2020-040729

10.1038/s41467-020-18684-2

10.1111/ijcp.13705

10.7326/M20-3905

10.23736/S0026-4806.20.07074-3

10.1055/s-0040-1716544

10.4414/smw.2021.20471

10.1371/journal.pone.0245840

10.1080/07853890.2020.1868564

10.1038/s41598-020-75651-z

10.1093/ije/dyaa209

10.1038/s41598-020-78505-w

10.2147/IDR.S263157

10.1016/S2213-2600(20)30559-2

10.1183/13993003.03498-2020

10.3389/fmed.2020.585003

10.1016/j.annemergmed.2020.07.022

10.1371/journal.pone.0239536

10.1080/07853890.2020.1828616

10.7554/eLife.60519

10.1159/000511403

10.1007/s00261-020-02823-w

10.1186/s40560-021-00527-x

10.2196/22131

10.2196/24973

10.1016/j.resplu.2020.100042

10.1017/dmp.2020.324

10.1016/j.nut.2020.111123

10.1002/iid3.353

10.1038/s41598-020-75629-x

10.1016/j.jiac.2020.10.013

10.2196/23458

10.5005/jp-journals-10071-23683

10.1080/1354750X.2020.1841296

10.3346/jkms.2020.35.e234

10.1371/journal.pone.0237419

10.1038/s41598-021-81844-x

10.1093/ofid/ofaa405

10.7759/cureus.11368

10.1016/j.meegid.2021.104737

10.1097/CCE.0000000000000300

10.2196/24225

10.24875/RIC.20000451

10.1371/journal.pone.0241825

10.1016/j.amjmed.2020.10.044

10.1016/j.cmpb.2021.105951

10.2196/25442

10.1016/j.jiac.2020.12.009

10.1016/j.resuscitation.2020.10.039

10.1016/j.jaci.2020.07.009

10.3390/jcm9113726

10.1038/s41467-020-20657-4

10.1007/s11606-020-06353-5

10.1186/s12879-020-05688-y

10.1111/jth.15261

10.18632/aging.202605

10.2147/CIA.S273720

10.1007/s00521-020-05592-1

10.7717/peerj.10337

10.3389/fpubh.2020.587937

10.1186/s12879-020-05561-y

10.1038/s41467-020-17280-8

10.7554/eLife.63195

10.1136/jitc-2020-001314

10.1097/CCM.0000000000004549

10.1016/j.medj.2020.12.013

10.18632/aging.103716

10.1038/s41598-021-81732-4

10.1016/S2589-7500(20)30316-2

10.2147/RMHP.S278365

10.1016/j.ajem.2020.07.019

10.1016/j.medin.2020.10.003

10.3390/jcm9092799

10.1007/s10875-020-00821-7

10.1016/j.micpath.2020.104706

10.3389/fpubh.2020.00475

10.1186/s12879-020-05614-2

10.1371/journal.pone.0245281

10.1161/JAHA.120.018477

10.1016/j.ebiom.2020.103026

10.2196/22033

10.1136/bmjopen-2020-044028

10.1038/s41598-020-78870-6

10.21149/11684

10.1007/s42979-020-00216-w

10.1186/s13049-020-00764-3

10.1016/j.ijid.2020.10.003

10.1016/j.patter.2020.100074

10.1080/07853890.2020.1803499

10.1101/2020.09.14.20194670

10.1038/s41551-020-00633-5

10.1017/dmp.2021.320

10.1007/s11739-020-02543-5

10.3389/fpubh.2020.00461

10.2196/23128

10.1136/bmjspcare-2020-002602

10.1093/labmed/lmaa105

10.1016/j.csbj.2021.01.042

10.1097/MD.0000000000021700

10.2196/24572

10.1038/s41746-020-00343-x

10.1038/s41598-020-78392-1

10.1371/journal.pone.0244627

10.1016/j.ijid.2020.11.003

10.1093/jamia/ocab005

10.1016/j.amjcard.2020.09.029

10.1016/j.ajem.2020.09.017

10.1016/j.amsu.2020.09.044

10.22088/cjim.11.0.536

10.1007/s00330-020-07623-w

10.3390/ijerph17228386

10.2196/23026

10.1007/s10096-020-04145-7

10.1148/radiol.2020202723

10.1186/s12967-021-02720-w

10.12688/f1000research.26723.1

10.1016/j.eclinm.2020.100426

10.1016/j.ajem.2020.10.068

10.1016/j.chest.2020.12.009

10.1111/ijcp.13926

10.1016/j.medj.2020.10.002

10.1007/s00432-020-03420-6

10.1002/emp2.12259

10.1111/dom.14256

10.1186/s12911-020-01359-9

10.1093/infdis/jiaa663

10.1016/j.athoracsur.2020.12.050

10.1002/jmv.26844

10.1186/s40246-020-00288-y

10.3390/jcm9103066

10.1186/s12911-020-01338-0

10.2196/24207

10.1136/bmjopen-2020-045141

van de Sande, 2020, Predicting thromboembolic complications in COVID-19 ICU patients using machine learning, J Clin Transl Res, 6, 179

10.1111/ijcp.13858

10.1136/emermed-2020-210199

10.7883/yoken.JJID.2020.227

10.1177/0300060520955037

10.7717/peerj.10018

10.1186/s12967-020-02655-8

10.1002/jcla.23566

10.2196/21788

10.1186/s12967-020-02505-7

10.1016/j.ijmedinf.2020.104258

10.1371/journal.pone.0240346

10.1183/13993003.01104-2020

10.1038/s41598-020-71114-7

10.1093/jamia/ocaa295

10.7150/thno.46428

10.1016/j.cca.2020.11.019

10.1016/j.ebiom.2020.102880

10.1016/j.eng.2020.05.014

10.1259/bjr.20200219

10.3389/fmed.2020.607821

10.1002/jmv.26551

10.3389/fmed.2020.00518

10.1016/j.intimp.2020.107065

10.1016/S2589-7500(20)30217-X

10.3389/fmed.2020.597791

10.1186/s12880-020-00513-z

10.7717/peerj.9885

10.1016/j.eng.2020.10.013

10.18632/aging.103980

10.3389/fmed.2020.590460

10.1186/s13054-020-03123-x

10.21037/atm-20-4977

10.2147/CIA.S268156

10.2147/IDR.S261725

Zhao, 2020, A disease progression prediction model and nervous system symptoms in coronavirus disease 2019 patients, Am J Transl Res, 12, 8192

10.1371/journal.pone.0236618

10.3348/kjr.2020.0485

10.1016/j.patter.2020.100092

10.1080/03007995.2020.1825365

10.7150/ijms.50007

10.1186/s13049-020-00795-w

10.1002/emp2.12205

The Royal College of Physicians . National Early Warning Score (NEWS) 2: Standardising the assessment of acute-illness severity in the NHS. Updated report of a working party. RCP, 2017.

10.1101/2020.04.24.20078006

Unit CCT. TACTIC: Cambridge Clinical Trials Unit; 2020. https://cctu.org.uk/portfolio/COVID-19/TACTIC.

10.1093/qjmed/94.10.521

10.1136/thorax.58.5.377

10.1111/j.1365-2796.2004.01321.x

10.1001/jama.2016.0288

10.1136/bmj.m441

10.1002/sim.9275

10.1002/sim.9025

10.1136/bmj.m441

10.1177/09622802211007522

10.1089/neu.2020.7218

10.1016/j.jmpt.2012.07.002

10.1177/0962280218784726

10.1016/j.jclinepi.2015.04.005

10.1186/s12916-019-1466-7

10.1161/CIRCULATIONAHA.115.017719

10.1136/bmj.i3140

10.1371/journal.pmed.1001886

10.1186/s41512-019-0046-9

10.1002/sim.7653

Infervision. Infervision launches hashtag#AI-based hashtag#Covid-19 solution in Europe 2020. https://www.linkedin.com/posts/infervision_ai-covid-medicine-activity-6650772755031613440-TqLJ.

Offord C. Surgisphere fallout hits African nonprotfits covid-19 efforts 2020. The Scientist. https://www.the-scientist.com/news-opinion/surgisphere-fallout-hits-african-nonprofits-covid-19-efforts--67617.

10.1093/jamia/ocz130

10.23889/ijpds.v5i4.1697

10.1016/S2589-7500(21)00080-7

10.1136/thoraxjnl-2021-217580

10.1371/journal.pone.0255748

10.1136/bmj-2021-069881

10.1177/0272989X14547233

10.1002/sim.6787

10.1016/j.jclinepi.2004.06.017

10.1136/bmj.m2815

10.1183/13993003.01494-2020