{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:20:05Z","timestamp":1772166005404,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T00:00:00Z","timestamp":1605744000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T00:00:00Z","timestamp":1605744000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurately predicting patient outcomes in Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) could aid patient management and allocation of healthcare resources. There are a variety of methods which can be used to develop prognostic models, ranging from logistic regression and survival analysis to more complex machine learning algorithms and deep learning. Despite several models having been created for SARS-CoV-2, most of these have been found to be highly susceptible to bias. We aimed to develop and compare two separate predictive models for death during admission with SARS-CoV-2.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>Between March 1 and April 24, 2020, 398 patients were identified with laboratory confirmed SARS-CoV-2 in a London teaching hospital. Data from electronic health records were extracted and used to create two predictive models using: (1) a Cox regression model and (2) an artificial neural network (ANN). Model performance profiles were assessed by validation, discrimination, and calibration.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Both the Cox regression and ANN models achieved high accuracy (83.8%, 95% confidence interval (CI) 73.8\u201391.1 and 90.0%, 95% CI 81.2\u201395.6, respectively). The area under the receiver operator curve (AUROC) for the ANN (92.6%, 95% CI 91.1\u201394.1) was significantly greater than that of the Cox regression model (86.9%, 95% CI 85.7\u201388.2),\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.0136. Both models achieved acceptable calibration with Brier scores of 0.13 and 0.11 for the Cox model and ANN, respectively.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We demonstrate an ANN which is non-inferior to a Cox regression model but with potential for further development such that it can learn as new data becomes available. Deep learning techniques are particularly suited to complex datasets with non-linear solutions, which make them appropriate for use in conditions with a paucity of prior knowledge. Accurate prognostic models for SARS-CoV-2 can provide benefits at the patient, departmental and organisational level.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-020-01316-6","type":"journal-article","created":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T11:03:03Z","timestamp":1605783783000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Comparison of deep learning with regression analysis in creating predictive models for SARS-CoV-2 outcomes"],"prefix":"10.1186","volume":"20","author":[{"given":"Ahmed","family":"Abdulaal","sequence":"first","affiliation":[]},{"given":"Aatish","family":"Patel","sequence":"additional","affiliation":[]},{"given":"Esmita","family":"Charani","sequence":"additional","affiliation":[]},{"given":"Sarah","family":"Denny","sequence":"additional","affiliation":[]},{"given":"Saleh A.","family":"Alqahtani","sequence":"additional","affiliation":[]},{"given":"Gary W.","family":"Davies","sequence":"additional","affiliation":[]},{"given":"Nabeela","family":"Mughal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7095-7922","authenticated-orcid":false,"given":"Luke S. P.","family":"Moore","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"issue":"10229","key":"1316_CR1","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1016\/S0140-6736(20)30566-3","volume":"395","author":"F Zhou","year":"2020","unstructured":"Zhou F, Yu T, Du R, Fan G, Liu Y, Liu Z, et al. Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study. Lancet. 2020;395(10229):1054\u201362.","journal-title":"Lancet"},{"issue":"5","key":"1316_CR2","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1016\/S2213-2600(20)30161-2","volume":"8","author":"J Phua","year":"2020","unstructured":"Phua J, Weng L, Ling L, Egi M, Lim C-M, Divatia JV, et al. Intensive care management of coronavirus disease 2019 (COVID-19): challenges and recommendations. Lancet Respir Med. 2020;8(5):506\u201317.","journal-title":"Lancet Respir Med"},{"issue":"8","key":"1316_CR3","doi-asserted-by":"publisher","first-page":"e20259","DOI":"10.2196\/20259","volume":"22","author":"A Abdulaal","year":"2020","unstructured":"Abdulaal A, Patel A, Charani E, Denny S, Mughal N, Moore L. Prognostic modeling of COVID-19 using artificial intelligence in the United Kingdom: model development and validation. J Med Internet Res. 2020;22(8):e20259. https:\/\/doi.org\/10.2196\/20259.","journal-title":"J Med Internet Res"},{"key":"1316_CR4","doi-asserted-by":"publisher","first-page":"109581","DOI":"10.1109\/ACCESS.2020.3001973","volume":"8","author":"M Jamshidi","year":"2020","unstructured":"Jamshidi M, Lalbakhsh A, Talla J, Peroutka Z, Hadjilooei F, Lalbakhsh P, et al. Artificial intelligence and COVID-19: deep learning approaches for diagnosis and treatment. IEEE Access. 2020;8:109581\u201395.","journal-title":"IEEE Access"},{"key":"1316_CR5","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","volume":"110","author":"E Christodoulou","year":"2019","unstructured":"Christodoulou E, Ma J, Collins GS, Steyerberg EW, Verbakel JY, Van Calster B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019;110:12\u201322. https:\/\/doi.org\/10.1016\/j.jclinepi.2019.02.004.","journal-title":"J Clin Epidemiol"},{"key":"1316_CR6","doi-asserted-by":"publisher","first-page":"m1328","DOI":"10.1136\/bmj.m1328","volume":"369","author":"L Wynants","year":"2020","unstructured":"Wynants L, Van Calster B, Bonten MMJ, Collins GS, Debray TPA, De Vos M, et al. Prediction models for diagnosis and prognosis of covid-19 infection: systematic review and critical appraisal. BMJ. 2020;369:m1328.","journal-title":"BMJ"},{"key":"1316_CR7","doi-asserted-by":"crossref","unstructured":"Xie J, Hungerford D, Chen H, Abrams ST, Li S, Wang G, et al. Development and external validation of a prognostic multivariable model on admission for hospitalized patients with COVID-19. medRxiv. Cold Spring Harbor Laboratory Press; 2020;2020.03.28.20045997.","DOI":"10.1101\/2020.03.28.20045997"},{"key":"1316_CR8","unstructured":"Yan L, Zhang H-T, Xiao Y, Wang M, Sun C, Liang J, et al. Prediction of criticality in patients with severe Covid-19 infection using three clinical features: a machine learning-based prognostic model with clinical data in Wuhan. medRxiv. Cold Spring Harbor Laboratory Press. 2020. https:\/\/medrxiv.org\/content\/early\/2020\/03\/03\/2020.02.27.20028027.abstract."},{"issue":"3","key":"1316_CR9","doi-asserted-by":"publisher","first-page":"e0230548","DOI":"10.1371\/journal.pone.0230548","volume":"15","author":"M Yuan","year":"2020","unstructured":"Yuan M, Yin W, Tao Z, Tan W, Hu Y. Association of radiologic findings with mortality of patients infected with 2019 novel coronavirus in Wuhan, China. PLoS ONE. 2020;15(3):e0230548.","journal-title":"PLoS ONE"},{"issue":"1","key":"1316_CR10","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1186\/s13054-020-2833-7","volume":"24","author":"Y Shi","year":"2020","unstructured":"Shi Y, Yu X, Zhao H, Wang H, Zhao R, Sheng J. Host susceptibility to severe COVID-19 and establishment of a host risk score: findings of 487 cases outside Wuhan. Crit Care. 2020;24(1):108. https:\/\/doi.org\/10.1186\/s13054-020-2833-7.","journal-title":"Crit Care"},{"issue":"3","key":"1316_CR11","doi-asserted-by":"publisher","first-page":"537","DOI":"10.32604\/cmc.2020.010691","volume":"62","author":"X Jiang","year":"2020","unstructured":"Jiang X, Coffee M, Bari A, Wang J, Jiang X, Huang J, et al. Towards an artificial intelligence framework for data-driven prediction of Coronavirus Clinical Severity. Comput Mater Contin Comput Mater Continua. 2020;62(3):537\u201351.","journal-title":"Comput Mater Contin Comput Mater Continua"},{"key":"1316_CR12","doi-asserted-by":"crossref","unstructured":"Lu J, Hu S, Fan R, Liu Z, Yin X, Wang Q, et al. ACP risk grade: a simple mortality index for patients with confirmed or suspected severe acute respiratory syndrome coronavirus 2 disease (COVID-19) during the early stage of outbreak in Wuhan, China. medRxiv. Cold Spring Harbor Laboratory Press; 2020;2020.02.20.20025510.","DOI":"10.2139\/ssrn.3543603"},{"issue":"1","key":"1316_CR13","doi-asserted-by":"publisher","first-page":"55","DOI":"10.7326\/M14-0697","volume":"162","author":"GS Collins","year":"2015","unstructured":"Collins GS, Reitsma JB, Altman DG, Moons KGM. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. Ann Intern Med. 2015;162(1):55\u201363.","journal-title":"Ann Intern Med"},{"key":"1316_CR14","doi-asserted-by":"publisher","unstructured":"Caramelo F, Ferreira N, Oliveiros B. Estimation of risk factors for COVID-19 mortality\u2014preliminary results. medRxiv. 2020. https:\/\/doi.org\/10.1101\/2020.02.24.20027268v1.","DOI":"10.1101\/2020.02.24.20027268v1"},{"issue":"9","key":"1316_CR15","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1016\/j.cmi.2020.05.026","volume":"26","author":"A Patel","year":"2020","unstructured":"Patel A, Charani E, Ariyanayagam D, Abdulaal A, Denny SJ, Mughal N, et al. New-onset anosmia and ageusia in adult patients diagnosed with SARS-CoV-2 infection. Clin Microbiol Infect. 2020;26(9):1236\u201341.","journal-title":"Clin Microbiol Infect"},{"issue":"1","key":"1316_CR16","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/1755-8794-4-31","volume":"4","author":"KK Dobbin","year":"2011","unstructured":"Dobbin KK, Simon RM. Optimally splitting cases for training and testing high dimensional classifiers. BMC Med Genomics. 2011;4(1):31. https:\/\/doi.org\/10.1186\/1755-8794-4-31.","journal-title":"BMC Med Genomics"},{"key":"1316_CR17","unstructured":"Menni C, Valdes AM, Freidin MB, Sudre CH, Nguyen LH, Drew DA, et al. Real-time tracking of self-reported symptoms to predict potential COVID-19. Nat Med. 2020;1\u20134. https:\/\/www.nature.com\/articles\/s41591-020-0916-2."},{"key":"1316_CR18","unstructured":"sklearn.metrics.brier_score_loss \u2014 scikit-learn 0.23.2 documentation. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.metrics.brier_score_loss.html."},{"key":"1316_CR19","doi-asserted-by":"crossref","unstructured":"Liao Z, Carneiro G. On the importance of normalisation layers in deep learning with piecewise linear activation units. In: 2016 IEEE Winter Conference on Applications of Computer Vision, WACV 2016. Institute of Electrical and Electronics Engineers Inc.; 2016.","DOI":"10.1109\/WACV.2016.7477624"},{"key":"1316_CR20","unstructured":"TensorFlow. https:\/\/www.tensorflow.org\/."},{"key":"1316_CR21","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER Delong","year":"1988","unstructured":"Delong ER, Delong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44:837.","journal-title":"Biometrics"},{"issue":"11","key":"1316_CR22","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1109\/LSP.2014.2337313","volume":"21","author":"X Sun","year":"2014","unstructured":"Sun X, Xu W. Fast implementation of DeLong\u2019s algorithm for comparing the areas under correlated receiver operating characteristic curves. IEEE Signal Process Lett. 2014;21(11):1389\u201393.","journal-title":"IEEE Signal Process Lett"},{"issue":"S8","key":"1316_CR23","doi-asserted-by":"publisher","first-page":"1636","DOI":"10.1002\/1097-0142(20010415)91:8+<1636::AID-CNCR1176>3.0.CO;2-D","volume":"91","author":"DJ Sargent","year":"2001","unstructured":"Sargent DJ. Comparison of artificial neural networks with other statistical approaches. Cancer. 2001;91(S8):1636\u201342.","journal-title":"Cancer"},{"key":"1316_CR24","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.jcrc.2019.08.010","volume":"54","author":"J Feng","year":"2019","unstructured":"Feng J, Wang Y, Peng J, Sun M, Zeng J, Jiang H. Comparison between logistic regression and machine learning algorithms on survival prediction of traumatic brain injuries. J Crit Care. 2019;54:110\u20136.","journal-title":"J Crit Care"},{"key":"1316_CR25","doi-asserted-by":"publisher","first-page":"100012","DOI":"10.1016\/j.wnsx.2019.100012","volume":"2","author":"SS Panesar","year":"2019","unstructured":"Panesar SS, D\u2019Souza RN, Yeh FC, Fernandez-Miranda JC. Machine learning versus logistic regression methods for 2-year mortality prognostication in a small, heterogeneous glioma database. World Neurosurg X. 2019;2:100012.","journal-title":"World Neurosurg X"},{"issue":"5","key":"1316_CR26","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1111\/j.1464-410X.2007.06755.x","volume":"99","author":"P Bassi","year":"2007","unstructured":"Bassi P, Sacco E, De Marco V, Aragona M, Volpe A. Prognostic accuracy of an artificial neural network in patients undergoing radical cystectomy for bladder cancer: a comparison with logistic regression analysis. BJU Int. 2007;99(5):1007\u201312. https:\/\/doi.org\/10.1111\/j.1464-410X.2007.06755.x.","journal-title":"BJU Int"},{"issue":"7767","key":"1316_CR27","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","volume":"572","author":"N Toma\u0161ev","year":"2019","unstructured":"Toma\u0161ev N, Glorot X, Rae JW, Zielinski M, Askham H, Saraiva A, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019;572(7767):116\u20139.","journal-title":"Nature"},{"key":"1316_CR28","doi-asserted-by":"publisher","first-page":"m1985","DOI":"10.1136\/bmj.m1985","volume":"369","author":"AB Docherty","year":"2020","unstructured":"Docherty AB, Harrison EM, Green CA, Hardwick HE, Pius R, Norman L, et al. Features of 20 133 UK patients in hospital with covid-19 using the ISARIC WHO Clinical Characterisation Protocol: prospective observational cohort study. BMJ. 2020;369:m1985. https:\/\/doi.org\/10.1136\/bmj.m1985.","journal-title":"BMJ"},{"key":"1316_CR29","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciaa443","author":"J Gong","year":"2020","unstructured":"Gong J, Ou J, Qiu X, Jie Y, Chen Y, Yuan L, et al. A tool to early predict severe 2019-Novel Coronavirus Pneumonia (COVID-19): a multicenter study using the risk nomogram in Wuhan and Guangdong. China Clin Infect Dis. 2020. https:\/\/doi.org\/10.1093\/cid\/ciaa443.","journal-title":"China Clin Infect Dis"},{"key":"1316_CR30","doi-asserted-by":"crossref","unstructured":"Huang H, Cai S, Li Y, Li Y, Fan Y, Li L, et al. Prognostic factors for COVID-19 pneumonia progression to severe symptom based on the earlier clinical features: a retrospective analysis. medRxiv. Cold Spring Harbor Laboratory Press; 2020. https:\/\/medrxiv.org\/content\/early\/2020\/03\/30\/2020.03.28.20045989.abstract.","DOI":"10.1101\/2020.03.28.20045989"},{"key":"1316_CR31","unstructured":"Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd edn. https:\/\/www.oreilly.com\/library\/view\/hands-on-machine-learning\/9781492032632\/."},{"issue":"5","key":"1316_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10916-020-01562-1","volume":"44","author":"KC Santosh","year":"2020","unstructured":"Santosh KC. AI-driven tools for coronavirus outbreak: need of active learning and cross-population train\/test models on multitudinal\/multimodal data. J Med Syst. 2020a;44(5):1\u20135. https:\/\/doi.org\/10.1007\/s10916-020-01562-1.","journal-title":"J Med Syst"},{"issue":"9","key":"1316_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10916-020-01645-z","volume":"44","author":"KC Santosh","year":"2020","unstructured":"Santosh KC. COVID-19 prediction models and unexploited data. J Med Syst. 2020b;44(9):1\u20134. https:\/\/doi.org\/10.1007\/s10916-020-01645-z.","journal-title":"J Med Syst"},{"issue":"10","key":"1316_CR34","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1016\/j.cmi.2020.06.025","volume":"26","author":"S Hughes","year":"2020","unstructured":"Hughes S, Troise O, Donaldson H, Mughal N, Moore LS. Bacterial and fungal coinfection among hospitalised patients with COVID-19: a retrospective cohort study in a UK secondary care setting. Clin Microbiol Infect. 2020;26(10):1395\u20139.","journal-title":"Clin Microbiol Infect"},{"key":"1316_CR35","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2021436","author":"P Horby","year":"2020","unstructured":"Horby P, Lim WS, Emberson J, Mafham M, Bell J, Linsell L, et al. Effect of dexamethasone in hospitalized patients with COVID-19: preliminary report. N Engl J Med. 2020. https:\/\/doi.org\/10.1056\/NEJMoa2021436.","journal-title":"N Engl J Med"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01316-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12911-020-01316-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01316-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T11:25:42Z","timestamp":1605785142000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-020-01316-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,19]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["1316"],"URL":"https:\/\/doi.org\/10.1186\/s12911-020-01316-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-52481\/v4","asserted-by":"object"},{"id-type":"doi","id":"10.21203\/rs.3.rs-52481\/v1","asserted-by":"object"},{"id-type":"doi","id":"10.21203\/rs.3.rs-52481\/v2","asserted-by":"object"},{"id-type":"doi","id":"10.21203\/rs.3.rs-52481\/v3","asserted-by":"object"}]},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,19]]},"assertion":[{"value":"6 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 November 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Data was collected as part of routine care by the responsible clinical team. Data was anonymised at the point of extraction by the care team and no patient identifiable data is reported in this analysis. The study protocol was approved by the Antimicrobial Stewardship Group at Chelsea & Westminster NHS Foundation Trust and this was confirmed (i) as a service development (Reference AP_89) and (ii) that individual written consent to participate was not required by the Research & Development Office of Chelsea & Westminster NHS Foundation Trust. The analysis was conducted in accordance with the Helsinki declaration.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"All authors have completed the ICMJE form for uniform disclosure Form for Disclosure of Potential Conflicts of Interest and declare the following: EC has received speaker fees from bioMerieux (2019). NM has received speaker fees from Beyer (2016) and Pfizer (2019\u20132020) and received educational support from Eumedica (2016) and Baxter (2017). LSPM has consulted for DNAelectronics (2015\u201318), Dairy Crest (2017\u20132018), bioMerieux (2013\u20132020), Umovis Lab (2020), received speaker fees from Profile Pharma (2018\u20132019) and Pfizer (2018\u20132020), received research grants from the National Institute for Health Research (2013\u20132020), CW\u2009+\u2009Charity (2018\u20132020), and Leo Pharma (2016), and received educational support from Eumedica (2016\u20132018). AA and AP none to declare.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"299"}}