{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T20:08:06Z","timestamp":1787170086307,"version":"build-2736575974"},"reference-count":34,"publisher":"JMIR Publications Inc.","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The current severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) outbreak is a public health emergency and the case fatality rate in the United Kingdom is significant. Although there appear to be several early predictors of outcome, there are no currently validated prognostic models or scoring systems applicable specifically to patients with confirmed SARS-CoV-2.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>We aim to create a point-of-admission mortality risk scoring system using an artificial neural network (ANN).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We present an ANN that can provide a patient-specific, point-of-admission mortality risk prediction to inform clinical management decisions at the earliest opportunity. The ANN analyzes a set of patient features including demographics, comorbidities, smoking history, and presenting symptoms and predicts patient-specific mortality risk during the current hospital admission. The model was trained and validated on data extracted from 398 patients admitted to hospital with a positive real-time reverse transcription polymerase chain reaction (RT-PCR) test for SARS-CoV-2.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Patient-specific mortality was predicted with 86.25% accuracy, with a sensitivity of 87.50% (95% CI 61.65%-98.45%) and specificity of 85.94% (95% CI 74.98%-93.36%). The positive predictive value was 60.87% (95% CI 45.23%-74.56%), and the negative predictive value was 96.49% (95% CI 88.23%-99.02%). The area under the receiver operating characteristic curve was 90.12%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This analysis demonstrates an adaptive ANN trained on data at a single site, which demonstrates the early utility of deep learning approaches in a rapidly evolving pandemic with no established or validated prognostic scoring systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/20259","type":"journal-article","created":{"date-parts":[[2020,7,24]],"date-time":"2020-07-24T08:20:52Z","timestamp":1595578852000},"page":"e20259","source":"Crossref","is-referenced-by-count":77,"title":["Prognostic Modeling of COVID-19 Using Artificial Intelligence in the United Kingdom: Model Development and Validation"],"prefix":"10.2196","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3536-4803","authenticated-orcid":false,"given":"Ahmed","family":"Abdulaal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2503-2602","authenticated-orcid":false,"given":"Aatish","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5938-1202","authenticated-orcid":false,"given":"Esmita","family":"Charani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8248-6053","authenticated-orcid":false,"given":"Sarah","family":"Denny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8013-5412","authenticated-orcid":false,"given":"Nabeela","family":"Mughal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7095-7922","authenticated-orcid":false,"given":"Luke","family":"Moore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2020,8,25]]},"reference":[{"key":"ref1","unstructured":"Mortality Analyses - Johns Hopkins Coronavirus Resource Center2020-05-11https:\/\/coronavirus.jhu.edu\/data\/mortality"},{"key":"ref2","unstructured":"Coronavirus cases in the UK: daily updated statistics2020-05-11https:\/\/www.gov.uk\/guidance\/coronavirus-covid-19-information-for-the-public"},{"key":"ref3","unstructured":"Office for National StatisticsDeaths registered weekly in England and Wales, provisional2020-05-11https:\/\/www.ons.gov.uk\/peoplepopulationandcommunity\/birthsdeathsandmarriages\/deaths\/bulletins\/deathsregisteredweeklyinenglandandwalesprovisional\/weekending10april2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(20)30566-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmi.2020.04.012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmet.2020.04.021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/ajt.15970"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/oby.22831"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.02439-2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1101\/2020.03.20.20037325"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1101\/2020.02.24.20027268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1101\/2020.02.20.20025510"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1101\/2020.02.27.20028027"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0230548"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2020.2033"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-2600(20)30161-2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1390-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2196\/20239"},{"key":"ref19","first-page":"1","author":"Lim, B","year":"2018","journal-title":"ArXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0029-1"},{"key":"ref21","unstructured":"HenaoRLuJLucasJFerrantiJCarinLHenaoCElectronic Health Record Analysis via Deep Poisson Factor ModelsPhenotype KnowledgeBase20152020-05-11https:\/\/phekb.org\/"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-018-0304-0"},{"key":"ref23","first-page":"A","author":"Xie, N","year":"2020","journal-title":"ArXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2016.2561974"},{"key":"ref25","first-page":"1","author":"Lipton, Z","year":"2015","journal-title":"ArXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aab3719"},{"key":"ref27","unstructured":"LundbergSAllenPA Unified Approach to Interpreting Model PredictionsGitHub20172020-05-11https:\/\/github.com\/slundberg\/shap"},{"key":"ref28","unstructured":"Loss Functions - ML Glossary documentationML Cheatsheet2020-05-13https:\/\/ml-cheatsheet.readthedocs.io\/en\/latest\/loss_functions.html"},{"key":"ref29","unstructured":"GlorotXBengioYUnderstanding the difficulty of training deep feedforward neural networks2020-05-13http:\/\/proceedings.mlr.press\/v9\/glorot10a\/glorot10a.pdf"},{"key":"ref30","first-page":"1","author":"Kingma, D","year":"2014","journal-title":"ArXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1101\/2020.04.23.20076042"},{"key":"ref32","unstructured":"TensorflowGitHub2020-08-11https:\/\/github.com\/tensorflow\/tensorflow"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1101\/2020.05.06.20092999"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.32388\/ujr2aw.7"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2020\/8\/e20259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:27:28Z","timestamp":1782840448000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.jmir.org\/2020\/8\/e20259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,25]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.2196\/20259","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.20259","asserted-by":"object"}]},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,25]]}}}