Using Machine Learning Algorithms to Develop a Clinical Decision-Making Tool for COVID-19 Inpatients.

Publisher: MDPI Country of Publication: Switzerland NLM ID: 101238455 Publication Model: Electronic Cited Medium: Internet ISSN: 1660-4601 (Electronic) Linking ISSN: 16604601 NLM ISO Abbreviation: Int J Environ Res Public Health Subsets: MEDLINE

Original Publication: Basel : MDPI, c2004-

COVID-19* ; Inpatients*; Adult ; Algorithms ; Bayes Theorem ; Clinical Decision-Making ; Humans ; Machine Learning ; Retrospective Studies ; SARS-CoV-2

Background: Within the UK, COVID-19 has contributed towards over 103,000 deaths. Although multiple risk factors for COVID-19 have been identified, using this data to improve clinical care has proven challenging. The main aim of this study is to develop a reliable, multivariable predictive model for COVID-19 in-patient outcomes, thus enabling risk-stratification and earlier clinical decision-making.
Methods: Anonymised data consisting of 44 independent predictor variables from 355 adults diagnosed with COVID-19, at a UK hospital, was manually extracted from electronic patient records for retrospective, case-control analysis. Primary outcomes included inpatient mortality, required ventilatory support, and duration of inpatient treatment. Pulmonary embolism sequala was the only secondary outcome. After balancing data, key variables were feature selected for each outcome using random forests. Predictive models were then learned and constructed using Bayesian networks.
Results: The proposed probabilistic models were able to predict, using feature selected risk factors, the probability of the mentioned outcomes. Overall, our findings demonstrate reliable, multivariable, quantitative predictive models for four outcomes, which utilise readily available clinical information for COVID-19 adult inpatients. Further research is required to externally validate our models and demonstrate their utility as risk stratification and clinical decision-making tools.

J Biomed Inform. 2018 Sep;85:189-203. (PMID: 30031057)
Hum Resour Health. 2020 Dec 17;18(1):100. (PMID: 33334335)
Artif Intell Med. 2020 Jul;107:101912. (PMID: 32828451)
Eur Urol. 2015 Jun;67(6):1142-1151. (PMID: 25572824)
Front Oncol. 2015 Dec 03;5:272. (PMID: 26697407)
Jpn J Radiol. 2020 May;38(5):409-410. (PMID: 32266524)
J Bioinform Comput Biol. 2020 Aug;18(4):2050023. (PMID: 32706288)
Head Neck. 2020 Jul;42(7):1629-1633. (PMID: 32342570)
J Bioinform Comput Biol. 2005 Apr;3(2):185-205. (PMID: 15852500)
Eur Respir J. 2020 May 14;55(5):. (PMID: 32217650)
J Biomed Inform. 2009 Apr;42(2):356-64. (PMID: 18824133)
Influenza Other Respir Viruses. 2020 Jul;14(4):474-475. (PMID: 32246886)
Bioinformatics. 2007 Oct 1;23(19):2507-17. (PMID: 17720704)
Int J Infect Dis. 2020 May;94:154-155. (PMID: 32179137)
West J Emerg Med. 2020 Apr 13;21(3):470-472. (PMID: 32302278)
JAMA. 2020 May 26;323(20):2052-2059. (PMID: 32320003)
Lancet. 2020 Mar 28;395(10229):1054-1062. (PMID: 32171076)
BMJ. 2020 Apr 7;369:m1328. (PMID: 32265220)
Sci China Life Sci. 2020 May;63(5):706-711. (PMID: 32146694)
Respir Med. 2020 Jul;168:105980. (PMID: 32364959)
Travel Med Infect Dis. 2020 May - Jun;35:101608. (PMID: 32114075)
Nat Rev Genet. 2015 Jun;16(6):321-32. (PMID: 25948244)
Eur Heart J Acute Cardiovasc Care. 2020 Apr;9(3):248-252. (PMID: 32347745)
Korean J Anesthesiol. 2013 May;64(5):402-6. (PMID: 23741561)
Malays J Pathol. 2020 Apr;42(1):23-35. (PMID: 32342928)
BMJ. 2020 Apr 2;369:m1375. (PMID: 32241884)
BMJ Open. 2013 Jun 28;3(6):. (PMID: 23811171)
Eur Respir J. 2020 Dec 24;56(6):. (PMID: 32978307)
Epidemiol Infect. 2020 Jun 25;148:e125. (PMID: 32580792)
Future Healthc J. 2018 Feb;5(1):47-51. (PMID: 31098532)
Global Health. 2020 Sep 29;16(1):92. (PMID: 32993696)
BMJ. 2020 Sep 9;370:m3339. (PMID: 32907855)

Keywords: Bayesian network; COVID-19; SARS CoV; random forest; risk stratification; synthetic minority oversampling technique (SMOTE)

Date Created: 20210702 Date Completed: 20210707 Latest Revision: 20210724

20240628

PMC8296041

10.3390/ijerph18126228

34207560