Prediction of in-hospital mortality rate in COVID-19 patients with diabetes mellitus using machine learning methods.
Coronavirus
Decision Tree Classifier
Diabetic patients
Epidemiology Research
Journal
Journal of diabetes and metabolic disorders
ISSN: 2251-6581
Titre abrégé: J Diabetes Metab Disord
Pays: Switzerland
ID NLM: 101590741
Informations de publication
Date de publication:
13 May 2023
13 May 2023
Historique:
received:
17
09
2022
accepted:
24
04
2023
pubmed:
26
6
2023
medline:
26
6
2023
entrez:
26
6
2023
Statut:
aheadofprint
Résumé
Since its emergence in December 2019, until June 2022, coronavirus 2019 (COVID-19) has impacted populations all around the globe with it having been contracted by ~ 535 M people and leaving ~ 6.31 M dead. This makes identifying and predicating COVID-19 an important healthcare priority. The dataset used in this study was obtained from Shahid Beheshti University of Medical Sciences in Tehran, and includes the information of 29,817 COVID-19 patients who were hospitalized between October 8, 2019 and March 8, 2021. As diabetes has been shown to be a significant factor for poor outcome, we have focused on COVID-19 patients with diabetes, leaving us with 2824 records. The data has been analyzed using a decision tree algorithm and several association rules were mined. Said decision tree was also used in order to predict the release status of patients. We have used accuracy (87.07%), sensitivity (88%), and specificity (80%) as assessment metrics for our model. Initially, this study provided information about the percentages of admitted Covid-19 patients with various underlying disease. It was observed that diabetic patients were the largest population at risk. As such, based on the rules derived from our dataset, we found that age category (51-80), CPR and ICU residency play a pivotal role in the discharge status of diabetic inpatients.
Sections du résumé
Background
UNASSIGNED
Since its emergence in December 2019, until June 2022, coronavirus 2019 (COVID-19) has impacted populations all around the globe with it having been contracted by ~ 535 M people and leaving ~ 6.31 M dead. This makes identifying and predicating COVID-19 an important healthcare priority.
Method and Material
UNASSIGNED
The dataset used in this study was obtained from Shahid Beheshti University of Medical Sciences in Tehran, and includes the information of 29,817 COVID-19 patients who were hospitalized between October 8, 2019 and March 8, 2021. As diabetes has been shown to be a significant factor for poor outcome, we have focused on COVID-19 patients with diabetes, leaving us with 2824 records.
Results
UNASSIGNED
The data has been analyzed using a decision tree algorithm and several association rules were mined. Said decision tree was also used in order to predict the release status of patients. We have used accuracy (87.07%), sensitivity (88%), and specificity (80%) as assessment metrics for our model.
Conclusion
UNASSIGNED
Initially, this study provided information about the percentages of admitted Covid-19 patients with various underlying disease. It was observed that diabetic patients were the largest population at risk. As such, based on the rules derived from our dataset, we found that age category (51-80), CPR and ICU residency play a pivotal role in the discharge status of diabetic inpatients.
Identifiants
pubmed: 37363202
doi: 10.1007/s40200-023-01228-y
pii: 1228
pmc: PMC10182753
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1-14Informations de copyright
© The Author(s), under exclusive licence to Tehran University of Medical Sciences 2023, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Déclaration de conflit d'intérêts
Conflicts of interestThe authors declare no conflict of interest.
Références
Diabetologia. 2021 Apr;64(4):778-794
pubmed: 33599800
Med Intensiva (Engl Ed). 2022 Feb;46(2):98-101
pubmed: 34896032
Metabolism. 2020 Jun;107:154217
pubmed: 32220611
Prim Care Diabetes. 2021 Oct;15(5):778-785
pubmed: 34210639
Metabolism. 2020 Jul;108:154248
pubmed: 32335075
Diabet Med. 2020 Jul;37(7):1146-1154
pubmed: 32392380
Sci China Life Sci. 2020 Mar;63(3):364-374
pubmed: 32048163
Diabetes Metab Syndr. 2020 Jul - Aug;14(4):303-310
pubmed: 32298981
Lancet Diabetes Endocrinol. 2021 Feb;9(2):82-93
pubmed: 33357491
Acta Diabetol. 2021 Feb;58(2):139-144
pubmed: 32583078
Chaos Solitons Fractals. 2020 Oct;139:110050
pubmed: 32834604
Health Care Manag Sci. 2008 Sep;11(3):275-87
pubmed: 18826005
Epidemiol Infect. 2022 Jan 21;150:e38
pubmed: 35057873
Diabetes Care. 2020 Aug;43(8):1690-1694
pubmed: 32540920
Nat Rev Endocrinol. 2021 Jan;17(1):11-30
pubmed: 33188364
Curr Diabetes Rev. 2021;17(5):e211020187087
pubmed: 33087031
Int J Environ Health Res. 2022 Apr;32(4):723-737
pubmed: 32672064
Virol Sin. 2016 Feb;31(1):81-4
pubmed: 26826080
Diabet Med. 2006 Jun;23(6):623-8
pubmed: 16759303
Diabetes Res Clin Pract. 2020 Apr;162:108142
pubmed: 32278764
Diabetes Metab Syndr. 2021 Sep-Oct;15(5):102231
pubmed: 34330072
Int J Environ Health Res. 2022 May;32(5):1095-1110
pubmed: 33090891
Healthc Inform Res. 2013 Jun;19(2):121-9
pubmed: 23882417
PLoS One. 2021 Mar 18;16(3):e0248580
pubmed: 33735272
J Med Virol. 2022 Jul;94(7):3147-3154
pubmed: 35261064
J Travel Med. 2020 Mar 13;27(2):
pubmed: 32052846
J Racial Ethn Health Disparities. 2023 Apr;10(2):805-816
pubmed: 35445324
JAMA Intern Med. 2020 Jul 1;180(7):934-943
pubmed: 32167524
J Clin Virol. 2020 Jun;127:104354
pubmed: 32305882
BMC Infect Dis. 2021 Aug 9;21(1):783
pubmed: 34372767
Front Public Health. 2022 Apr 11;10:841906
pubmed: 35480594
Open Life Sci. 2021 Mar 25;16(1):297-302
pubmed: 33817321