Seasonality of acute kidney injury phenotypes in England: an unsupervised machine learning classification study of electronic health records.
Acute kidney injury
Clustering
Phenotypes
Seasonality
Journal
BMC nephrology
ISSN: 1471-2369
Titre abrégé: BMC Nephrol
Pays: England
ID NLM: 100967793
Informations de publication
Date de publication:
09 08 2023
09 08 2023
Historique:
received:
05
05
2023
accepted:
14
07
2023
medline:
11
8
2023
pubmed:
10
8
2023
entrez:
9
8
2023
Statut:
epublish
Résumé
Acute Kidney Injury (AKI) is a multifactorial condition which presents a substantial burden to healthcare systems. There is limited evidence on whether it is seasonal. We sought to investigate the seasonality of AKI hospitalisations in England and use unsupervised machine learning to explore clustering of underlying comorbidities, to gain insights for future intervention. We used Hospital Episodes Statistics linked to the Clinical Practice Research Datalink to describe the overall incidence of AKI admissions between 2015 and 2019 weekly by demographic and admission characteristics. We carried out dimension reduction on 850 diagnosis codes using multiple correspondence analysis and applied k-means clustering to classify patients. We phenotype each group based on the dominant characteristics and describe the seasonality of AKI admissions by these different phenotypes. Between 2015 and 2019, weekly AKI admissions peaked in winter, with additional summer peaks related to periods of extreme heat. Winter seasonality was more evident in those diagnosed with AKI on admission. From the cluster classification we describe six phenotypes of people admitted to hospital with AKI. Among these, seasonality of AKI admissions was observed among people who we described as having a multimorbid phenotype, established risk factor phenotype, and general AKI phenotype. We demonstrate winter seasonality of AKI admissions in England, particularly among those with AKI diagnosed on admission, suggestive of community triggers. Differences in seasonality between phenotypes suggests some groups may be more likely to develop AKI as a result of these factors. This may be driven by underlying comorbidity profiles or reflect differences in uptake of seasonal interventions such as vaccines.
Sections du résumé
BACKGROUND
Acute Kidney Injury (AKI) is a multifactorial condition which presents a substantial burden to healthcare systems. There is limited evidence on whether it is seasonal. We sought to investigate the seasonality of AKI hospitalisations in England and use unsupervised machine learning to explore clustering of underlying comorbidities, to gain insights for future intervention.
METHODS
We used Hospital Episodes Statistics linked to the Clinical Practice Research Datalink to describe the overall incidence of AKI admissions between 2015 and 2019 weekly by demographic and admission characteristics. We carried out dimension reduction on 850 diagnosis codes using multiple correspondence analysis and applied k-means clustering to classify patients. We phenotype each group based on the dominant characteristics and describe the seasonality of AKI admissions by these different phenotypes.
RESULTS
Between 2015 and 2019, weekly AKI admissions peaked in winter, with additional summer peaks related to periods of extreme heat. Winter seasonality was more evident in those diagnosed with AKI on admission. From the cluster classification we describe six phenotypes of people admitted to hospital with AKI. Among these, seasonality of AKI admissions was observed among people who we described as having a multimorbid phenotype, established risk factor phenotype, and general AKI phenotype.
CONCLUSION
We demonstrate winter seasonality of AKI admissions in England, particularly among those with AKI diagnosed on admission, suggestive of community triggers. Differences in seasonality between phenotypes suggests some groups may be more likely to develop AKI as a result of these factors. This may be driven by underlying comorbidity profiles or reflect differences in uptake of seasonal interventions such as vaccines.
Identifiants
pubmed: 37558976
doi: 10.1186/s12882-023-03269-0
pii: 10.1186/s12882-023-03269-0
pmc: PMC10413486
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
234Subventions
Organisme : Department of Health
Pays : United Kingdom
Informations de copyright
© 2023. BioMed Central Ltd., part of Springer Nature.
Références
Eur Heart J. 2000 Feb;21(4):315-20
pubmed: 10653679
Clin Epidemiol. 2018 Jan 30;10:187-202
pubmed: 29430198
PLoS Comput Biol. 2019 Jun 20;15(6):e1006907
pubmed: 31220072
J Biomed Inform. 2020 Feb;102:103361
pubmed: 31911172
Kidney Int. 2016 Nov;90(5):943-949
pubmed: 27317356
J Am Coll Cardiol. 2002 Mar 6;39(5):760-6
pubmed: 11869838
Nat Rev Nephrol. 2014 Apr;10(4):193-207
pubmed: 24445744
Stud Health Technol Inform. 2020 Jun 16;270:499-503
pubmed: 32570434
Sci Total Environ. 2018 Mar;616-617:1134-1138
pubmed: 29089137
Sci Rep. 2020 Dec 7;10(1):21340
pubmed: 33288774
J Comp Eff Res. 2020 May;9(7):441-446
pubmed: 32148084
Environ Health. 2019 Jun 14;18(1):55
pubmed: 31200714
J Clin Transl Sci. 2020 Jul 24;5(1):e21
pubmed: 33948244
Nephrol Dial Transplant. 2018 Aug 1;33(8):1354-1362
pubmed: 29462342
Heart Vessels. 2015 Mar;30(2):193-203
pubmed: 24398627
Health Serv Res. 2008 Aug;43(4):1424-41
pubmed: 18756617
Int J Epidemiol. 2015 Jun;44(3):827-36
pubmed: 26050254
Am J Epidemiol. 2019 Dec 31;188(12):2222-2239
pubmed: 31509183
Crit Care. 2022 Aug 19;26(1):251
pubmed: 35986336
Am J Nephrol. 2012;35(4):349-55
pubmed: 22473149
Am J Epidemiol. 2012 May 1;175(9):907-16
pubmed: 22455834
Am J Kidney Dis. 2018 Feb;71(2):200-208
pubmed: 29074166
Respir Res. 2010 Mar 16;11:30
pubmed: 20233420
Nephrol Dial Transplant. 2018 Aug 1;33(8):1281-1283
pubmed: 29635645
BMC Nephrol. 2014 May 29;15:84
pubmed: 24885247
Environ Health. 2017 Oct 27;16(1):114
pubmed: 29078794
Int J Clin Pract. 2017 Sep;71(9):
pubmed: 28869717
BMJ. 2020 Nov 4;371:m3919
pubmed: 33148619
Environ Health. 2019 Apr 18;18(1):35
pubmed: 30999920