Machine Learning Consensus Clustering Approach for Hospitalized Patients with Phosphate Derangements.
artificial intelligence
clustering
electrolytes
hyperphosphatemia
hypophosphatemia
individualized medicine
machine learning
nephrology
personalized medicine
phosphate
precision medicine
Journal
Journal of clinical medicine
ISSN: 2077-0383
Titre abrégé: J Clin Med
Pays: Switzerland
ID NLM: 101606588
Informations de publication
Date de publication:
27 Sep 2021
27 Sep 2021
Historique:
received:
08
08
2021
revised:
18
09
2021
accepted:
25
09
2021
entrez:
13
10
2021
pubmed:
14
10
2021
medline:
14
10
2021
Statut:
epublish
Résumé
The goal of this study was to categorize patients with abnormal serum phosphate upon hospital admission into distinct clusters utilizing an unsupervised machine learning approach, and to assess the mortality risk associated with these clusters. We utilized the consensus clustering approach on demographic information, comorbidities, principal diagnoses, and laboratory data of hypophosphatemia (serum phosphate ≤ 2.4 mg/dL) and hyperphosphatemia cohorts (serum phosphate ≥ 4.6 mg/dL). The standardized mean difference was applied to determine each cluster's key features. We assessed the association of the clusters with mortality. In the hypophosphatemia cohort ( Our cluster analysis classified clinically distinct phenotypes with different mortality risks among hospitalized patients with serum phosphate derangements. Age, comorbidities, and kidney function were the key features that differentiated the phenotypes.
Sections du résumé
BACKGROUND
BACKGROUND
The goal of this study was to categorize patients with abnormal serum phosphate upon hospital admission into distinct clusters utilizing an unsupervised machine learning approach, and to assess the mortality risk associated with these clusters.
METHODS
METHODS
We utilized the consensus clustering approach on demographic information, comorbidities, principal diagnoses, and laboratory data of hypophosphatemia (serum phosphate ≤ 2.4 mg/dL) and hyperphosphatemia cohorts (serum phosphate ≥ 4.6 mg/dL). The standardized mean difference was applied to determine each cluster's key features. We assessed the association of the clusters with mortality.
RESULTS
RESULTS
In the hypophosphatemia cohort (
CONCLUSION
CONCLUSIONS
Our cluster analysis classified clinically distinct phenotypes with different mortality risks among hospitalized patients with serum phosphate derangements. Age, comorbidities, and kidney function were the key features that differentiated the phenotypes.
Identifiants
pubmed: 34640457
pii: jcm10194441
doi: 10.3390/jcm10194441
pmc: PMC8509302
pii:
doi:
Types de publication
Journal Article
Langues
eng
Références
J Am Soc Nephrol. 2004 Aug;15(8):2208-18
pubmed: 15284307
Int J Clin Pract. 1997 Nov-Dec;51(8):501-3
pubmed: 9536603
Hosp Pract (1995). 2018 Aug;46(3):121-127
pubmed: 29848117
Medicine (Baltimore). 2000 Jan;79(1):1-8
pubmed: 10670405
BMC Nephrol. 2020 Oct 7;21(1):427
pubmed: 33028266
Arch Intern Med. 1982 Mar;142(3):517-20
pubmed: 6802095
Clin J Am Soc Nephrol. 2015 Jul 7;10(7):1257-72
pubmed: 25287933
Chest. 1997 Mar;111(3):595-600
pubmed: 9118693
J Am Soc Nephrol. 2021 Mar;32(3):639-653
pubmed: 33462081
J Crit Care. 2013 Aug;28(4):536.e9-19
pubmed: 23265292
Panminerva Med. 2017 Sep;59(3):230-240
pubmed: 28497938
BMC Pharmacol Toxicol. 2021 May 28;22(1):30
pubmed: 34049590
Bioinformatics. 2010 Jun 15;26(12):1572-3
pubmed: 20427518
Arch Intern Med. 2003 Apr 14;163(7):803-8
pubmed: 12695271
Sci Rep. 2014 Aug 27;4:6207
pubmed: 25158761
Am J Med. 2005 Oct;118(10):1094-101
pubmed: 16194637
Arch Intern Med. 2007 May 14;167(9):879-85
pubmed: 17502528
Front Neurol. 2021 Apr 14;12:652941
pubmed: 33935953
PLoS One. 2015 Aug 07;10(8):e0133426
pubmed: 26252874
Circulation. 2005 Oct 25;112(17):2627-33
pubmed: 16246962
Anaesth Crit Care Pain Med. 2015 Aug;34(4):255-6
pubmed: 26074380
J Intern Med. 2018 Dec;284(6):603-619
pubmed: 30102808
Prog Biophys Mol Biol. 2020 Mar;151:14-22
pubmed: 31816343
BMC Nephrol. 2019 Sep 18;20(1):362
pubmed: 31533650
Thorax. 1986 Aug;41(8):635-40
pubmed: 3787545
Int J Nephrol Renovasc Dis. 2013 Mar 16;6:61-4
pubmed: 23662071
Am J Med. 2013 Apr;126(4):311-8
pubmed: 23375678
Heart Fail Rev. 2017 May;22(3):349-356
pubmed: 28432604
Chest. 1983 Mar;83(3):504-8
pubmed: 6825484
J Healthc Inform Res. 2018;2(4):402-422
pubmed: 30533598
Ann Clin Lab Sci. 2006 Winter;36(1):67-72
pubmed: 16501239
J Am Soc Nephrol. 2005 Jun;16(6):1788-93
pubmed: 15814832
Diseases. 2021 Aug 01;9(3):
pubmed: 34449583
J Am Soc Nephrol. 2009 Feb;20(2):397-404
pubmed: 18987306
PLoS One. 2012;7(10):e47746
pubmed: 23082206
Postgrad Med J. 2020 Oct 21;:
pubmed: 33087530
Intensive Care Med. 1995 Oct;21(10):826-31
pubmed: 8557871
Genome. 2021 Apr;64(4):416-425
pubmed: 33091314
BMC Med. 2018 Aug 27;16(1):150
pubmed: 30145981
Annu Rev Physiol. 2013;75:535-50
pubmed: 23398154
Eur J Cardiothorac Surg. 2004 Aug;26(2):306-10
pubmed: 15296888
QJM. 2021 Jul 16;:
pubmed: 34270780
J Nephrol. 2018 Apr;31(2):241-247
pubmed: 28975589
J Am Soc Nephrol. 2005 Feb;16(2):520-8
pubmed: 15615819
Nat Clin Pract Nephrol. 2006 Mar;2(3):136-48
pubmed: 16932412
J Clin Pathol. 2008 Oct;61(10):1104-7
pubmed: 18820097
Liver Transpl. 2003 Mar;9(3):248-53
pubmed: 12619021
Am J Kidney Dis. 1997 Jan;29(1):103-5
pubmed: 9002537
Int J Clin Pract. 2020 Apr;74(4):e13461
pubmed: 31830348
Medicina (Kaunas). 2021 Aug 30;57(9):
pubmed: 34577826
Indian J Physiol Pharmacol. 2000 Apr;44(2):225-8
pubmed: 10846641
Kidney Int. 2008 Jul;74(2):148-57
pubmed: 18449174