Environmental exposures in machine learning and data mining approaches to diabetes etiology: A scoping review.
Data mining
Diabetes mellitus
Environmental exposures
Machine learning
Journal
Artificial intelligence in medicine
ISSN: 1873-2860
Titre abrégé: Artif Intell Med
Pays: Netherlands
ID NLM: 8915031
Informations de publication
Date de publication:
01 2023
01 2023
Historique:
received:
05
04
2022
revised:
06
10
2022
accepted:
23
11
2022
pmc-release:
01
01
2024
entrez:
11
1
2023
pubmed:
12
1
2023
medline:
13
1
2023
Statut:
ppublish
Résumé
Environmental exposures are implicated in diabetes etiology, but are poorly understood due to disease heterogeneity, complexity of exposures, and analytical challenges. Machine learning and data mining are artificial intelligence methods that can address these limitations. Despite their increasing adoption in etiology and prediction of diabetes research, the types of methods and exposures analyzed have not been thoroughly reviewed. We aimed to review articles that implemented machine learning and data mining methods to understand environmental exposures in diabetes etiology and disease prediction. We queried PubMed and Scopus databases for machine learning and data mining studies that used environmental exposures to understand diabetes etiology on September 19th, 2022. Exposures were classified into specific external, general external, or internal exposures. We reviewed machine learning and data mining methods and characterized the scope of environmental exposures studied in the etiology of general diabetes, type 1 diabetes, type 2 diabetes, and other types of diabetes. We identified 44 articles for inclusion. Specific external exposures were the most common exposures studied, and supervised models were the most common methods used. Well-established specific external exposures of low physical activity, high cholesterol, and high triglycerides were predictive of general diabetes, type 2 diabetes, and prediabetes, while novel metabolic and gut microbiome biomarkers were implicated in type 1 diabetes. The use of machine learning and data mining methods to elucidate environmental triggers of diabetes was largely limited to well-established risk factors identified using easily explainable and interpretable models. Future studies should seek to leverage machine learning and data mining to explore the temporality and co-occurrence of multiple exposures and further evaluate the role of general external and internal exposures in diabetes etiology.
Sections du résumé
BACKGROUND
Environmental exposures are implicated in diabetes etiology, but are poorly understood due to disease heterogeneity, complexity of exposures, and analytical challenges. Machine learning and data mining are artificial intelligence methods that can address these limitations. Despite their increasing adoption in etiology and prediction of diabetes research, the types of methods and exposures analyzed have not been thoroughly reviewed.
OBJECTIVE
We aimed to review articles that implemented machine learning and data mining methods to understand environmental exposures in diabetes etiology and disease prediction.
METHODS
We queried PubMed and Scopus databases for machine learning and data mining studies that used environmental exposures to understand diabetes etiology on September 19th, 2022. Exposures were classified into specific external, general external, or internal exposures. We reviewed machine learning and data mining methods and characterized the scope of environmental exposures studied in the etiology of general diabetes, type 1 diabetes, type 2 diabetes, and other types of diabetes.
RESULTS
We identified 44 articles for inclusion. Specific external exposures were the most common exposures studied, and supervised models were the most common methods used. Well-established specific external exposures of low physical activity, high cholesterol, and high triglycerides were predictive of general diabetes, type 2 diabetes, and prediabetes, while novel metabolic and gut microbiome biomarkers were implicated in type 1 diabetes.
DISCUSSION
The use of machine learning and data mining methods to elucidate environmental triggers of diabetes was largely limited to well-established risk factors identified using easily explainable and interpretable models. Future studies should seek to leverage machine learning and data mining to explore the temporality and co-occurrence of multiple exposures and further evaluate the role of general external and internal exposures in diabetes etiology.
Identifiants
pubmed: 36628796
pii: S0933-3657(22)00213-5
doi: 10.1016/j.artmed.2022.102461
pmc: PMC9834645
mid: NIHMS1855110
pii:
doi:
Types de publication
Journal Article
Review
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
102461Subventions
Organisme : NIDDK NIH HHS
ID : T32 DK110966
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR002538
Pays : United States
Organisme : NLM NIH HHS
ID : T15 LM007124
Pays : United States
Organisme : NIDDK NIH HHS
ID : F30 DK134113
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR001067
Pays : United States
Informations de copyright
Copyright © 2022 Elsevier B.V. All rights reserved.
Déclaration de conflit d'intérêts
Declaration of competing interest The authors do not have any conflict of interest to declare.
Références
Int J Diabetes Dev Ctries. 2010 Apr;30(2):63-8
pubmed: 20535308
J Am Med Inform Assoc. 2020 Mar 1;27(3):396-406
pubmed: 31889178
Int J Environ Res Public Health. 2018 Jan 05;15(1):
pubmed: 29304014
BMJ Open. 2016 Dec 1;6(12):e013336
pubmed: 27909038
BMC Med Inform Decis Mak. 2010 Mar 22;10:16
pubmed: 20307319
Circulation. 2015 Nov 17;132(20):1920-30
pubmed: 26572668
Diabetes. 2005 Dec;54 Suppl 2:S125-36
pubmed: 16306330
Diabetes Care. 2021 Apr;44(4):935-943
pubmed: 33563654
Comput Biol Med. 2014 Jul;50:70-5
pubmed: 24835087
Iran Biomed J. 2018 Jan 27;22(5):303-11
pubmed: 29374085
J Pers Med. 2022 May 31;12(6):
pubmed: 35743691
J Psychosom Res. 2002 Oct;53(4):891-5
pubmed: 12377299
J Res Health Sci. 2018 Apr 24;18(2):e00412
pubmed: 29784893
N Engl J Med. 2019 Apr 4;380(14):1347-1358
pubmed: 30943338
J Diabetes Res. 2020 Sep 24;2020:6873891
pubmed: 33029536
Thorax. 2014 Sep;69(9):876-8
pubmed: 24906490
Int J Epidemiol. 2012 Feb;41(1):24-32
pubmed: 22296988
J Epidemiol Glob Health. 2020 Mar;10(1):107-111
pubmed: 32175717
Ann N Y Acad Sci. 2008 Dec;1150:1-13
pubmed: 19120261
Syst Rev. 2021 Nov 1;10(1):288
pubmed: 34724973
Prev Chronic Dis. 2019 Sep 19;16:E130
pubmed: 31538566
Environ Res. 2022 Sep;212(Pt B):113259
pubmed: 35460634
Sensors (Basel). 2022 Aug 17;22(16):
pubmed: 36015915
Int J Environ Res Public Health. 2022 May 10;19(10):
pubmed: 35627338
Diabetes Care. 2021 Jan;44(Suppl 1):S15-S33
pubmed: 33298413
Cell Host Microbe. 2020 Aug 12;28(2):258-272.e6
pubmed: 32619440
Prim Care Diabetes. 2021 Jun;15(3):435-443
pubmed: 33642253
Diabetes Res Clin Pract. 2014 Sep;105(3):391-8
pubmed: 25085758
BMC Med Inform Decis Mak. 2019 Mar 12;19(1):41
pubmed: 30866905
Kaohsiung J Med Sci. 2013 Feb;29(2):93-9
pubmed: 23347811
J Med Internet Res. 2016 Dec 16;18(12):e323
pubmed: 27986644
Lancet. 2016 Jun 4;387(10035):2340-2348
pubmed: 27302273
Environ Sci Technol. 2012 Mar 20;46(6):3046-53
pubmed: 22324457
PLoS One. 2011;6(10):e25792
pubmed: 22043294
BMC Med. 2017 Jul 19;15(1):131
pubmed: 28720102
Anal Chim Acta. 2009 Feb 9;633(2):257-62
pubmed: 19166731
Ann Intern Med. 2015 Jan 6;162(1):W1-73
pubmed: 25560730
Diabetes. 2021 Jan;70(1):282-292
pubmed: 33106256
J Clin Endocrinol Metab. 2022 Jul 14;107(8):2329-2338
pubmed: 35468213
Diabetes. 2020 Feb;69(2):238-248
pubmed: 31740441
Artif Intell Med. 2019 Jul;98:109-134
pubmed: 31383477
Curr Diabetes Rev. 2020;16(8):833-850
pubmed: 31971112
Sci Total Environ. 2022 Feb 1;806(Pt 2):150674
pubmed: 34597539
J Diabetes Metab Disord. 2022 Mar 14;21(1):339-352
pubmed: 35673418
J Diabetes Res. 2019 Jan 22;2019:4248218
pubmed: 30805372
Ann Intern Med. 2018 Oct 2;169(7):467-473
pubmed: 30178033
BMJ Open. 2018 Sep 10;8(9):e021311
pubmed: 30206078
BMC Med Inform Decis Mak. 2019 Nov 6;19(1):211
pubmed: 31694707
Comput Math Methods Med. 2014;2014:618976
pubmed: 25165484
Biomed Res Int. 2015;2015:321656
pubmed: 25883954
Diabetologia. 2017 Sep;60(9):1740-1750
pubmed: 28597074
Vis Comput Ind Biomed Art. 2021 Dec 3;4(1):30
pubmed: 34862560
Health Promot Perspect. 2020 Mar 30;10(2):98-115
pubmed: 32296622
Trends Endocrinol Metab. 2015 Jul;26(7):384-94
pubmed: 26068457
Rev Diabet Stud. 2012 Spring;9(1):6-22
pubmed: 22972441
Int J Endocrinol Metab. 2015 Apr 30;13(2):e25389
pubmed: 25926855
Sao Paulo Med J. 2017 May-Jun;135(3):234-246
pubmed: 28746659
Diabetes Res Clin Pract. 2013 Apr;100(1):111-8
pubmed: 23453177
PLoS Med. 2015 Mar 31;12(3):e1001779
pubmed: 25826379
Med Microbiol Immunol. 2022 Aug;211(4):185-194
pubmed: 35701558
Diabetes Care. 2002 Mar;25(3):471-5
pubmed: 11874932
IEEE/ACM Trans Comput Biol Bioinform. 2015 Jul-Aug;12(4):726-8
pubmed: 26605379
J Diabetes. 2021 Feb;13(2):143-153
pubmed: 33124145
Diabetes Metab Syndr Obes. 2020 Nov 26;13:4621-4630
pubmed: 33273837
Comput Methods Programs Biomed. 2013 Jan;109(1):104-11
pubmed: 23127283
J Clin Endocrinol Metab. 2020 Sep 1;105(9):
pubmed: 32692360
Int J Environ Res Public Health. 2021 Mar 23;18(6):
pubmed: 33806973
Comput Struct Biotechnol J. 2017 Jan 08;15:104-116
pubmed: 28138367
Diabetes Care. 2018 May;41(5):917-928
pubmed: 29567642
J Healthc Inf Manag. 2005 Spring;19(2):64-72
pubmed: 15869215
JMIR Diabetes. 2021 Mar 19;6(1):e23364
pubmed: 33739298
Health Place. 2019 Jul;58:102119
pubmed: 31203032
Diabetes. 2020 Mar;69(3):465-476
pubmed: 32029481