Data-driven research on eczema: Systematic characterization of the field and recommendations for the future.
artificial intelligence
atopic dermatitis
bibliometric analysis
statistics
Journal
Clinical and translational allergy
ISSN: 2045-7022
Titre abrégé: Clin Transl Allergy
Pays: England
ID NLM: 101576043
Informations de publication
Date de publication:
Jun 2022
Jun 2022
Historique:
received:
24
01
2022
revised:
23
05
2022
accepted:
25
05
2022
entrez:
10
6
2022
pubmed:
11
6
2022
medline:
11
6
2022
Statut:
epublish
Résumé
The past decade has seen a substantial rise in the employment of modern data-driven methods to study atopic dermatitis (AD)/eczema. The objective of this study is to summarise the past and future of data-driven AD research, and identify areas in the field that would benefit from the application of these methods. We retrieved the publications that applied multivariate statistics (MS), artificial intelligence (AI, including machine learning-ML), and Bayesian statistics (BS) to AD and eczema research from the SCOPUS database over the last 50 years. We conducted a bibliometric analysis to highlight the publication trends and conceptual knowledge structure of the field, and applied topic modelling to retrieve the key topics in the literature. Five key themes of data-driven research on AD and eczema were identified: (1) allergic co-morbidities, (2) image analysis and classification, (3) disaggregation, (4) quality of life and treatment response, and (5) risk factors and prevalence. ML&AI methods mapped to studies investigating quality of life, prevalence, risk factors, allergic co-morbidities and disaggregation of AD/eczema, but seldom in studies of therapies. MS was employed evenly between the topics, particularly in studies on risk factors and prevalence. BS was focused on three key topics: treatment, risk factors and allergy. The use of AD or eczema terms was not uniform, with studies applying ML&AI methods using the term eczema more often. Within MS, papers using cluster and factor analysis were often only identified with the term AD. In contrast, those using logistic regression and latent class/transition models were "eczema" papers. Research areas that could benefit from the application of data-driven methods include the study of the pathogenesis of the condition and related risk factors, its disaggregation into validated subtypes, and personalised severity management and prognosis. We highlight BS as a new and promising approach in AD and eczema research.
Sections du résumé
Background
UNASSIGNED
The past decade has seen a substantial rise in the employment of modern data-driven methods to study atopic dermatitis (AD)/eczema. The objective of this study is to summarise the past and future of data-driven AD research, and identify areas in the field that would benefit from the application of these methods.
Methods
UNASSIGNED
We retrieved the publications that applied multivariate statistics (MS), artificial intelligence (AI, including machine learning-ML), and Bayesian statistics (BS) to AD and eczema research from the SCOPUS database over the last 50 years. We conducted a bibliometric analysis to highlight the publication trends and conceptual knowledge structure of the field, and applied topic modelling to retrieve the key topics in the literature.
Results
UNASSIGNED
Five key themes of data-driven research on AD and eczema were identified: (1) allergic co-morbidities, (2) image analysis and classification, (3) disaggregation, (4) quality of life and treatment response, and (5) risk factors and prevalence. ML&AI methods mapped to studies investigating quality of life, prevalence, risk factors, allergic co-morbidities and disaggregation of AD/eczema, but seldom in studies of therapies. MS was employed evenly between the topics, particularly in studies on risk factors and prevalence. BS was focused on three key topics: treatment, risk factors and allergy. The use of AD or eczema terms was not uniform, with studies applying ML&AI methods using the term eczema more often. Within MS, papers using cluster and factor analysis were often only identified with the term AD. In contrast, those using logistic regression and latent class/transition models were "eczema" papers.
Conclusions
UNASSIGNED
Research areas that could benefit from the application of data-driven methods include the study of the pathogenesis of the condition and related risk factors, its disaggregation into validated subtypes, and personalised severity management and prognosis. We highlight BS as a new and promising approach in AD and eczema research.
Identifiants
pubmed: 35686200
doi: 10.1002/clt2.12170
pii: CLT212170
pmc: PMC9172212
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e12170Informations de copyright
© 2022 The Authors. Clinical and Translational Allergy published by John Wiley & Sons Ltd on behalf of European Academy of Allergy and Clinical Immunology.
Déclaration de conflit d'intérêts
Nothing to declare.
Références
Br J Dermatol. 2022 Feb;186(2):274-284
pubmed: 34564850
Phytomedicine. 2019 Jun;59:152914
pubmed: 30991183
Nature. 2017 Feb 2;542(7639):115-118
pubmed: 28117445
Ann Allergy Asthma Immunol. 2020 Dec;125(6):665-673.e1
pubmed: 32971247
Expert Rev Respir Med. 2021 May;15(5):609-621
pubmed: 33618597
J Allergy Clin Immunol. 2017 Feb;139(2):400-407
pubmed: 27871876
Nature. 2020 Jan;577(7788):89-94
pubmed: 31894144
Bioinform Biol Insights. 2020 Jan 31;14:1177932219899051
pubmed: 32076369
J Dermatolog Treat. 2022 Jun;33(4):2024-2033
pubmed: 33761805
Exp Dermatol. 2016 Jun;25(6):453-9
pubmed: 26841714
BMC Genomics. 2021 Aug 4;22(1):592
pubmed: 34348664
Nat Med. 2019 Sep;25(9):1337-1340
pubmed: 31427808
Gene. 2017 Jun 20;617:17-23
pubmed: 28351738
BMJ Open. 2018 Aug 29;8(8):e023061
pubmed: 30158235
Clin Transl Allergy. 2022 Jun 07;12(6):e12170
pubmed: 35686200
J Allergy Clin Immunol. 2017 Jun;139(6):1861-1872.e7
pubmed: 27931974
J Allergy Clin Immunol Pract. 2020 Jan;8(1):236-247.e3
pubmed: 31430591
Allergy. 2022 Feb;77(2):582-594
pubmed: 33894014
Allergy. 2016 Oct;71(10):1480-5
pubmed: 27392131
J Allergy Clin Immunol. 2019 Jan;143(1):36-45
pubmed: 30414395
J Allergy Clin Immunol Pract. 2019 Feb;7(2):578-588.e2
pubmed: 30179741
J Theor Biol. 2018 Jul 7;448:66-79
pubmed: 29625204
Lancet Digit Health. 2020 Aug;2(8):e407-e416
pubmed: 33328045
Clin Exp Allergy. 2021 Sep;51(9):1185-1194
pubmed: 34213816
Clin Exp Allergy. 2020 Nov;50(11):1258-1266
pubmed: 32750186
Syst Rev. 2020 Sep 28;9(1):222
pubmed: 32988419
PLoS Med. 2014 Oct 21;11(10):e1001748
pubmed: 25335105
Sci Transl Med. 2019 Feb 20;11(480):
pubmed: 30787169
Lancet. 2020 Aug 1;396(10247):345-360
pubmed: 32738956
Dermatol Ther (Heidelb). 2020 Jun;10(3):365-386
pubmed: 32253623
JAMA Dermatol. 2020 Jun 1;156(6):659-667
pubmed: 32320001
Br J Dermatol. 2019 Dec;181(6):1272-1279
pubmed: 30822368
J Allergy Clin Immunol. 2015 Nov;136(5):1254-64
pubmed: 26428954
Ann Allergy Asthma Immunol. 2019 Jan;122(1):99-110.e6
pubmed: 30223113
PLoS One. 2020 Nov 23;15(11):e0242781
pubmed: 33227018
Expert Rev Clin Immunol. 2020 Sep;16(9):873-881
pubmed: 32856959
J Allergy Clin Immunol. 2017 Sep;140(3):730-737
pubmed: 28412391