Serviceeinschränkungen vom 12.-22.02.2026 - weitere Infos auf der UB-Homepage
  • Invited commentary: deep learn...

Treffer: Invited commentary: deep learning-methods to amplify epidemiologic data collection and analyses.

Title:
Invited commentary: deep learning-methods to amplify epidemiologic data collection and analyses.
Authors:
Quistberg DA; Urban Health Collaborative, Dornsife School of Public Health, Drexel University, Philadelphia, PA 19104, United States.; Department of Environmental and Occupational Health, Dornsife School of Public Health, Drexel University, Philadelphia, PA 19104, United States., Mooney SJ; Department of Epidemiology, School of Public Health, University of Washington, Seattle, WA 98195, United States., Tasdizen T; Department of Electrical and Computer Engineering, College of Engineering, University of Utah, Salt Lake City, UT 84112, United States.; The Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT 84112, United States., Arbelaez P; Department of Biomedical Engineering, Universidad de los Andes, Bogota 111711, Colombia.; Centro de Investigacion y Formacion en Inteligencia Artificial (CinfonIA), Universidad de los Andes, Bogota 111711, Colombia., Nguyen QC; Department of Epidemiology and Biostatistics, School of Public Health, University of Maryland, College Park, MD 20742, United States.
Source:
American journal of epidemiology [Am J Epidemiol] 2025 Feb 05; Vol. 194 (2), pp. 322-326.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Oxford University Press Country of Publication: United States NLM ID: 7910653 Publication Model: Print Cited Medium: Internet ISSN: 1476-6256 (Electronic) Linking ISSN: 00029262 NLM ISO Abbreviation: Am J Epidemiol Subsets: MEDLINE
Imprint Name(s):
Publication: Cary, NC : Oxford University Press
Original Publication: Baltimore, School of Hygiene and Public Health of Johns Hopkins Univ.
MeSH Terms:
Deep Learning* , Data Collection*/methods, Humans ; Epidemiologic Methods
References:
Am J Epidemiol. 2021 Aug 1;190(8):1476-1482. (PMID: 33751024)
Int J Epidemiol. 2021 Jan 23;49(6):2058-2064. (PMID: 31298274)
Adv Nutr. 2021 Jun 1;12(3):621-631. (PMID: 33606879)
J Biomed Inform. 2023 Jan;137:104274. (PMID: 36539106)
BMC Med Inform Decis Mak. 2021 Mar 9;21(1):92. (PMID: 33750385)
Proc Natl Acad Sci U S A. 2017 Dec 12;114(50):13108-13113. (PMID: 29183967)
JMIR Med Inform. 2020 Jul 30;8(7):e17784. (PMID: 32729840)
Gigascience. 2019 Nov 1;8(11):. (PMID: 31730697)
Brief Bioinform. 2018 Nov 27;19(6):1236-1246. (PMID: 28481991)
Am J Prev Med. 2020 Jan;58(1):152-160. (PMID: 31862100)
JAMA Dermatol. 2019 Oct 01;155(10):1135-1141. (PMID: 31411641)
IEEE Trans Neural Netw Learn Syst. 2024 Apr;35(4):5027-5038. (PMID: 35737602)
PLoS One. 2019 Mar 27;14(3):e0214365. (PMID: 30917171)
JAMA. 2020 Nov 17;324(19):1957-1969. (PMID: 33201204)
JAMA. 2018 Sep 18;320(11):1101-1102. (PMID: 30178065)
JAMA. 2018 Sep 18;320(11):1192-1193. (PMID: 30422287)
Nutr Diabetes. 2022 May 27;12(1):27. (PMID: 35624098)
JMIR Form Res. 2020 May 5;4(5):e14064. (PMID: 32369025)
Comput Methods Programs Biomed. 2021 Nov;211:106433. (PMID: 34614452)
PLoS Comput Biol. 2018 Apr 26;14(4):e1006106. (PMID: 29698408)
J Epidemiol Community Health. 2018 Mar;72(3):260-266. (PMID: 29335255)
Lancet Digit Health. 2019 Oct;1(6):e271-e297. (PMID: 33323251)
Sci Rep. 2022 Jan 27;12(1):1534. (PMID: 35087165)
Environ Health Perspect. 2014 Oct;122(10):A268-75. (PMID: 25272250)
Am J Epidemiol. 2023 Nov 3;192(11):1904-1916. (PMID: 37139570)
J Am Med Inform Assoc. 2020 Mar 1;27(3):457-470. (PMID: 31794016)
JAMA. 2017 Dec 12;318(22):2199-2210. (PMID: 29234806)
Epidemiology. 2023 Mar 1;34(2):206-215. (PMID: 36722803)
G3 (Bethesda). 2020 Nov 5;10(11):4177-4190. (PMID: 32934019)
JAMA Intern Med. 2019 Mar 1;179(3):293-294. (PMID: 30556825)
Nat Protoc. 2021 Jun;16(6):2765-2787. (PMID: 33953393)
Nat Commun. 2020 Aug 13;11(1):4054. (PMID: 32792511)
Plant Genome. 2021 Nov;14(3):e20118. (PMID: 34323393)
BMC Public Health. 2020 Feb 12;20(1):215. (PMID: 32050938)
Nat Med. 2019 Jan;25(1):24-29. (PMID: 30617335)
NEJM Evid. 2022 May;1(5):. (PMID: 36875289)
JAMA Netw Open. 2018 Aug 3;1(4):e181535. (PMID: 30646134)
JAMA. 2018 Sep 18;320(11):1107-1108. (PMID: 30178025)
Proc Natl Acad Sci U S A. 2017 Jul 18;114(29):7571-7576. (PMID: 28684401)
NPJ Digit Med. 2018 May 8;1:18. (PMID: 31304302)
JAMA Netw Open. 2020 Sep 1;3(9):e2017135. (PMID: 32970157)
Int J Epidemiol. 2021 Jan 23;49(6):1770-1773. (PMID: 33485274)
Grant Information:
K01 TW011782 United States TW FIC NIH HHS; K01TW011782 Fogarty International Center of the National Institutes of Health; R00LM012868 United States LM NLM NIH HHS; R01 LM012849 United States LM NLM NIH HHS; R01MD016037 United States MD NIMHD NIH HHS; R00 LM012868 United States LM NLM NIH HHS; R01 MD016037 United States MD NIMHD NIH HHS
Contributed Indexing:
Keywords: artificial intelligence; computer vision; data analysis; data collection; deep learning; epidemiologic methods; neural networks
Entry Date(s):
Date Created: 20240716 Date Completed: 20250422 Latest Revision: 20250718
Update Code:
20250718
PubMed Central ID:
PMC11815488
DOI:
10.1093/aje/kwae215
PMID:
39013794
Database:
MEDLINE

Weitere Informationen

Deep learning is a subfield of artificial intelligence and machine learning, based mostly on neural networks and often combined with attention algorithms, that has been used to detect and identify objects in text, audio, images, and video. Serghiou and Rough (Am J Epidemiol. 2023;192(11):1904-1916) presented a primer for epidemiologists on deep learning models. These models provide substantial opportunities for epidemiologists to expand and amplify their research in both data collection and analyses by increasing the geographic reach of studies, including more research subjects, and working with large or high-dimensional data. The tools for implementing deep learning methods are not as straightforward or ubiquitous for epidemiologists as traditional regression methods found in standard statistical software, but there are exciting opportunities for interdisciplinary collaboration with deep learning experts, just as epidemiologists have with statisticians, health care providers, urban planners, and other professionals. Despite the novelty of these methods, epidemiologic principles of assessing bias, study design, interpretation, and others still apply when implementing deep learning methods or assessing the findings of studies that have used them.
(© The Author(s) 2024. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)