Machine learning-based assessment of the built environment on prevalence and severity risks of acne

H Yang; X Cui; H Wang; M Helbich; C Yin; X Chen; J Wen; C Ren; L Xiang; A Xu; Q Ju; T Zhu; J Chen; S Tian; M Dijst; L He

doi:10.1016/j.crsus.2024.100235

Machine learning-based assessment of the built environment on prevalence and severity risks of acne

H Yang^*, X Cui , H Wang, M Helbich, C Yin, X Chen, J Wen, C Ren, L Xiang, A Xu, Q Ju, T Zhu, J Chen, S Tian, M Dijst, L He

^*Corresponding author for this work

Urban Accessibility and Social Inclusion

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Understanding the determinants of acne prevalence and severity is crucial for effective prevention and management of this dermatological condition. While urban interventions have long-lasting, far-reaching, and costly implications for health promotion, the associations between built environments (BEs) and acne need further investigation. To address this gap, our study utilizes a nationwide cross-sectional sample of 23,488 undergraduates from 90 campuses in China to conduct a comprehensive analysis. We examined the combined and specific contributions of BEs in relation to other domains of acne-related factors in acne development. By employing the optimal random forest model, our findings reveal that BEs collectively ranked as the second-largest contributors to both the overall prevalence of acne among all participants and the severity of acne in the affected individuals. Moreover, our analysis identifies curvilinear associations between acne and most BEs, underscoring the importance of incorporating BE considerations into the prevention, diagnosis, and management of acne.

Original language	English
Article number	100235
Number of pages	13
Journal	Cell Reports Sustainability
Volume	1
Issue number	10
DOIs	https://doi.org/10.1016/j.crsus.2024.100235
Publication status	Published - 25 Oct 2024

Bibliographical note

Publisher Copyright:
© 2024 The Author(s)

Funding

This project received support from the Program for Innovative Research Team from the Ministry of Education of China (grant no. IRT17-R49), the National Key Research and Development Program of China (grant no. 2023YFC2509000), and National Natural Science Foundation of China Joint Fund Project (grant no. U22A20310), which contributed to the study design of epidemiological survey and the collection of individual information, including biological and medical attributes, demographic and socioeconomic characteristics, lifestyle factors, and the specific locations of the surveyed campuses. The Key Program of National Natural Science Foundation of China (no. 42330510) and the National Natural Science Foundation of China (no. 42101184) provided support for the study design and collection of neighborhood information encompassing built environments and natural environments. We extend our sincere gratitude to the over 100 dermatologists who participated in the acne diagnosis process and the collection of individuals\u2019 information.

Funders	Funder number
National Key Research and Development Program of China	2023YFC2509000
Ministry of Education of the People's Republic of China	IRT17-R49
National Natural Science Foundation of China	42330510, 42101184
National Natural Science Foundation of China Joint Fund Project	U22A20310

Keywords

acne vulgaris
built environment
college student
machine learning
prevalence risk
severity

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.crsus.2024.100235Licence: CC BY-NC-ND

1-s2.0-S2949790624003768-mainFinal published version, 4.86 MBLicence: CC BY-NC-ND

Cite this

@article{70066ab7c44a48d5b569284510e03be8,

title = "Machine learning-based assessment of the built environment on prevalence and severity risks of acne",

abstract = "Understanding the determinants of acne prevalence and severity is crucial for effective prevention and management of this dermatological condition. While urban interventions have long-lasting, far-reaching, and costly implications for health promotion, the associations between built environments (BEs) and acne need further investigation. To address this gap, our study utilizes a nationwide cross-sectional sample of 23,488 undergraduates from 90 campuses in China to conduct a comprehensive analysis. We examined the combined and specific contributions of BEs in relation to other domains of acne-related factors in acne development. By employing the optimal random forest model, our findings reveal that BEs collectively ranked as the second-largest contributors to both the overall prevalence of acne among all participants and the severity of acne in the affected individuals. Moreover, our analysis identifies curvilinear associations between acne and most BEs, underscoring the importance of incorporating BE considerations into the prevention, diagnosis, and management of acne.",

keywords = "acne vulgaris, built environment, college student, machine learning, prevalence risk, severity",

author = "H Yang and X Cui and H Wang and M Helbich and C Yin and X Chen and J Wen and C Ren and L Xiang and A Xu and Q Ju and T Zhu and J Chen and S Tian and M Dijst and L He",

note = "Publisher Copyright: {\textcopyright} 2024 The Author(s)",

year = "2024",

month = oct,

day = "25",

doi = "10.1016/j.crsus.2024.100235",

language = "English",

volume = "1",

journal = "Cell Reports Sustainability",

issn = "2949-7906",

number = "10",

}

TY - JOUR

T1 - Machine learning-based assessment of the built environment on prevalence and severity risks of acne

AU - Yang, H

AU - Cui , X

AU - Wang, H

AU - Helbich, M

AU - Yin, C

AU - Chen, X

AU - Wen, J

AU - Ren, C

AU - Xiang, L

AU - Xu, A

AU - Ju, Q

AU - Zhu, T

AU - Chen, J

AU - Tian, S

AU - Dijst, M

AU - He, L

PY - 2024/10/25

Y1 - 2024/10/25

N2 - Understanding the determinants of acne prevalence and severity is crucial for effective prevention and management of this dermatological condition. While urban interventions have long-lasting, far-reaching, and costly implications for health promotion, the associations between built environments (BEs) and acne need further investigation. To address this gap, our study utilizes a nationwide cross-sectional sample of 23,488 undergraduates from 90 campuses in China to conduct a comprehensive analysis. We examined the combined and specific contributions of BEs in relation to other domains of acne-related factors in acne development. By employing the optimal random forest model, our findings reveal that BEs collectively ranked as the second-largest contributors to both the overall prevalence of acne among all participants and the severity of acne in the affected individuals. Moreover, our analysis identifies curvilinear associations between acne and most BEs, underscoring the importance of incorporating BE considerations into the prevention, diagnosis, and management of acne.

AB - Understanding the determinants of acne prevalence and severity is crucial for effective prevention and management of this dermatological condition. While urban interventions have long-lasting, far-reaching, and costly implications for health promotion, the associations between built environments (BEs) and acne need further investigation. To address this gap, our study utilizes a nationwide cross-sectional sample of 23,488 undergraduates from 90 campuses in China to conduct a comprehensive analysis. We examined the combined and specific contributions of BEs in relation to other domains of acne-related factors in acne development. By employing the optimal random forest model, our findings reveal that BEs collectively ranked as the second-largest contributors to both the overall prevalence of acne among all participants and the severity of acne in the affected individuals. Moreover, our analysis identifies curvilinear associations between acne and most BEs, underscoring the importance of incorporating BE considerations into the prevention, diagnosis, and management of acne.

KW - acne vulgaris

KW - built environment

KW - college student

KW - machine learning

KW - prevalence risk

KW - severity

UR - https://www.scopus.com/pages/publications/85207325096

U2 - 10.1016/j.crsus.2024.100235

DO - 10.1016/j.crsus.2024.100235

M3 - Article

SN - 2949-7906

VL - 1

JO - Cell Reports Sustainability

JF - Cell Reports Sustainability

IS - 10

M1 - 100235

ER -

Machine learning-based assessment of the built environment on prevalence and severity risks of acne

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this