Performance of different machine learning algorithms in identifying undiagnosed diabetes based on nonlaboratory parameters and the influence of muscle strength: A cross‐sectional study
Journal of Diabetes Investigation · 2024-06 · 15 (6) · 743-750
DOI: 10.1111/jdi.14166 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Diabetes Investigation, online erschienen am 04.03.2024. Verfasst von Ying Xu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Endocrine Metabolism, The First People's Hospital of Yunnan Province, The Affiliated Hospital of Kunming University of Science and Tech…. Hauptthemen laut MEDLINE: Machine Learning, Muscle Strength, Diabetes Mellitus. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Themen: Künstliche Intelligenz in der Pflege, Diabetes mellitus
Abstract (Originalsprache)
Aims/Introduction Machine learning algorithms based on the artificial neural network (ANN), support vector machine, naive Bayesian or logistic regression model are commonly used to identify diabetes. This study investigated which approach performed the best and whether muscle strength provided any incremental benefit in identifying undiagnosed diabetes in Chinese adults.
Methods
This cross‐sectional study enrolled 4,482 eligible participants from eight provinces in China, who were randomly divided into the training dataset ( n = 3,586) and the testing dataset ( n = 896). Muscle strength was assessed by handgrip strength and the number of chair stands in the 30‐s chair stand test. An oral glucose tolerance test was used to ascertain undiagnosed diabetes. The areas under the curve (AUCs) were calculated accordingly and compared with each other.
Results
Of the included participants, 233 had newly diagnosed diabetes. All the four machine learning algorithms, which were developed based on nonlaboratory parameters, showed acceptable discriminative ability in identifying undiagnosed diabetes (all AUCs >0.70), with the ANN approach performing the best (AUC 0.806). Adding handgrip strength or the 30‐s chair stand test to this approach did not increase the AUC further ( P = 0.39 and 0.26, respectively). Furthermore, compared with the New Chinese Diabetes Risk Score, the ANN approach showed a larger AUC in identifying undiagnosed diabetes ( P comparison < 0.01), regardless of the addition of handgrip strength or the 30‐s chair stand test.
Conclusions
The ANN approach performed the best in identifying undiagnosed diabetes in Chinese adults; however, the addition of muscle strength might not improve its efficacy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Endocrine Metabolism, The First People's Hospital of Yunnan Province, The Affiliated Hospital of Kunming University of Science and Technology, Kunming, China.
- Department of General Practice, School of Medicine, Institute of Diabetes, Zhongda Hospital, Southeast University, Nanjing, China.
- School of Mathematics and Statistics, Yunnan University, Kunming, China.
- Department of Endocrinology, School of Medicine, Institute of Diabetes, Zhongda Hospital, Southeast University, Nanjing, China.
ORCID-Profile: Ying Xu
Zitieren
APA
Xu, Y., Qiu, S., Ye, J., Chen, D., Wang, D., Zhou, X., & Sun, Z. (2024). Performance of different machine learning algorithms in identifying undiagnosed diabetes based on nonlaboratory parameters and the influence of muscle strength: A cross‐sectional study. Journal of Diabetes Investigation, 15(6), 743-750. https://doi.org/10.1111/jdi.14166
Vancouver
Xu Y, Qiu S, Ye J, Chen D, Wang D, Zhou X, et al. Performance of different machine learning algorithms in identifying undiagnosed diabetes based on nonlaboratory parameters and the influence of muscle strength: A cross‐sectional study. Journal of Diabetes Investigation. 2024;15(6):743-750. doi:10.1111/jdi.14166
BibTeX
@article{Xu2024,
author = {Xu, Ying and Qiu, Shanhu and Ye, Jinli and Chen, Dan and Wang, Donglei and Zhou, Xiaoying and Sun, Zilin},
title = {Performance of different machine learning algorithms in identifying undiagnosed diabetes based on nonlaboratory parameters and the influence of muscle strength: A cross‐sectional study},
journal = {Journal of Diabetes Investigation},
year = {2024},
volume = {15},
number = {6},
pages = {743--750},
doi = {10.1111/jdi.14166}
}
EUVIMED