Publication Date
1-1-2024
Document Type
Article
Publication Title
PeerJ Computer Science
Volume
10
DOI
10.7717/PEERJ-CS.2015
Abstract
One of the limitations of currently-used metabolic syndrome (MetS) risk calculations is that they often depend on sample characteristics. To address this, we introduced a novel sample-independent risk quantification method called ‘triangular areal similarity’ (TAS) that employs three-axis radar charts constructed from five MetS factors in order to assess the similarity between standard diagnostic thresholds and individual patient measurements. The method was evaluated using large datasets of Korean (n = 72, 332) and American (n = 11, 286) demographics further segmented by sex, age, and race. The risk score exhibited a strong positive correlation with the number of abnormal factors and was closely aligned with the current diagnostic paradigm. The proposed score demonstrated high diagnostic accuracy and robustness, surpassing previously reported risk scores. This method demonstrated superior performance and stability when tested on cross-national datasets. This novel sample-independent approach has the potential to enhance the precision of MetS risk prediction.
Funding Number
2021-0-01531
Funding Sponsor
Ministry of Science, ICT and Future Planning
Keywords
Chronic disease, Healthcare, Metabolic syndrome, Risk quantification, Risk score
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Department
Applied Data Science
Recommended Citation
Hyunseok Shin, Simon Shim, and Sejong Oh. "Robust metabolic syndrome risk score based on triangular areal similarity" PeerJ Computer Science (2024). https://doi.org/10.7717/PEERJ-CS.2015
