Background Hyperglycemia is rising globally and its associated complications impose heavy health and economic burden on the countries. Developing effective survey-based screening tools for hyperglycemia using reliable surveillance data, such as the WHO STEPs surveys, would be of great importance in early detection and/or prevention of hyperglycemia, especially in low or middle-income regions. Methods In this study, data from the nationwide 2016 STEPs study in Iran were used to identify socioeconomic, lifestyle, and metabolic factors associated with hyperglycemia. Furthermore, the ability of five commonly used machine learning algorithms (random forest; gradient boosting; support vector machine; logistic regression; artificial neural network) in the prediction of hyperglycemia on STEPs dataset were compared via tenfold cross validation in terms of specificity, sensitivity, and the area under the receiver operating characteristic curve. Results A total of 17,705 individuals were included in this study, of those 29.624% (n = 5245) had (undiagnosed) hyperglycemia. Multivariate logistic regression analysis showed that older age (for the elderly group: OR = 5.096; for the middle-aged group: OR = 2.784), high BMI status (morbidly obese: OR = 3.465; obese: OR = 1.992), having hypertension (OR = 1.647), consuming fish more than twice per week (OR = 1.496), and abdominal obesity (OR = 1.464) were the five most important risk factors for hyperglycemia. Furthermore, all the five hyperglycemia prediction models achieved AUC around 0.70, and logistic regression (specificity = 70.22%; sensitivity = 70.2%) and random forest (specificity = 70.75%; sensitivity = 69.78%) had the optimal performance. Conclusions This study shows that it is possible to develop survey-based screening tools for early detection of hyperglycemia using data from nationwide surveys, such as WHO STEPs surveys, and machine learning techniques, such as random forest and logistic regression, without using blood tests. Such screening tools can potentially improve hyperglycemia control, especially in low or middle-income countries.
It is a well-known result of Auslander and Reiten that contravariant finiteness of the class P fin ∞ (of finitely generated modules of finite projective dimension) over an Artin algebra is a sufficient condition for validity of finitistic dimension conjectures. Motivated by the fact that finitistic dimensions of an algebra can alternatively be computed by Gorenstein projective dimension, in this work we examine the Gorenstein counterpart of Auslander-Reiten condition, namely contravariant finiteness of the class GP fin ∞ (of finitely generated modules of finite Gorenstein projective dimension), and its relation to validity of finitistic dimension conjectures. It is proved that contravariant finiteness of the class GP fin ∞ implies validity of the second finitistic dimension conjecture over left artinian rings. In the more special setting of Artin algebras, however, it is proved that the Auslander-Reiten sufficient condition and its Gorenstein counterpart are virtually equivalent in the sense that contravariant finiteness of the class GP fin ∞ implies contravariant finiteness of the class P fin ∞ over any Artin algebra, and the converse holds for Artin algebras over which the class GP fin 0 (of finitely generated Gorenstein projective modules) is contravariantly finite.
The theory of finitely generated relative (co)tilting modules has been established in the 1980s by Auslander and Solberg, and infinitely generated relative tilting modules have recently been studied by many authors in the context of Gorenstein homological algebra. In this work, we build on the theory of infinitely generated Gorenstein tilting modules by developing "Gorenstein tilting approximations" and employing these approximations to study Gorenstein tilting classes and their associated relative cotorsion pairs. As applications of our results, we discuss the problem of existence of complements to partial Gorenstein tilting modules as well as some connections between Gorenstein tilting modules and finitistic dimension conjectures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.