A Data-Driven Assessment of the Metabolic Syndrome Criteria for Adult Health Management in Taiwan.

Int J Environ Res Public Health

Department of Information Management, Cheng Shiu University, Kaohsiung City 83347, Taiwan.

Published: December 2018

According to the modified Adult Treatment Panel III, five indices are used to define metabolic syndrome (MetS): waist circumference (WC), high blood pressure, fasting glucose, triglycerides (TG), and high-density lipoprotein cholesterol. Our work evaluates the importance of these indices. In addition, we attempted to identify whether trends and patterns existed among young, middle-aged, and older people. Following the analysis, a decision tree algorithm was used to analyze the importance of the five criteria for MetS because the algorithm in question selects the attribute with the highest information gain as the split node. The most important indices are located on the top of the tree, indicating that these indices can effectively distinguish data in a binary tree and the importance of this criterion. That is, the decision tree algorithm specifies the priority of the influence factors. The decision tree algorithm examined four of the five indices because one was excluded. Moreover, the tree structures differed among the three age groups. For example, the first key index for middle-aged and older people was TG whereas for younger people it was WC. Furthermore, the order of the second to fourth indices differed among the groups. Because the key index was identified for each age group, researchers and practitioners could provide different health care strategies for individuals based on age. High-risk middle-aged and healthy older people maintained low values of TG, which might be the most crucial index. When a person can avoid the first and second indices provided by the decision tree, they are at lower risk of MetS. Therefore, this paper provides a data-driven guideline for MetS prevention.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6339104PMC
http://dx.doi.org/10.3390/ijerph16010092DOI Listing

Publication Analysis

Top Keywords

decision tree
16
older people
12
tree algorithm
12
metabolic syndrome
8
middle-aged older
8
indices
7
tree
7
data-driven assessment
4
assessment metabolic
4
syndrome criteria
4

Similar Publications

Background And Objective: Accurate prediction of perioperative major adverse cardiovascular events (MACEs) is crucial, as it not only aids clinicians in comprehensively assessing patients' surgical risks and tailoring personalized surgical and perioperative management plans, but also for information-based shared decision-making with patients and efficient allocation of medical resources. This study developed and validated a machine learning (ML) model using accessible preoperative clinical data to predict perioperative MACEs in stable coronary artery disease (SCAD) patients undergoing noncardiac surgery (NCS).

Methods: We collected data from 9171 adult SCAD patients who underwent NCS and extracted 64 preoperative variables.

View Article and Find Full Text PDF

Background: Active screening programs and early detection of asymptomatic carriers are effective in preventing carbapenem-resistant Acinetobacter baumannii (CRAB) dissemination in healthcare facilities. This study aims to identify risk factors associated with CRAB carriage among patients upon admission to an acute care hospital.

Methods: A case-case-control study was conducted at an acute care hospital.

View Article and Find Full Text PDF

Background: Men who have sex with men (MSM) globally face a high risk of HIV infection. Previous studies indicate that customized short message service (SMS) interventions could reduce high-risk behaviors that associated with HIV transmission. This study aims to evaluate the health and economic impacts of such interventions among MSM in China.

View Article and Find Full Text PDF

Alternative assessment of machine learning to polynomial regression in response surface methodology for predicting decolorization efficiency in textile wastewater treatment.

Chemosphere

December 2024

Department of Energy Systems Research, Ajou University, Suwon, 16499, Republic of Korea; Department of Environmental and Safety Engineering, Ajou University, Suwon, 16499, Republic of Korea. Electronic address:

This study investigated the potential of machine learning (ML) as a substitute for polynomial regression in conventional response surface methodology (RSM) for decolorizing textile wastewater via a UV/HO process. While polynomial regression offers limited adaptability, ML models provide superior flexibility in capturing nonlinear responses but are prone to overfitting, particularly with constrained RSM datasets. In this study, we evaluated decision tree (DT), random forest (RF), multilayer perceptron (MLP), and extreme gradient boosting (XGBoost) models with respect to a quadratic regression model.

View Article and Find Full Text PDF

In the contemporary context of a burgeoning energy crisis, the accurate and dependable prediction of Solar Radiation (SR) has emerged as an indispensable component within thermal systems to facilitate renewable energy generation. Machine Learning (ML) models have gained widespread recognition for their precision and computational efficiency in addressing SR prediction challenges. Consequently, this paper introduces an innovative SR prediction model, denoted as the Cheetah Optimizer-Random Forest (CO-RF) model.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!