Combinational risk factors of metabolic syndrome identified by fuzzy neural network analysis of health-check data

Abstract

BackgroundLifestyle-related diseases represented by metabolic syndrome develop as results of complex interaction. By using health check-up data from two large studies collected during a long-term follow-up, we searched for risk factors associated with the development of metabolic syndrome.MethodsIn our original study, we selected 77 case subjects who developed metabolic syndrome during the follow-up and 152 healthy control subjects who were free of lifestyle-related risk components from among 1803 Japanese male employees. In a replication study, we selected 2196 case subjects and 2196 healthy control subjects from among 31343 other Japanese male employees. By means of a bioinformatics approach using a fuzzy neural network (FNN), we searched any significant combinations that are associated with MetS. To ensure that the risk combination selected by FNN analysis was statistically reliable, we performed logistic regression analysis including adjustment.ResultsWe selected a combination of an elevated level of γ-glutamyltranspeptidase (γ-GTP) and an elevated white blood cell (WBC) count as the most significant combination of risk factors for the development of metabolic syndrome. The FNN also identified the same tendency in a replication study. The clinical characteristics of γ-GTP level and WBC count were statistically significant even after adjustment, confirming that the results obtained from the fuzzy neural network are reasonable. Correlation ratio showed that an elevated level of γ-GTP is associated with habitual drinking of alcohol and a high WBC count is associated with habitual smoking.ConclusionsThis result obtained by fuzzy neural network analysis of health check-up data from large long-term studies can be useful in providing a personalized novel diagnostic and therapeutic method involving the γ-GTP level and the WBC count.

Automatic Diagnosis Metabolic Syndrome via a $$k-$$ Nearest Neighbour Classifier

“…Computer-aided techniques that employ machine learning methods to learn to identify patients with MetS can thus facilitate a more reliable diagnosis of the metabolic syndrome. Existing approaches for the automatic identification of MetS proposed different machine learning methods including Decision Trees [16], Artificial Neural Networks [19] and Tree Regression [20]. Jose M. Bioucas-Dias and Antonio Plaza [1] proposed an algorithm that uses Multinomial Logistic Regression (MLR) to find the posterior class probability which is aided by a semi supervised segmentation [2], [3].…”

Diagnosing Metabolic Syndrome Using Genetically Optimised Bayesian ARTMAP

“…However, body fat mass, waist-to-height ratio, and waist-to-hip ratio included as part of the risk factors for the prediction of MetS in their work are not clinically recognized as risk factors of MetS. In another study, Fuzzy ANN was used to search for significant combinations of risk factors connected with MetS [55]. Furthermore, the association between the traditional MetS risk factors, human nuclear receptors responsible for regulating fatty acid storage and glucose metabolism, and environmental factors was investigated using Back-error Propagation ANN (BPANN) [64].…”

Pruning Fuzzy Neural Network Applied to the Construction of Expert Systems to Aid in the Diagnosis of the Treatment of Cryotherapy and Immunotherapy

“…Already in health, models have highlights in different performances. As examples, work has been done towards arrhythmia detection [68], mass lesion detection [69], risk factors of metabolic syndrome [70], ovarian cancer diagnosis [71]. Hybrid models found in applications and problems in other fields, such as [72][73][74][75].…”