Résumé
Background@#To analyze the factors associated with women's vasomotor symptoms (VMS) using machine learning. @*Methods@#Data on 3,298 women, aged 40–80 years, who attended their general health check-up from January 2010 to December 2012 were obtained from Korea University Anam Hospital in Seoul, Korea. Five machine learning methods were applied and compared for the prediction of VMS, measured by the Menopause Rating Scale. Variable importance, the effect of a variable on model performance, was used for identifying the major factors associated with VMS. @*Results@#In terms of the mean squared error, the random forest (0.9326) was much better than linear regression (12.4856) and artificial neural networks with one, two, and three hidden layers (1.5576, 1.5184, and 1.5833, respectively). Based on the variable importance from the random forest, the most important factors associated with VMS were age, menopause age, thyroid-stimulating hormone, and monocyte, triglyceride, gamma glutamyl transferase, blood urea nitrogen, cancer antigen 19-9, C-reactive protein, and low-density lipoprotein cholesterol levels. Indeed, the following variables were ranked within the top 20 in terms of variable importance: cancer antigen 125, total cholesterol, insulin, free thyroxine, forced vital capacity, alanine aminotransferase, forced expired volume in 1 second, height, homeostatic model assessment for insulin resistance, and carcinoembryonic antigen. @*Conclusion@#Machine learning provides an invaluable decision support system for the prediction of VMS. For managing VMS, comprehensive consideration is needed regarding thyroid function, lipid profile, liver function, inflammation markers, insulin resistance, monocyte count, cancer antigens, and lung function.
Résumé
Background@#To analyze the factors associated with women's vasomotor symptoms (VMS) using machine learning. @*Methods@#Data on 3,298 women, aged 40–80 years, who attended their general health check-up from January 2010 to December 2012 were obtained from Korea University Anam Hospital in Seoul, Korea. Five machine learning methods were applied and compared for the prediction of VMS, measured by the Menopause Rating Scale. Variable importance, the effect of a variable on model performance, was used for identifying the major factors associated with VMS. @*Results@#In terms of the mean squared error, the random forest (0.9326) was much better than linear regression (12.4856) and artificial neural networks with one, two, and three hidden layers (1.5576, 1.5184, and 1.5833, respectively). Based on the variable importance from the random forest, the most important factors associated with VMS were age, menopause age, thyroid-stimulating hormone, and monocyte, triglyceride, gamma glutamyl transferase, blood urea nitrogen, cancer antigen 19-9, C-reactive protein, and low-density lipoprotein cholesterol levels. Indeed, the following variables were ranked within the top 20 in terms of variable importance: cancer antigen 125, total cholesterol, insulin, free thyroxine, forced vital capacity, alanine aminotransferase, forced expired volume in 1 second, height, homeostatic model assessment for insulin resistance, and carcinoembryonic antigen. @*Conclusion@#Machine learning provides an invaluable decision support system for the prediction of VMS. For managing VMS, comprehensive consideration is needed regarding thyroid function, lipid profile, liver function, inflammation markers, insulin resistance, monocyte count, cancer antigens, and lung function.
Résumé
Lysimachia foenum-graecum has been used as an oriental medicine with anti-inflammatory effect. The anti-obesity effect of L. foenum-graecum extract (LFE) was first discovered in our screening of natural product extract library against adipogenesis. To characterize its anti-obesity effects and to evaluate its potential as an anti-obesity drug, we performed various obesity-related experiments in vitro and in vivo. In adipogenesis assay, LFE blocked the differentiation of 3T3-L1 preadipocyte in a dose-dependent manner with an IC50 of 2.5 microg/ml. In addition, LFE suppressed the expression of lipogenic genes, while increasing the expression of lipolytic genes in vitro at 10 microg/ml and in vivo at 100 mg/kg/day. The anti-adipogenic and anti-lipogenic effect of LFE seems to be mediated by the inhibition of PPARgamma and C/EBPalpha expression as shown in in vitro and in vivo, and the suppression of PPARgamma activity in vitro. Moreover, LFE stimulated fatty acid oxidation in an AMPK-dependent manner. In high-fat diet (HFD)-induced obese mice (n = 8/group), oral administration of LFE at 30, 100, and 300 mg/kg/day decreased total body weight gain significantly in all doses tested. No difference in food intake was observed between vehicle- and LFE-treated HFD mice. The weight of white adipose tissues including abdominal subcutaneous, epididymal, and perirenal adipose tissue was reduced markedly in LFE-treated HFD mice in a dose-dependent manner. Treatment of LFE also greatly improved serum levels of obesity-related biomarkers such as glucose, triglycerides, and adipocytokines leptin, adiponectin, and resistin. All together, these results showed anti-obesity effects of LFE on adipogenesis and lipid metabolism in vitro and in vivo and raised a possibility of developing LFE as anti-obesity therapeutics.