Risk prediction model of metabolic syndrome in perimenopausal women based on machine learning.

INTRODUCTION: Metabolic syndrome (MetS) is considered to be an important parameter of cardio-metabolic health and contributing to the development of atherosclerosis, type 2 diabetes. The incidence of MetS significantly increases in postmenopausal women, therefore, the perimenopausal period is considered a critical phase for prevention. We aimed to use four machine learning methods to predict whether perimenopausal women will develop MetS within 2 years. METHODS: Women aged 45-55 years who underwent 2 consecutive years of physical examinations in Ninth Clinical College of Peking University between January 2021 and December 2022 were included. We extracted 26 features from physical examinations, and used backward selection method to select top 10 features with the largest area under the receiver operating characteristic curve (AUC). Extreme gradient boosting (XGBoost), Random forest (RF), Multilayer perceptron (MLP) and Logistic regression (LR) were used to establish the model. Those performance were measured by AUC, accuracy, precision, recall and F1 score. SHapley Additive exPlanation (SHAP) value was used to identify risk factors affecting perimenopausal MetS. RESULTS: A total of 8700 women had physical examination records, and 2,254 women finally met the inclusion criteria. For predicting MetS events, RF and XGBoost had the highest AUC (0.96, 0.95, respectively). XGBoost has the highest F1 value (F1 = 0.77), followed by RF, LR and MLP. SHAP value suggested that the top 5 variables affecting MetS in this study were Waist circumference, Fasting blood glucose, High-density lipoprotein cholesterol, Triglycerides and Diastolic blood pressure, respectively. CONCLUSION: We've developed a targeted MetS risk prediction model for perimenopausal women, using health examination data. This model enables early identification of high MetS risk in this group, offering significant benefits for individual health management and wider socio-economic health initiatives.

Effects of black cohosh and estrogen on the hypothalamic nuclei of ovariectomized rats at different temperatures.

ETHNOPHARMACOLOGICAL RELEVANCE: Cimicifuga racemosa (L.) Nutt. (CR), known as black cohosh, has been used in Europe as a medicinal plant for more than a century and its roots have been widely used for the treatment of menopausal symptoms. Remifemin, the main ingredient in liquid or tablet medications prepared from isopropyl alcohol extracts of black cohosh rhizome, has also been evaluated in clinical studies. OBJECTIVES: To observe changes in the expression of the c-Fos protein in the hypothalamic nuclei of four groups of rats-sham-operated group (SHAM), ovariectomized (OVX) group, ovariectomized group treated with estrogen(OVX+E), and ovariectomized group treated with the isopropanol extract of Cimicifuga racemosa (OVX+ICR)-and to investigate the mechanisms of black cohosh and estrogen that take place in the hypothalamic nuclei of ovariectomized rats. METHODS: Fifty rats were assigned to each of the four groups and placed in incubators at 4 °C, 10 °C, 25 °C, 33 °C, or 38 °C for 2 h. They were then anesthetized, and their brains were removed after heart perfusion. c-Fos expression in the hypothalamic nuclei was evaluated using immunohistochemical methods. RESULTS: In the median preoptic nucleus (MnPO), ventromedial preoptic nucleus (VMPO), and suprachiasmatic nucleus (SCh) of the SHAM group, in the anterior hypothalamic area (AH) and supraoptic nucleus (SO) of all four groups, and in the paraventricular nucleus (PVN) of the SHAM, OVX and OVX+E groups, the c-Fos-positive cell densities all changed in a similar manner: the cell density decreased when the temperature was less than 25 °C and the density increased when the temperature was greater than 25 °C, demonstrating a V-type curve. The c-Fos density was lowest at 25°C. The other nuclei demonstrated irregular changes. The positive cell densities in the MnPO, AH, and PVN of the SHAM, OVX+E, and OVX+ICR groups were greater than the densities measured in the OVX group at all temperatures, except 25 °C. Positive cell densities in the SHAM, OVX+E, and OVX+ICR groups were greater than the densities measured in the OVX groups in the MPA at 25 °C, in the VMPO at 4 °C, 33 °C, and 38 °C, in the SO at 4 °C, 10 °C, and 38 °C, and in the SCh at 33 °C. CONCLUSION: Regardless of the temperature, positive cell densities were lower in the MnPO, MPA, VMPO, AH, SCh, SO, and PVN of the OVX groups in comparison with the densities measured in the same sites in the SHAM group. Following the administration of black cohosh and estrogen, the positive cell densities in the OVX groups increased and became closer to, or exceeded, those measured in the SHAM group, suggesting that both drugs may act on the hypothalamic nuclei and have therapeutic effects on menopausal symptoms.