首页|Peking University Reports Findings in Metabolic Syndrome (Risk prediction model of metabolic syndrome in perimenopausal women based on machine learning)
Peking University Reports Findings in Metabolic Syndrome (Risk prediction model of metabolic syndrome in perimenopausal women based on machine learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Nutritional and Metabo lic Diseases and Conditions - Metabolic Syndrome is the subject of a report. Acc ording to news originating from Beijing, People's Republic of China, by NewsRx c orrespondents, research stated, "Metabolic syndrome (MetS) is considered to be a n important parameter of cardio-metabolic health and contributing to the develop ment of atherosclerosis, type 2 diabetes. The incidence of MetS significantly in creases in postmenopausal women, therefore, the perimenopausal period is conside red a critical phase for prevention."Our news journalists obtained a quote from the research from Peking University, "We aimed to use four machine learning methods to predict whether perimenopausal women will develop MetS within 2 years. Women aged 45-55 years who underwent 2 consecutive years of physical examinations in Ninth Clinical College of Peking U niversity between January 2021 and December 2022 were included. We extracted 26 features from physical examinations, and used backward selection method to selec t top 10 features with the largest area under the receiver operating characteris tic curve (AUC). Extreme gradient boosting (XGBoost), Random forest (RF), Multil ayer perceptron (MLP) and Logistic regression (LR) were used to establish the mo del. Those performance were measured by AUC, accuracy, precision, recall and F1 score. SHapley Additive exPlanation (SHAP) value was used to identify risk facto rs affecting perimenopausal MetS. A total of 8700 women had physical examination records, and 2,254 women finally met the inclusion criteria. For predicting Met S 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 su ggested that the top 5 variables affecting MetS in this study were Waist circumf erence, Fasting blood glucose, Highdensity lipoprotein cholesterol, Triglycerid es and Diastolic blood pressure, respectively. We've developed a targeted MetS r isk prediction model for perimenopausal women, using health examination data."
BeijingPeople's Republic of ChinaAsi aCyborgsDiseases and ConditionsEmerging TechnologiesHealth and MedicineHealthcareMachine LearningMetabolic SyndromeNutritional and Metabolic Dis eases and ConditionsRisk and Prevention
NETL
NSTL
