Utilizing Machine Learning Techniques to Predict the Efficacy of Aerobic Exercise Intervention on Young Hypertensive Patients Based on Cardiopulmonary Exercise Testing.

Recently, the incidence of hypertension has significantly increased among young adults. While aerobic exercise intervention (AEI) has long been recognized as an effective treatment, individual differences in response to AEI can seriously influence clinicians' decisions. In particular, only a few studies have been conducted to predict the efficacy of AEI on lowering blood pressure (BP) in young hypertensive patients. As such, this paper aims to explore the implications of various cardiopulmonary metabolic indicators in the field by mining patients' cardiopulmonary exercise testing (CPET) data before making treatment plans. CPET data are collected "breath by breath" by using an oxygenation analyzer attached to a mask and then divided into four phases: resting, warm-up, exercise, and recovery. To mitigate the effects of redundant information and noise in the CPET data, a sparse representation classifier based on analytic dictionary learning was designed to accurately predict the individual responsiveness to AEI. Importantly, the experimental results showed that the model presented herein performed better than the baseline method based on BP change and traditional machine learning models. Furthermore, the data from the exercise phase were found to produce the best predictions compared with the data from other phases. This study paves the way towards the customization of personalized aerobic exercise programs for young hypertensive patients.

[Study on the relationship between obesity and lipid metabolism in children and adolescent in yinchuan].

OBJECTIVE: Discuss the relationship between obesity and hyperlipidemia in children and adolescent. METHODS: According to the BMI classification criteria of overweight and obesity screening in Chinese school-age child and adolescent, and the gender and nationality, age ( ≤1 year-old), we performed the 1:1:1 match of the obesity, overweight and normal, there were 321 subjects in each group. Using "national unified measurement and method of youth physical fitness research", we did physical measurements on the subjects, and collected fasting venous blood to do biochemical detections, including blood glucose (FPG), triglyceride (TG), total cholesterol (TC), high density lipoprotein cholesterol (HDL-C ) , low density lipoprotein cholesterol (LDL-C). RESULTS: The differences of weight, waist circumference, hip circumference, SBP, DBP, TG, TC, LDL-C were statistically significant among the three groups (all P <0. 01 or 0. 05), the obese group was significantly higher than the normal group. With the increase of BMI, the abnormal rate of TG and TC were all upward trend, the obese group was significantly higher than the normal group, the differences were statistically significant( all P <0. 01 or 0. 05). After controlling factors of gender, nationality and age, TG was positively correlated with BMI, waist circumference, hip circumference and waist-high ratio (WHtR) (all P <0.01 or 0.05), HDL-C was negatively correlated with and BMI, waist circumference, hip circumference and WHtR (all P <0. 01 or 0. 05). After adjusting gender, nationality and age, with the increase of BMI, the risk for hyperlipidemia increased significantly, the risk of the obese group for hyperlipidemia was 1. 593 times than the normal group (95% CI 1. 144 -2. 220), it was statistically significance (P <0. 01). The level of TC, LDL-C and HDL-C in Muslim children and adolescents were higher than in Han., the level of TG were lower than in Han, but the differences were not statistically significant( All P > 0. 05) ). The abnormal rates of TC, LDL-C in Muslim children and adolescents were higher than in Han, the differences were statistically significant. CONCLUSIONS: The blood lipids levels of obese children and adolescents were obviously higher than that of normal one, especially TG and TC; obesity significantly increased the risk for hyperlipidemia in children and adolescents; the abnormal rates of TC, LDL-C in Muslim children and adolescents were significantly higher than in Han; Whether it is associated with ethnic genetic, remains to be further research.