How Are BMI, Nutrition, and Physical Exercise Related? An Application of Ordinal Logistic Regression.

BACKGROUND: This paper performs a detailed ordinal logistic regression study in an evaluation of a survey at a university in South Texas, USA. We show that, for categorical data in our case, ordinal logistic regression works well. METHODS: The survey was designed according to the guidelines in diet and lifestyle from the American Heart Association and the United States Department of Agriculture and was sent out to all registered students at Texas A&M International University in Laredo, Texas. Data analysis included 601 students' results from the survey. Data analysis was conducted in Rstudio. RESULTS: The results showed that, compared with students who do not have enough whole grain food and exercise, those who have enough in both tend to have normal BMIs. As age increases, BMI tends to be out of the normal range. CONCLUSIONS: Because BMI in this research has three categories, applying an ordinal logistic regression model to describe the relationship between an ordered categorical response variable and more explanatory variables has several advantages compared with other models, such as the linear regression model.

Prevalence of Fatty Liver among Children under Multiple Machine Learning Models.

OBJECTIVES: To analyze the possible factors causing fatty liver in children based on ultrasound data of children in south Texas, and to establish machine learning models of fatty liver in children to provide ideas for the prevention and treatment of fatty liver in children. METHODS: The binary classification model of fatty liver problem in obese children in Texas was established under the multiple model. First, we selected important features using the CatBoost algorithm. Second, the best parameters of the algorithm were selected on the training set and the validation set by using the grid search method, and all six models were tested on the test set. The six models then were compared by area under the curve value, precision, accuracy, recall rate, and F1 score in a model evaluation. Then, two algorithms, logic regression and CatBoost, were selected to establish prediction models of fatty liver disease in children. RESULTS: We selected body mass index, height, liver size, kidney volume, glomerular filtration rate, and liver diameter as the features used in the machine learning model. The prediction models we chose showed that children with higher body mass index at the same age tended to have a greater probability of fatty liver. CONCLUSIONS: Based on the analysis of the results of the two prediction models established by logistic regression and CatBoost, we determined that the mean probability of fatty liver in severely obese children was between 74.47% and 92.22%, 73.45% and 85.41% in obese children, and slightly higher in boys than in girls, with a mean difference of 3.00% to 3.95%.

Meteorological indicators for Amblyomma cajennense and population dynamics in the Tamaulipan Biotic Province in Texas.

We studied the population dynamics of free-living ticks in the Tamaulipan Biotic Province in south Texas from March, 2005 to November, 2008. We collected 70,873 ticks using carbon dioxide traps. Amblyomma cajennense represented 93.6% of the ticks identified. A. cajennense is distributed from northern Argentina to south Texas in the Tamaulipan Biotic Province. Emergence of larval A. cajennense ticks was observed two to five weeks after significant rain events (p<0.0001) and had a strong negative correlation with temperature (p<0.0001). More larvae were observed under humid conditions (p<0.05). Fewer larvae were observed during windy and warmer conditions (p<0.05). This observation indicates high sensitivity of larvae to desiccating conditions. Peaks in nymphal activity were observed after peaks of larval emergence. Activity of nymphs was negatively correlated with temperature (p<0.05). Adult activity was negatively correlated with humidity (p<0.05) and negatively correlated with total rain from three to six weeks prior to observation (p<0.05). Adult A. cajennense are particularly tolerant to drier conditions relative to other closely related ticks. Adult female activity was positively correlated with temperature (p<0.05). Peaks in rain activity and a summer behavioral diapause appear to be the dominant factors controlling emergence of larvae, and by extension, the life cycle of A. cajennense in the Tamaulipan Biotic Province.