Browsing by Subject "childhood obesity"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Attitudes towards Nutrition Education among Pediatricians and Guardians
    (2020-03-06) DeGoey, Madison; Kubascik, Erica; Uzelac, Biljana; Simpson, Steve; Kostrominova, Tatiana
    Childhood obesity rates in the United States are at historic highs. In Lake County, Indiana, the obesity rates of WIC children ages 2-5 years old is 12.1%. While the causes of obesity are well known within the scientific community, there appears to be a disconnect when relaying this information to patients. One cause of this disconnect is the inadequate nutrition education that physicians receive during medical school and residency. A survey found that the average medical school devotes less than 20 hours to nutrition education. Additionally, the biochemical nutrition education that students receive in medical school cannot be easily translated to patient intervention. Since 62% of patients believe that their physicians can help them lose weight, having physicians who do not have adequate education on nutrition leaves patients without the help they need. Our surveys were developed to assess the level of nutrition counseling provided by pediatricians and how patients/guardians prefer to be educated. Our hypothesis is that pediatricians will benefit from further nutrition education in medical school, and that guardians will desire in person instructions in pediatric offices as well as easy and accessible online sources. Two surveys were created, one for physicians and another for parents/guardians of children ages 1-12 years old residing in Lake County. The physician survey contained 15 items that evaluated attitudes toward nutrition and obesity education. Topics included level of nutrition counseling education received in medical school and residency, how much time physicians spend educating patients/parents on nutrition, what nutrition education resources they currently provide, opinion on whose responsibility it is to provide nutrition education, and what approach they think would be best to educate patients and parents. The guardian survey contained 21 items that evaluated dietary behaviors. The dietary behaviors included family dynamics (who typically feds the children, if food is prepared in the home, and how much is spent on food each week) and child eating habits (how many snacks per day, how often the child eats fast food, and how often the child consumes sweetened beverages). The surveys will be utilized for future research, and the results will help determine the approach for educating physicians and guardians. A booklet of healthy recipes was also developed to educate on healthy eating and as a participation benefit. The goal of the booklet was to choose easy, child friendly recipes that the family could cook together. To gain background on nutrition education, we observed the different education methods of local pediatricians and reviewed the literature. Intervention at both the clinical and community levels will be important for improving long-term health outcomes in pediatric patients. The knowledge gained from these surveys will aide in the development of programs needed to provide physicians, guardians,and patients with proper nutrition education.
  • Thumbnail Image
    Item
    Influences of the Home Environment and Daily Routines on Sleep and Obesity
    (Indiana Public Health Training Center, 2014-04-08) Jones, Blake L
    A presentation regarding the research and implementation of interventions for risky youth behavior. Behaviors discussed will include sleep, health, obesity, and home environments.
  • Thumbnail Image
    Item
    Predicting Childhood Obesity Using Machine Learning: Practical Considerations
    (MDPI, 2022) Cheng, Erika R.; Steinhardt, Rai; Ben Miled, Zina; Pediatrics, School of Medicine
    Previous studies demonstrate the feasibility of predicting obesity using various machine learning techniques; however, these studies do not address the limitations of these methods in real-life settings where available data for children may vary. We investigated the medical history required for machine learning models to accurately predict body mass index (BMI) during early childhood. Within a longitudinal dataset of children ages 0–4 years, we developed predictive models based on long short-term memory (LSTM), a recurrent neural network architecture, using history EHR data from 2 to 8 clinical encounters to estimate child BMI. We developed separate, sex-stratified models using 80% of the data for training and 20% for external validation. We evaluated model performance using K-fold cross-validation, mean average error (MAE), and Pearson’s correlation coefficient (R2). Two history encounters and a 4-month prediction yielded a high prediction error and low correlation between predicted and actual BMI (MAE of 1.60 for girls and 1.49 for boys). Model performance improved with additional history encounters; improvement was not significant beyond five history encounters. The combined model outperformed the sex-stratified models, with a MAE = 0.98 (SD 0.03) and R2 = 0.72. Our models show that five history encounters are sufficient to predict BMI prior to age 4 for both boys and girls. Moreover, starting from an initial dataset with more than 269 exposure variables, we were able to identify a limited set of 24 variables that can facilitate BMI prediction in early childhood. Nine of these final variables are collected once, and the remaining 15 need to be updated during each visit.