Parent and child physical activity and sleep in determining overweight and obese children’s behaviors

Revision as of 21:30, 12 January 2020 by Praveen (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Title: Relationships between parent and child physical activity and sleep in determining overweight and obese children’s behaviors and identifying risk factors.

Mentor: Dr. Paula E. Papanek

Approach: Develop and use appropriate analytic tools on large dataset of daily minutes of physical activity and sleep to determine relationships between parents and overweight children’s physical activity and sleep behaviors to predict risk of obesity. Students will gain experience with all aspects of data science – data cleaning, data wrangling, feature engineering, data visualization, implementing and evaluating machine learning models for accuracy, precision and recall. Over 40 pairs of child/parent dyads with multiple weeks of data over 3 year study. Data was collected via fitbit and captured for research purposes via fitabase. Summary: The United States has seen a significant obesity epidemic with minority populations particularly at risk for obesity and the complications and comorbidities associated with overweight including heart disease and stroke, hypertension and diabetes. Components of these diseases are now presenting in children as young as 8-10 years old. Fit4Yes is an intervention targeting and helping families to learn to cook and eat healthier meals including the addition of fresh fruit and vegetables, and to engage daily in physical activity, increasing moderate to vigorous activity in the children and supporting families to be active together. Very few studies have looked at the problem of relationships between parents and children’s activity and sleep behaviors as related issues as risk factors for childhood obesity.

The goal of this study is to utilize data collected over the study to identify key relationships such as total physical activity per day, mins of light, moderate and vigorous activity and total minutes of sedentary behaviors per day and patterns of sleep as they relate with their child’s behaviors.

Student Research Activities: The REU fellows will perform the following major tasks:

  • Perform a systematic literature review in the area of obesity epidemic with an emphasis on children’s behavior and risk factors.
  • Analyze the fitbit data that was collected by the mentor to identify key variables such as total physical activity per day, minutes of light, moderate and vigorous activity.
  • Implement and evaluate machine learning models to identify factors leading to obese children behavior.

Student Background: Students need to have basic computing knowledge and introductory programming skills in Python or R and understanding of statistics.