Browsing by Author "Li, Linlin"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Bayesian Inference on Ratios Subject to Differentially Private Noise
    (2021) Li, Linlin

    Data privacy is a long-term issue for data sharing, especially in health-related data. Agencies need to find a balance between data utility and the privacy of the respondents. Differential privacy provides a solution by ensuring that the statistic of interest is basically the same, regardless of whether an individual is included or excluded. Due to this differentially private perturbation, analysts need to infer the true value from the released value. In this thesis, I propose Bayesian inference methods to infer the posterior distribution of ratios of two counts given the released values. I illustrate the Bayesian inference methods under several scenarios and with two commonly used differentially private mechanisms and prior distributions. The Bayesian inference method not only provides a point estimate but also provides posterior intervals. Simulation studies show that the Bayesian inference method can generate accurate inferences with close to nominal coverage rates, and have small values of bias and mean squared error.

  • Thumbnail Image
    ItemOpen Access
    Cardiometabolic Risk Factors among Severely Obese Children and Adolescents in the United States, 1999-2012.
    (Childhood obesity (Print), 2016-02) Li, Linlin; Pérez, Adriana; Wu, Li-Tzy; Ranjit, Nalini; Brown, Henry S; Kelder, Steven H

    Background

    Severely obese children and adolescents are at high risk of suffering obesity-related comorbidities. This article is to examine the dose-response relationship between weight status and cardiometabolic risk factors among US adolescents.

    Methods

    Youths aged 6-19 years participating in the National Health and Nutrition Examination Surveys (NHANES) 1999-2012 were included (N = 20,905). Severe obesity was defined as BMI ≥120% of 95th percentile of gender-specific BMI-for-age or BMI ≥35 kg/m(2). Obesity-related cardiometabolic risk factors included blood pressure (BP), high-density lipoprotein cholesterol (HDL), low-density lipoprotein cholesterol (LDL), total cholesterol (TC), triglycerides, and fasting glucose (FG). Weighted multiple logistic regression was used to assess whether severe obesity significantly changed the odds of having cardiometabolic risk factors.

    Results

    The prevalence of high BP, high TC, low HDL, high triglycerides, high LDL, and high FG among severely obese adolescents was 9.9%, 16.5%, 40.0%, 30.0%, 13.0%, and 26.8%, respectively. Severely obese adolescents had at least twice the odds compared to normal weight adolescents of presenting high BP (OR = 5.3, 95% CI: 3.8-7.3); high TC (OR = 2.3, 95% CI: 1.8-3.0); low HDL (OR = 7.3, 95% CI: 6.1-8.8); high triglycerides (OR = 4.5, 95% CI: 3.4-5.9); high LDL (OR = 2.3, 95% CI: 1.5-3.5); and high FG (OR = 2.7, 95% CI: 1.8-4.0). Significant differences were also found between severely obese status and moderately obese status in the odds of having high BP (OR = 1.8, 95% CI: 1.7-2.2) and low HDL (OR = 1.9, 95% CI: 1.6-2.3).

    Conclusion

    Adolescents classified as severe status exhibit higher odds of having cardiometabolic risk factors compared to those with normal weight and moderately obese weight status.
  • Thumbnail Image
    ItemOpen Access
    Substance use after bariatric surgery: A review.
    (Journal of psychiatric research, 2016-05) Li, Linlin; Wu, Li-Tzy
    Prevalence of obesity has increased dramatically. Obese individuals may undergo bariatric surgery to lose excessive body fat and mitigate obesity-related comorbidities. However, bariatric patients are particularly vulnerable to substance use problems. We conducted a review to examine the prevalence change and factors associated with substance use and determine the association between substance use and health status after weight loss among bariatric patients.We searched peer-reviewed articles published between January 1990 and January 2015 in several databases (PubMed, PsycINFO, Cochrane Library, Google Scholar) using different keywords combinations. Studies that focused on pre-surgery substance use only or without reported effect measurements were excluded.Overall, 40 studies were included in the review. Preoperative history of substance use was a reliable correlate of postoperative substance use. The prevalence of postoperative alcohol use was higher among patients with preoperative history of alcohol use than those without. Postoperative prevalence of alcohol use ranged from 7.6% to 11.8%. No significant prevalence change in cigarette smoking from pre-to postoperative period was observed. Time effect was not observed on smoking or drug use prevalence, while an increase in alcohol consumption was inconsistent across studies. The proportion of new-onset substance users among bariatric patients after surgery ranged from 34.3% to 89.5%.Substance use is associated with poor health among bariatric patients. Preoperative assessment and postoperative follow-up should include interventions to reduce relapse among users and prevent substance use initiation.