Biomedical subjects

Heejung Bang

Publications and source records attributed to Heejung Bang.

11 recordsLinked to original sources

PubMed2005

Medical cost analysis: application to colorectal cancer data from the SEER Medicare database.

Incompleteness is a key feature of most survival data. Numerous well established statistical methodologies and algorithms exist for analyzing life or failure time data. However, induced censorship invalidates the use of those standard analytic tools for some survival-type data such as medical costs. In this paper, some valid methods currently available for analyzing censored medical cost data are reviewed. Some cautionary findings under different assumptions are envisioned through application to medical costs from colorectal cancer patients. Cost analysis should be suitably planned and carefully interpreted under various meaningful scenarios even with judiciously selected statistical methods. This approach would be greatly helpful to policy makers who seek to prioritize health care expenditures and to assess the elements of resource use.

Aged↗

PubMed2005

Sample size calculation for multiple testing in microarray data analysis.

Microarray technology is rapidly emerging for genome-wide screening of differentially expressed genes between clinical subtypes or different conditions of human diseases. Traditional statistical testing approaches, such as the two-sample t-test or Wilcoxon test, are frequently used for evaluating statistical significance of informative expressions but require adjustment for large-scale multiplicity. Due to its simplicity, Bonferroni adjustment has been widely used to circumvent this problem. It is well known, however, that the standard Bonferroni test is often very conservative. In the present paper, we compare three multiple testing procedures in the microarray context: the original Bonferroni method, a Bonferroni-type improved single-step method and a step-down method. The latter two methods are based on nonparametric resampling, by which the null distribution can be derived with the dependency structure among gene expressions preserved and the family-wise error rate accurately controlled at the desired level. We also present a sample size calculation method for designing microarray studies. Through simulations and data analyses, we find that the proposed methods for testing and sample size calculation are computationally fast and control error and power precisely.

Computer Simulation↗

PubMed2005

Identifying individuals at high risk for diabetes: The Atherosclerosis Risk in Communities study.

OBJECTIVE: To develop and evaluate clinical rules to predict risk for diabetes in middle-aged adults. RESEARCH DESIGN AND METHODS: The Atherosclerosis Risk in Communities is a cohort study conducted from 1987-1989 to 1996-1998. We studied 7,915 participants 45-64 years of age, free of diabetes at baseline, and ascertained 1,292 incident cases of diabetes by clinical diagnosis or oral glucose tolerance testing. RESULTS: We derived risk functions to predict diabetes using logistic regression in a random half of the sample. Rules based on these risk functions were evaluated in the other half. A risk function based on waist, height, hypertension, blood pressure, family history of diabetes, ethnicity, and age was performed similarly to one based on fasting glucose (area under the receiver-operating characteristic curve [AUC] 0.71 and 0.74, respectively; P = 0.2). Risk functions composed of the clinical variables plus fasting glucose (AUC 0.78) and additionally including triglycerides and HDL cholesterol (AUC 0.80) performed better (P < 0.001). Evaluation of scores based on the metabolic syndrome as defined by the National Cholesterol Education Program or with slight variations showed AUCs of 0.75 and 0.78, respectively. Rules based on all these approaches, while identifying 20-56% of the sample as screen positive, achieved sensitivities of 40-87% and specificities of 50-86%. CONCLUSIONS: Rules derived from clinical information, alone or combined with simple laboratory measures, can characterize degrees of diabetes risk in middle-aged adults, permitting preventive actions of appropriate intensity. Rules based on the metabolic syndrome are reasonable alternatives to rules derived from risk functions.

Arteriosclerosis↗

PubMed2004

Lipoprotein-associated phospholipase A2, high-sensitivity C-reactive protein, and risk for incident coronary heart disease in middle-aged men and women in the Atherosclerosis Risk in Communities (ARIC) study.

BACKGROUND: Measuring C-reactive protein (CRP) has been recommended to identify patients at high risk for coronary heart disease (CHD) with low LDL cholesterol (LDL-C). Lipoprotein-associated phospholipase A2 (Lp-PLA2) is a proinflammatory enzyme associated primarily with LDL. METHODS AND RESULTS: In a prospective, case cohort study in 12 819 apparently healthy middle-aged men and women in the Atherosclerosis Risk in Communities study, the relation between Lp-PLA2, CRP, traditional risk factors, and risk for CHD events over a period of approximately 6 years was examined in a proportional hazards model, stratified by LDL-C. Lp-PLA2 and CRP levels were higher in the 608 cases than the 740 noncases. Both Lp-PLA2 and CRP were associated with incident CHD after adjustment for age, sex, and race with a hazard ratio of 1.78 for the highest tertile of Lp-PLA2 and 2.53 for the highest category of CRP versus the lowest categories. Lp-PLA2 correlated positively with LDL-C (r=0.36) and negatively with HDL-C (r=-0.33) but not with CRP (r=-0.05). In a model adjusted for traditional risk factors including LDL-C, the association of Lp-PLA2 with CHD was attenuated and not statistically significant. For individuals with LDL-C below the median (130 mg/dL), Lp-PLA2 and CRP were both significantly and independently associated with CHD in fully adjusted models. For individuals with LDL-C <130 mg/dL, those with both Lp-PLA2 and CRP levels in the highest tertile were at the greatest risk for a CHD event. CONCLUSIONS: Lp-PLA2 and CRP may be complementary in identifying individuals at high CHD risk who have low LDL-C.

1-Alkyl-2-acetylglycerophosphocholine Esterase↗

PubMed2004

Assessment of blinding in clinical trials.

Success of blinding is a fundamental issue in many clinical trials. The validity of a trial may be questioned if this important assumption is violated. Although thousands of ostensibly double-blind trials are conducted annually and investigators acknowledge the importance of blinding, attempts to measure the effectiveness of blinding are rarely discussed. Several published papers proposed ways to evaluate the success of blinding, but none of the methods are commonly used or regarded as standard. This paper investigates a new approach to assess the success of blinding in clinical trials. The blinding index proposed is scaled to an interval of -1 to 1, 1 being complete lack of blinding, 0 being consistent with perfect blinding and -1 indicating opposite guessing which may be related to unblinding. It has the ability to detect a relatively low degree of blinding, response bias and different behaviors in two arms. The proposed method is applied to a clinical trial of cholesterol-lowering medication in a group of elderly people.

Aged↗

PubMed2004

Estimating treatment effects in studies of perinatal transmission of HIV.

Fetal loss often precludes the ascertainment of infection status in studies of perinatal transmission of HIV. The standard analysis based on liveborn babies can result in biased estimation and invalid inference in the presence of fetal death. This paper focuses on the problem of estimating treatment effects for mother-to-child transmission when infection status is unknown for some babies. Minimal data structures for identifiability of parameters are given. Methods using full likelihood and the inverse probability of selection-weighted estimators are suggested. Simulation studies are used to show that these estimators perform well in finite samples. Methods are applied to the data from a clinical trial in Dar es Salaam, Tanzania. To validly estimate the treatment effect using likelihood methods, investigators should make sure that the design includes a mini-study among uninfected mothers and that efforts are made to ascertain the infection status of as many babies lost as possible. The inverse probability weighting methods need precise estimation of the probability of observing infection status. We can further apply our methodology to the study of other vertically transmissible infections which are potentially fatal pre- and perinatally.

Female↗

PubMed2004

Adiponectin and the development of type 2 diabetes: the atherosclerosis risk in communities study.

Adipocyte-derived secretory proteins have been increasingly linked to diabetes. To investigate whether adiponectin, a major adipocyte secretory protein, predicts diabetes, we conducted a case-cohort study representing the approximately 9-year experience of the 10,275 middle-aged, U.S. African-American and white participants of the Atherosclerosis Risk in Communities (ARIC) study. Adiponectin was measured on stored plasma of 581 incident diabetes case subjects and 572 noncase subjects. Overall hazard ratios (95% CIs) for developing diabetes, for those in the second, third, and fourth (versus the first) quartile of adiponectin were 0.57 (0.41-0.78), 0.39 (0.27-0.56), and 0.18 (0.11-0.27), respectively, after adjustment for age, sex, ethnicity, study center, parental history of diabetes, and hypertension and 0.72 (0.48-1.09), 0.67 (0.43-1.04), and 0.58 (0.34-0.99), respectively, after additional adjustment for BMI, waist-to-hip ratio, fasting glucose, insulin, and a score composed of six inflammation markers. The association was of similar magnitude in men and women and in whites and African Americans, but was absent in smokers and in those with a greater inflammation score (interaction P < 0.01 for each). In conclusion, in this community-based sample of U.S. adults, higher adiponectin levels were associated with a lower incidence of diabetes.

Adiponectin↗

PubMed2002

Transmission of HIV-1 through breastfeeding among women in Dar es Salaam, Tanzania.

BACKGROUND: Transmission of HIV-1 through breastfeeding is a major problem, although its timing is not well characterized. METHODS: The authors examined the timing and correlates of HIV-1 transmission through breastfeeding among 1078 HIV-infected pregnant women from Dar es Salaam, Tanzania enrolled in a trial to examine the effect of vitamin A and other vitamin supplements on mother-to-child transmission of HIV-1 and other health outcomes. Cumulative incidence was measured among children of women not randomized to vitamin A (n = 312), given the higher risk of infection observed among those in the vitamin A arm. For analyses of correlates, data from all children not infected by age 6 weeks were used (p = 659). RESULTS: Mean duration of breastfeeding was 20.3 months (SD = 4.4 months; median = 20.5 months). Thirty-seven infections were observed during 4372 child-months of follow-up evaluation, or 10.2 cases per 100 child-years. Infection risk by age 4 months was 3.8% (95% confidence interval [CI], 1.6%-6.1%) and increased to 17.9% (95% CI, 11.2%-24.5%) by age 24 months. In a multivariate proportional hazards model, high maternal viral load (p =.0001), low CD4 cell count (p =.004), and high maternal erythrocyte sedimentation rate (ESR; p=.004) were significant predictors of transmission of HIV-1 through breastfeeding. Mothers who had breast lesions during pregnancy were 2.00 times more likely to transmit the virus during breastfeeding than mothers without these lesions (95% CI, 1.29-3.08; p=.002). CONCLUSIONS: The rate of breastfeeding transmission of HIV-1 is high, and early weaning is likely to be associated with reduced transmission. Antiretroviral drugs given to HIV-infected mothers are likely to reduce the risk of breastfeeding transmission. In their absence, interventions that enhance immune reconstitution, such as micronutrient supplements, may be beneficial against transmission. Methods to prevent and treat nipple cracks and mastitis may also be important.

Breast Feeding↗

PubMed2002

Randomized trial of vitamin supplements in relation to transmission of HIV-1 through breastfeeding and early child mortality.

BACKGROUND: HIV-1 transmission through breastfeeding is a global problem and has been associated with poor maternal micronutrient status. METHODS: A total of 1078 HIV-infected pregnant women from Tanzania were randomly assigned to vitamin A or multivitamins excluding A from approximately 20 weeks' gestation and throughout lactation. RESULTS: Multivitamins excluding A had no effect on the total risk of HIV-1 transmission (RR 1.04, 95% CI 0.82-1.32, P= 0.76). Vitamin A increased the risk of transmission (RR 1.38, 95% CI 1.09-1.76, P = 0.009). Multivitamins were associated with non-statistically significant reductions in transmission through breastfeeding, and mortality by 24 months among those alive and not infected at 6 weeks. Multivitamins significantly reduced breastfeeding transmission in infants of mothers with low baseline lymphocyte counts (RR 0.37; 95% CI 0.16-0.85, P = 0.02) compared with infants of mothers with higher counts (RR 0.99, 95% CI 0.68-1.45, P = 0.97; -for-interaction 0.03). Multivitamins also protected against transmission among mothers with a high erythrocyte sedimentation rate (P-for-interaction 0.06), low hemoglobin (P-for-interaction 0.06), and low birthweight babies (P-for-interaction 0.04). Multivitamins reduced death and prolonged HIV-free survival significantly among children born to women with low maternal immunological or nutritional status. Vitamin A alone increased breastfeeding transmission but had no effect on mortality by 24 months. CONCLUSION: Vitamin A increased the risk of HIV-1 transmission. Multivitamin (B, C, and E) supplementation of breastfeeding mothers reduced child mortality and HIV-1 transmission through breastfeeding among immunologically and nutritionally compromised women. The provision of these supplements to HIV-infected lactating women should be considered.

Adult↗

PubMed2002

Correlates of plasma HIV-1 RNA viral load among HIV-1-seropositive women in Dar es Salaam, Tanzania.

This study was conducted to determine the predictors of plasma HIV-1 RNA viral load in HIV-1-positive pregnant women (N = 151) participating in a clinical trial in Tanzania. Viral load was measured at randomization, delivery, and approximately 7 months after delivery. The median viral load was 20,400 copies/mL at baseline, 20,216 copies/mL at delivery, and 19,100 copies/mL 7 months after delivery. The absolute CD4+ lymphocyte count had a strong negative correlation with HIV-1 RNA viral load at baseline (r = -.38), time of delivery (r = -.36), and 7 months after delivery (r = -.53). The association between CD4+ lymphocyte count and HIV-1 RNA viral load was modified by the per capita daily food expenditure in the household, although the difference in viral load became small as the food expenditure in the household increased and was marginally significant at the 75th percentile of the per capita food expenditure. The presence of malaria parasites at baseline was associated with an approximate 116% higher viral load at the three evaluation points (p =.007). Although the long-term effects of malaria on viral load are unknown, prevention of malaria among people living with HIV-1 should be given the highest priority.

Adult↗

PubMed2002

Median regression with censored cost data.

Because of the skewness of the distribution of medical costs, we consider modeling the median as well as other quantiles when establishing regression relationships to covariates. In many applications, the medical cost data are also right censored. In this article, we propose semiparametric procedures for estimating the parameters in median regression models based on weighted estimating equations when censoring is present. Numerical studies are conducted to show that our estimators perform well with small samples and the resulting inference is reliable in circumstances of practical importance. The methods are applied to a dataset for medical costs of patients with colorectal cancer.

Biometry↗