Bayesian generalized linear models for meta-analysis of diagnostic tests

With the recognition of the importance of evidence-based medicine, there is an emerging need for methods to systematically synthesize available data. Specifically, methods to provide accurate estimates of test characteristics for diagnostic tests are needed to help physicians make better clinical decisions. To provide more flexible approaches for meta-analysis of diagnostic tests, we developed three Bayesian generalized linear models. Two of these models, a bivariate normal and a binomial model, analyzed pairs of sensitivity and specificity values while incorporating the correlation between these two outcome variables. Noninformative independent uniform priors were used for the variance of sensitivity, specificity and correlation. We also applied an inverse Wishart prior to check the sensitivity of the results. The third model was a multinomial model where the test results were modeled as multinomial random variables. All three models can include specific imaging techniques as covariates in order to compare performance. Vague normal priors were assigned to the coefficients of the covariates. The computations were carried out using the 'Bayesian inference using Gibbs sampling' implementation of Markov chain Monte Carlo techniques. We investigated the properties of the three proposed models through extensive simulation studies. We also applied these models to a previously published meta-analysis dataset on cervical cancer as well as to an unpublished melanoma dataset. In general, our findings show that the point estimates of sensitivity and specificity were consistent among Bayesian and frequentist bivariate normal and binomial models. However, in the simulation studies, the estimates of the correlation coefficient from Bayesian bivariate models are not as good as those obtained from frequentist estimation regardless of which prior distribution was used for the covariance matrix. The Bayesian multinomial model consistently underestimated the sensitivity and specificity regardless of the sample size and correlation coefficient. In conclusion, the Bayesian bivariate binomial model provides the most flexible framework for future applications because of its following strengths: (1) it facilitates direct comparison between different tests; (2) it captures the variability in both sensitivity and specificity simultaneously as well as the intercorrelation between the two; and (3) it can be directly applied to sparse data without ad hoc correction. ^

A simulation study using the hybrid statistic and the meta-analysis t-test for data with matched and unmatched subjects in the interim analysis of clinical trials

An interim analysis is usually applied in later phase II or phase III trials to find convincing evidence of a significant treatment difference that may lead to trial termination at an earlier point than planned at the beginning. This can result in the saving of patient resources and shortening of drug development and approval time. In addition, ethics and economics are also the reasons to stop a trial earlier. In clinical trials of eyes, ears, knees, arms, kidneys, lungs, and other clustered treatments, data may include distribution-free random variables with matched and unmatched subjects in one study. It is important to properly include both subjects in the interim and the final analyses so that the maximum efficiency of statistical and clinical inferences can be obtained at different stages of the trials. So far, no publication has applied a statistical method for distribution-free data with matched and unmatched subjects in the interim analysis of clinical trials. In this simulation study, the hybrid statistic was used to estimate the empirical powers and the empirical type I errors among the simulated datasets with different sample sizes, different effect sizes, different correlation coefficients for matched pairs, and different data distributions, respectively, in the interim and final analysis with 4 different group sequential methods. Empirical powers and empirical type I errors were also compared to those estimated by using the meta-analysis t-test among the same simulated datasets. Results from this simulation study show that, compared to the meta-analysis t-test commonly used for data with normally distributed observations, the hybrid statistic has a greater power for data observed from normally, log-normally, and multinomially distributed random variables with matched and unmatched subjects and with outliers. Powers rose with the increase in sample size, effect size, and correlation coefficient for the matched pairs. In addition, lower type I errors were observed estimated by using the hybrid statistic, which indicates that this test is also conservative for data with outliers in the interim analysis of clinical trials.^

Evaluating the disparity of female breast cancer mortality among racial groups - a spatiotemporal analysis

Background The literature suggests that the distribution of female breast cancer mortality demonstrates spatial concentration. There remains a lack of studies on how the mortality burden may impact racial groups across space and over time. The present study evaluated the geographic variations in breast cancer mortality in Texas females according to three predominant racial groups (non-Hispanic White, Black, and Hispanic females) over a twelve-year period. It sought to clarify whether the spatiotemporal trend might place an uneven burden on particular racial groups, and whether the excess trend has persisted into the current decade. Methods The Spatial Scan Statistic was employed to examine the geographic excess of breast cancer mortality by race in Texas counties between 1990 and 2001. The statistic was conducted with a scan window of a maximum of 90% of the study period and a spatial cluster size of 50% of the population at risk. The next scan was conducted with a purely spatial option to verify whether the excess mortality persisted further. Spatial queries were performed to locate the regions of excess mortality affecting multiple racial groups. Results The first scan identified 4 regions with breast cancer mortality excess in both non-Hispanic White and Hispanic female populations. The most likely excess mortality with a relative risk of 1.12 (p = 0.001) occurred between 1990 and 1996 for non-Hispanic Whites, including 42 Texas counties along Gulf Coast and Central Texas. For Hispanics, West Texas with a relative risk of 1.18 was the most probable region of excess mortality (p = 0.001). Results of the second scan were identical to the first. This suggested that the excess mortality might not persist to the present decade. Spatial queries found that 3 counties in Southeast and 9 counties in Central Texas had excess mortality involving multiple racial groups. Conclusion Spatiotemporal variations in breast cancer mortality affected racial groups at varying levels. There was neither evidence of hot-spot clusters nor persistent spatiotemporal trends of excess mortality into the present decade. Non-Hispanic Whites in the Gulf Coast and Hispanics in West Texas carried the highest burden of mortality, as evidenced by spatial concentration and temporal persistence.

Whence a healthy mind: Correlation of physical fitness and academic performance among schoolchildren

Background. Public schools are a key forum in the fight for child health because of the opportunities they present for physical activity and fitness surveillance. However, because schools are evaluated and funded on the basis of standardized academic performance rather than physical activity, empirical research evaluating the connections between fitness and academic performance is needed to justify curriculum allocations to physical activity. ^ Methods. Analyses were based on a convenience sample of 315,092 individually-matched standardized academic (TAKS™) and fitness (FITNESSGRAM®) test records collected by 13 Texas school districts under state mandates. We categorized each fitness result in quintiles by age and gender and used a mixed effects regression model to compare the academic performance of the top and bottom fitness groups for each fitness test and grade level combination. ^ Results. All fitness variables except BMI showed significant, positive associations with academic performance after sociodemographic covariate adjustments, with effect sizes ranging from 0.07 (95% CI: 0.05,0.08) in girls trunklift-TAKS reading to 0.34 (0.32,0.35) in boys cardiovascular-TAKS math. Cardiovascular fitness showed the largest inter-quintile difference in TAKS score (32-75 points), followed by curl-ups. After an additional adjustment for BMI and curl-ups, cardiovascular associations peaked in 8th-9 th grades (maximum inter-quintile difference 142 TAKS points; effect size 0.75 (0.69,0.82) for 8th grade girls math) and showed dose-response characteristics across quintiles (p<0.001 for both genders and outcomes). BMI analysis demonstrated limited, non-linear association with academic performance after adjustment for sociodemographic, cardiovascular fitness and curl-up variables. Low-BMI Hispanic high school boys showed significantly lower TAKS scores than the moderate (but not high) BMI group. High-BMI non-Hispanic white high school girls showed significantly lower scores than the moderate (but not low) BMI group. ^ Conclusions. In this study, fitness was strongly and significantly related to academic performance. Cardiovascular fitness showed a distinct dose-response association with academic performance independent of other sociodemographic and fitness variables. The association peaked in late middle to early high school. The independent association of BMI to academic performance was only found in two sub-groups and was non-linear, with both low and high BMI posing risk relative to moderate BMI but not to each other. In light of our findings, we recommend that policymakers consider PE mandates in middle-high school and require linkage of academic and fitness records to facilitate longitudinal surveillance. School administrators should consider increasing PE time in pursuit of higher academic test scores, and PE practitioners should emphasize cardiovascular fitness over BMI reduction.^

Correlation of blood type with thrombosis in pancreatic cancer patients

Objective: The study aimed to identify the risk factors involved in initiating thromboembolism (TE) in pancreatic cancer (PC) patients, with focus on ABO blood type. ^ Methods and Patients: There were 35.7% confirmed cases of TE and 64.3% cases remained free of TE (n=687). There were 12.7% only Pulmonary embolism (PE), 9% only Deep vein thrombosis (DVT), 53.5% only other sites, 3.3% combined PE and DVT, 8.6% combined PE and other sites, 9.8% combined DVT and other sites, and 3.3% all three combined cases. ^ Results: The risk factors for thrombosis identified by multivariate logistic regression were: history of previous anti-thrombotic treatment, tumor site in pancreatic body or tail, large tumor size, maximum glucose category more than 126 and 200 mg/dL. ^ The factors with worse overall survival by multivariate Cox regression and Kaplan Meier analyses were: locally advanced or metastatic stage, worsening performance status, high CA 19-9 levels, and HbA1C levels more than 6 %, at diagnosis. ^ There were 29.1% and 39.1% of the patients with thrombosis in the O and non-O blood type groups respectively. Both Non-O blood type (P=0.02) and the A, B and AB blood types (P= 0.007) were associated with thrombosis as compared to O type. The odds of thrombosis were nearly half in O blood type patients as compared to non-O blood type [OR-0.54 (95% C.I.- 0.37-0.79), P<0.001]. ^ Conclusion: A better understanding of the TE and PC relationship and involved risk factors may provide insights on tumor biology and patient response to prophylactic anticoagulation therapy.^