Return to search

Methodological and Clinical Issues in the Analysis of Data from HIV Cardiovascular Research: Validity of Ultrasound Methods, Impact of Anti-Retroviral Therapy on Atherosclerosis, and Imputation of Missing Values

<p>Background and Objectives: There are some methodological and clinical challenges in conducting HIV related research. A subset of such challenges include: non-availability of a universally accepted method to quantify subclinical atherosclerosis in HIV patients; ultrasound imaging techniques aimed at quantifying atheroma burden and endothelial dysfunction have been proposed, however there is no universally accepted ultrasound protocol; conflicting inferences on the nature ofthe relationship between anti-retroviral therapy (ART) and cardiovascular disease (CVD) due to small sample sizes; and missing data from longitudinal studies and ultrasound data. The objective of this thesis is to investigate selected aspects of the afore-mentioned issues, and to provide recommendations for future research.</p> <p>Methods:</p> <p>Project 1: We compared the construct validity of carotid artery intima media thickness (IMT) and brachial artery flow mediated vasodilation (FMD); two non-invasive ultrasound techniques used in measuring the extent of sub-clinical atherosclerosis. Baseline and one-year follow-up data were obtained for a sample of 257 subjects aged 35 years or older, recruited into an ongoing study of cardiovascular risk in HIV. An ultrasound technique having statistically significantly strong association with known CVD risk factors was adjudged to have good construct validity. The relationship between baseline IMT or FMD and known CVD risk factors was studied using multiple regression analysis. We modelled the relationship between progression of IMT or FMD and risk factors using fixed-effects models.</p> <p>Project 2: To more precisely investigate the relationship between ARTs and IMT (as a surrogate for CVD), we pooled cross-sectional baseline, record-level data for 1,032 patients recruited across three cohort studies in Canada, France and USA in a metaanalysis. We investigated the association between exposure to ARTs and CVD using hierarchical linear models.</p> <p>Project 3: On missing data, we studied the impact ofan inclusive strategy for conducting multiple imputation (MI) on the efficiency ofregression parameter estimates using Monte-Carlo simulation. In an inclusive strategy, all final analysis variables are included in a multivariate normal model to impute plausible values for missing data. This issue is not well studied for longitudinal HIV data.</p> <p>Results and Conclusions:</p> <p>Project 1: Baseline IMT was significantly associated with age (p < 0.001), male gender (p = 0.034), current smoking status (p < 0.001), systolic blood pressure (p < 0.001) and total:HDL cholesterol ratio (p = 0.004). IMT progression was significantly associated with age (p < 0.001), male gender (p = 0.0051) and current smoking status (p = 0.011). Neither extent nor progression ofFMD was significantly associated with any of the examined vascular risk factors. IMT was adjudged to have better construct validity than FMD.</p> <p>Project 2: Similar to some (but not all) previous studies, AR Ts do not appear to lead to CVD independent of traditional risk factors. However, exploratory analysis of two-way interactions suggests statistically significant moderating effects between ARTs and traditional risk factors. These results warrant further investigation into potential
moderating effects between ARTs and known CVD risk factors.</p> <p>Project 3: In conducting MI, simulation results show that a strategy that includes all final analysis model variables in the imputation model provides the least combined variability and bias for final regression estimates. This is important to note because final regression estimates are used in making clinically relevant inferences in practice.</p> / Thesis / Doctor of Philosophy (PhD)

Identiferoai:union.ndltd.org:mcmaster.ca/oai:macsphere.mcmaster.ca:11375/17386
Date11 1900
CreatorsOdueyungbo, Adefowope
ContributorsThabane, Lehana, None
Source SetsMcMaster University
LanguageEnglish
Detected LanguageEnglish

Page generated in 0.0017 seconds