The annual incidence of knee replacement (KR) procedures in the United States is predicted to reach over 3.5 million by the year 2030. KR is the current definitive treatment for debilitating knee osteoarthritis (KOA). There has yet to be substantial research regarding the impact of KR on participation in community activities and quality of life. The hypotheses evaluated in this dissertation were that persons following KR will have 1) faster gait speed and 2) lower risk of participation restrictions than persons without KR; and 3) a decreased risk of all-cause mortality compared to persons without KR. To address the first two hypotheses, we collected data from subjects with KOA from the Multicenter Osteoarthritis Study and the Osteoarthritis Initiative, large cohorts of older adults with or at risk of KOA at the time of enrollment. In the first study, KR did not have an effect on gait speed overall and among most subgroups, however subjects with a slow gait speed prior to KR did have an 80% increased risk (RR 1.8, 95% CI 1.1, 3.0) of having a healthy gait speed compared with non-KR subjects. In the second study, KR was associated with a small decreased risk of having participation restriction (RR 0.82, 95% CI 0.67, 0.99). The third study used data on patients with KOA from the Clinical Practice Research Datalink, a database of clinical information on > 8 million people throughout the United Kingdom. There was a decrease in the death rate among KOA subjects who had a KR compared to those who did not, and the hazard of death was reduced by over one half in the first five years after the procedure (HR 0.46 (95% CI 0.43, 0.51). For most subjects, this benefit did not extend longer than five years, and patients least likely to have KR (due to clinical and medical presentation) showed an increased hazard of death compared to the non-KR subjects. In conclusion, the results of this dissertation support the hypotheses that KR confers a positive benefit to activity and participation related pursuits which may extend to survival in the short term for some people.

Les scores de propension (PS) sont fréquemment utilisés dans l’ajustement pour des facteurs confondants liés au biais d’indication. Cependant, ils sont limités par le fait qu’ils permettent uniquement l’ajustement pour des facteurs confondants connus et mesurés. Les scores de propension à hautes dimensions (hdPS), une variante des PS, utilisent un algorithme standardisé afin de sélectionner les covariables pour lesquelles ils vont ajuster. L’utilisation de cet algorithme pourrait permettre l’ajustement de tous les types de facteurs confondants. Cette thèse a pour but d’évaluer la performance de l’hdPS vis-à-vis le biais d’indication dans le contexte d’une étude observationnelle examinant l’effet diabétogénique potentiel des statines. Dans un premier temps, nous avons examiné si l’exposition aux statines était associée au risque de diabète. Les résultats de ce premier article suggèrent que l’exposition aux statines est associée avec une augmentation du risque de diabète et que cette relation est dose-dépendante et réversible dans le temps. Suite à l’identification de cette association, nous avons examiné dans un deuxième article si l’hdPS permettait un meilleur ajustement pour le biais d’indication que le PS; cette évaluation fut entreprise grâce à deux approches: 1) en fonction des mesures d’association ajustées et 2) en fonction de la capacité du PS et de l’hdPS à sélectionner des sous-cohortes appariées de patients présentant des caractéristiques similaires vis-à-vis 19 caractéristiques lorsqu’ils sont utilisés comme critère d’appariement. Selon les résultats présentés dans le cadre du deuxième article, nous avons démontré que l’évaluation de la performance en fonction de la première approche était non concluante, mais que l’évaluation en fonction de la deuxième approche favorisait l’hdPS dans son ajustement pour le biais d’indication. Le dernier article de cette thèse a cherché à examiner la performance de l’hdPS lorsque des facteurs confondants connus et mesurés sont masqués à l’algorithme de sélection. Les résultats de ce dernier article indiquent que l’hdPS pourrait, au moins partiellement, ajuster pour des facteurs confondants masqués et qu’il pourrait donc potentiellement ajuster pour des facteurs confondants non mesurés. Ensemble ces résultats indiquent que l’hdPS serait supérieur au PS dans l’ajustement pour le biais d’indication et supportent son utilisation lors de futures études observationnelles basées sur des données médico-administratives. / Propensity scores (PS) are frequently used to adjust for confounders leading to indication bias. However, PS are limited by the fact that they can only adjust for measured and known confounders. High-dimensional propensity scores (hdPS), a specific type of PS, select which variables they adjust for by means of a standardized selection algorithm. Thanks to the use of this selection algorithm, hdPS could potentially adjust for all type of confounders. This thesis aims to evaluate the hdPS’s performance in the adjustment for indication bias in the context of an observational study focussing on the potential diabetogenic effect of statins. The first article’s aim was to identify if the exposure to statins was associated with the risk of diabetes. Results of this article suggest that exposure to statins is associated with an increase in the risk of diabetes and that this association is dose-dependent and reversible in nature. After having identified this association, we examined if the hdPS outperforms the PS in the adjustment for indication bias. Both methods’ performance were compared by means of the obtained adjusted measures of associations and by means of the standardized differences regarding 19 characteristics following the creation of two matched sub-cohorts (each matched on either patients’ PS or patients’ hdPS). Results of this second article identify that the performance of either method could not be differentiated by means of the first approach but that, based on the second approach, the hdPS outperforms the PS in its adjustment for indication bias. The last article aimed to evaluate if the hdPS could adjust for known confounders which were hidden to the selection algorithm. Results of this third article suggest that the hdPS method can adjust for at least some hidden confounders and that it could potentially adjust for some unmeasured confounders. As a whole, this thesis suggests that the hdPS method could be superior to the PS method in its ability to adjust for indication bias and supports its use in future observational studies using medico-administrative databases.

Propensity score analysis has been used to minimize the selection bias in observational studies to identify causal relationships. A propensity score is an estimate of an individual's probability of being placed in a treatment group given a set of covariates. Propensity score analysis aims to use the estimate to create balanced groups, akin to a randomized experiment. This study used Monte Carlo methods to examine the appropriateness of using propensity score methods to achieve balance between groups on observed covariates and reproduce treatment effect estimates in multilevel studies. Specifically, this study examined the extent to which four different propensity score estimation models and three different propensity score conditioning methods produced balanced samples and reproduced the treatment effects with clustered data. One single-level logistic model and three multilevel models were investigated. Conditioning methods included: (a) covariance adjustment, (b) matching, and (c) stratification. Design factors investigated included: (a) level-1sample size, (b) level-2 sample size, (c) level-1 covariate relationship to treatment, (d) level-2 covariate relationship to treatment, (e) level-1 covariate relationship to outcome, (f) level-2 covariate relationship to outcome, and (g) population effect size. The results of this study suggest the degree to which propensity score analyses are able to create balanced groups and reproduce treatment effect estimates with clustered data is largely dependent upon the propensity score estimation model and conditioning method selected. Overall, the single-level logistic and random intercepts models fared slightly better than the more complex multilevel models while covariance adjustment and matching methods tended to be more stable in terms of balancing groups than stratification. Additionally, the results indicate propensity score analysis should not be conducted with small samples. Finally, this study did not identify an estimation model or conditioning method that was consistently able to create adequately balanced groups and reproduce treatment effect estimates.

In this thesis we develop a theoretical framework for the identification of situations where the equal frequency (EF) or equal variance (EV) subclassification may produce lower bias and/or variance of the estimator. We conduct simulation studies to examine the EF and EV approaches under different types of model misspecification. We apply two weighting schemes in our simulations: equal weights (EW) and inverse variance (IV) weights. Our simulation results indicate that under the quadratic term misspecification, the EF-IV estimator provides the lowest bias and root mean square error as compared to the ordinary least square estimator and other propensity score estimators. Our theorem development demonstrates that if higher variation occurs with larger bias for within subclass treatment effect estimates then the EF-IV estimator has a smaller overall bias than the EF-EW estimator. We show that the EF-IV estimator always has a smaller variance than the EF-EW estimator. We also propose a novel method of subclassification that focuses on creating homogeneous propensity score subclasses to produce an estimator with reduced biased in some circumstances. We feel our research contributes to the field of propensity score adjustments by providing new theorems to compare the overall bias and variance between different propensity score estimators. / Graduation date: 2012

Background: Little is known regarding the health-related quality of life among myocardial infarction (MI) survivors in the United States. The purpose of this population-based study was to identify differences in health-related quality of life domains between MI survivors and propensity score matched controls. Methods: This retrospective, cross-sectional matched case-control study examined differences in health-related quality of life (HRQoL) among MI survivors of myocardial infarction compared to propensity score matched controls using data from the 2015 Behavioral Risk Factor Surveillance System (BRFSS) survey. Propensity scores were generated via logistic regression for MI survivors and controls based on gender, race/ethnicity, age, body mass index (BMI), smoking status, and comorbidities. Chi-square tests were used to compare differences between MI survivors to controls for demographic variables. A multivariate analysis of HRQoL domains estimated odds ratios. Life satisfaction, sleep quality, and activity limitations were estimated using binary logistic regression. Social support, perceived general health, perceived physical health, and perceived mental health were estimated using multinomial logistic regression. Significance was set at p < 0.05. Results: The final sample consisted of 16,729 MI survivors matched to 50,187 controls (n = 66,916). Survivors were approximately 2.7 times more likely to report fair/poor general health compared to control (AOR = 2.72, 95% CI: 2. 43-3.05) and 1.5 times more likely to report limitations to daily activities (AOR = 1.46, 95% CI: 1.34-1.59). Survivors were more likely to report poor physical health > 15 days in the month (AOR = 1.63, 95% CI: 1.46-1.83) and poor mental health > 15 days in the month (AOR = 1.25, 95% CI: 1.07-1.46) compared to matched controls. There was no difference in survivors compared to controls in level of emotional support (rarely/never: AOR = 0.75, 95% CI: 0.48-1. 18; sometimes: AOR = 0.73, 95% CI: 0.41-1.28), hours of recommended sleep (AOR = 1.14, 95% CI: 0.94-1.38), or life satisfaction (AOR = 1.62, 95% CI: 0.99-2.63). Conclusion: MI survivors experienced lower HRQoL on domains of general health, physical health, daily activity, and mental health compared to the general population.

No description available.

No description available.

No description available.

No description available.

No description available.