South Africa has the largest HIV-infected population in the world, with 2015 estimates of 7 million people living with HIV and 180,000 AIDS-related deaths. The South African government began scale-up of a public-sector HIV care and treatment program in 2004, and by the end of 2015, 3.4 million HIV-infected individuals were on antiretroviral therapy (ART). When scale-up began in South Africa, ART was only available to HIV-infected individuals with CD4 counts ≤200 cells/µL or WHO clinical stage 4 disease. In 2010, treatment was extended to patients who were pregnant or who had tuberculosis and a CD4 ≤350 cells/µL, and in 2011, eligibility was extended to all patients with CD4 ≤350 cells/µL. In 2013 patients with WHO clinical stage 3 disease became eligible. In 2015, the eligibility threshold was increased to CD4 ≤500 cells/µL, and in 2016, the South African National Department of Health announced that the country would implement a “test and treat” strategy, offering free ART to all HIV-infected individuals, regardless of CD4 count. This dissertation examines the effectiveness of several expansions and modifications to South Africa’s treatment program. In study 1, we investigated whether the 2011 extension of HIV treatment to patients with CD4 counts ≤350 cells/µL successfully increased the number of newly-eligible patients on treatment (those with CD4 counts between 201–350 cells/µL) without crowding out previously-eligible patients with more severe disease (CD4 counts ≤200 cells/µL), focusing on a network of rural clinics in KwaZulu-Natal. We found encouraging results, with newly-eligible patients (CD4 201–350) initiating treatment at a greater frequency (73.0 additional patients per month; 95% CI: 42.1; 103.9) and 47% faster than before (95% CI: 19%; 82%), while previously eligible patients (CD4 ≤200) experienced no decline in the number of patients initiating treatment or the speed of treatment uptake. In study 2, we evaluated whether the introduction of a single-pill fixed-dose combination (FDC) treatment for ART initiators in South Africa had an impact on attrition from care compared to the previously-recommended multiple-pill regimen. We focused on an urban clinic in Johannesburg, using four different clinic attendance measures to define attrition (generally a combined measure of loss to follow-up and mortality). An intention-to-treat analysis revealed an estimated 11.3 percentage point decrease in attrition (95% CI: -22.0; -0.6) associated with the policy change, while a regression discontinuity analysis estimated an 18.0 percentage point drop in attrition (95% CI: -33.6; -2.4) associated with single-pill FDC treatment relative to multiple pills, controlling for unmeasured confounding. In study 3, we used stratified instrumental variable analysis to examine whether the effect of FDCs on attrition varied across subsets of the patient population in the same Johannesburg clinic we evaluated in study 2. We saw larger effects among women (RD -0.25; 95% CI: -0.42; -0.09), non-anemic patients (RD -0.24; 95% CI: -0.41; -0.08), patients with early-stage (as opposed to advanced) clinical disease (RD -0.20; 95% CI: -0.32; -0.07), and those with high CD4 counts (for CD4 ≥350 cells/µL, RD -0.58; 95% CI: -1.58; 0.42). These results suggest that healthier patients saw the greatest improvement in retention in care following the switch from multiple-pill to single-pill regimens. In an era where the healthiest HIV-infected patients are now being targeted for ART treatment, FDCs can play a large role in preventing attrition from care. These three studies depict an HIV program that has successfully grown to treat increasing numbers of patients using up-to-date strategies of care. Given the immense scale and cost of South Africa’s HIV treatment program, it is important to continue to monitor its effectiveness, especially as it introduces new treatments and strategies and adapts to the changing epidemic.

We first studied factors associated with the rate of colonoscopy by primary care physicians (PCPs) in Ontario between the years 1996 and 2005. Next, we conducted an Instrumental Variable Analysis (IVA) to estimate the effect of colonoscopy on colorectal cancer (CRC) incidence and mortality on average-risk subjects aged 50-74 years. Finally, we explored two study cohorts, one by including subjects who had the outcomes during the exposure period (unselected cohort) and the other cohort by excluding those subjects (restricted cohort). We estimated the absolute risk reduction associated with colonoscopy in preventing CRC incidence and mortality using traditional regression analysis, propensity score analysis and IVA. PCPs who were Canadian medical graduates and with more years of experience were more likely to use colonoscopy. PCPs were more likely to use colonoscopy if their patient populations were predominantly women, older, had more illnesses, and if their patients resided in less marginalized neighborhoods (lower unemployment, fewer immigrants, higher income, higher education, and higher English/French fluency). Using PCP rate of discretionary colonoscopy as an instrumental variable, receipt of colonoscopy was associated with a 0.60% absolute reduction in 7-year CRC incidence and a 0.17% absolute reduction in 5-year risk of death due to CRC. The unselected cohort showed an increase in CRC incidence and mortality associated with colonoscopy, whereas the restricted cohort showed a reduction in CRC incidence and mortality associated with colonoscopy. In the restricted cohort, using different statistical models, the absolute risk reduction varied from 0.52-0.60% for CRC incidence and 0.08-0.17% for CRC mortality. There were social disparities in the use of colonoscopy by PCPs and this disparity increased as the overall use of colonoscopy increased over time. Colonoscopy is effective in reducing incidence and mortality due to CRC. Different methods of subject selection and statistical analysis provided different estimates of colonoscopy effectiveness.

We first studied factors associated with the rate of colonoscopy by primary care physicians (PCPs) in Ontario between the years 1996 and 2005. Next, we conducted an Instrumental Variable Analysis (IVA) to estimate the effect of colonoscopy on colorectal cancer (CRC) incidence and mortality on average-risk subjects aged 50-74 years. Finally, we explored two study cohorts, one by including subjects who had the outcomes during the exposure period (unselected cohort) and the other cohort by excluding those subjects (restricted cohort). We estimated the absolute risk reduction associated with colonoscopy in preventing CRC incidence and mortality using traditional regression analysis, propensity score analysis and IVA. PCPs who were Canadian medical graduates and with more years of experience were more likely to use colonoscopy. PCPs were more likely to use colonoscopy if their patient populations were predominantly women, older, had more illnesses, and if their patients resided in less marginalized neighborhoods (lower unemployment, fewer immigrants, higher income, higher education, and higher English/French fluency). Using PCP rate of discretionary colonoscopy as an instrumental variable, receipt of colonoscopy was associated with a 0.60% absolute reduction in 7-year CRC incidence and a 0.17% absolute reduction in 5-year risk of death due to CRC. The unselected cohort showed an increase in CRC incidence and mortality associated with colonoscopy, whereas the restricted cohort showed a reduction in CRC incidence and mortality associated with colonoscopy. In the restricted cohort, using different statistical models, the absolute risk reduction varied from 0.52-0.60% for CRC incidence and 0.08-0.17% for CRC mortality. There were social disparities in the use of colonoscopy by PCPs and this disparity increased as the overall use of colonoscopy increased over time. Colonoscopy is effective in reducing incidence and mortality due to CRC. Different methods of subject selection and statistical analysis provided different estimates of colonoscopy effectiveness.