Propensity Score Methods in Health Technology Assessment: Principles, Extended Applications, and Recent Advances

Abstract

Randomized clinical trials (RCT) are accepted as the gold-standard approaches to measure effects of intervention or treatment on outcomes. They are also the designs of choice for health technology assessment (HTA). Randomization ensures comparability, in both measured and unmeasured pretreatment characteristics, of individuals assigned to treatment and control or comparator. However, even adequately powered RCTs are not always feasible for several reasons such as cost, time, practical and ethical constraints, and limited generalizability. RCTs rely on data collected on selected, homogeneous population under highly controlled conditions; hence, they provide evidence on efficacy of interventions rather than on effectiveness. Alternatively, observational studies can provide evidence on the relative effectiveness or safety of a health technology compared to one or more alternatives when provided under the setting of routine health care practice. In observational studies, however, treatment assignment is a non-random process based on an individual’s baseline characteristics; hence, treatment groups may not be comparable in their pretreatment characteristics. As a result, direct comparison of outcomes between treatment groups might lead to biased estimate of the treatment effect. Propensity score approaches have been used to achieve balance or comparability of treatment groups in terms of their measured pretreatment covariates thereby controlling for confounding bias in estimating treatment effects. Despite the popularity of propensity scores methods and recent important methodological advances, misunderstandings on their applications and limitations are all too common. In this article, we present a review of the propensity scores methods, extended applications, recent advances, and their strengths and limitations.

Diabetes-Related Effectiveness and Cost of Liraglutide or Insulin in German Patients with Type 2 Diabetes: A 5-Year Retrospective Claims Analysis

“…When comparing individuals receiving different treatments in non-randomised groups, the question of comparability due to systematic differences across treatment groups needs to be addressed. Propensity score matching (PSM) is a common approach to adjust for patients' characteristics [27]. Patients with the same propensity score have theoretically the same probabilistic distribution over other covariates, independently of the treatment they received.…”

Rates of delirium associated with calcium channel blockers compared to diuretics, renin-angiotensin system agents and beta-blockers: An electronic health records network study

“…Here we used an electronic medical records network to assess whether AHT classes are associated with differential risks of delirium over a two-year period, taking advantage of a large sample size and unusually detailed data availability. We used extensive propensity score matching ( Ali et al, 2019 ; Austin, 2011 ) and negative control outcomes ( Arnold and Ercumen, 2016 ; Lipsitch et al, 2010 ) to reduce the confounding which affects pharmacoepidemiological studies ( Davis et al, 2020 ; Freemantle et al, 2013 ; Kyriacou and Lewis, 2016 ). We chose CCBs as our reference AHT class for two main reasons.…”

Reply to the Letter to the Editor: “Comparison of the Safety and Efficacy of Yttrium-90 Radioembolization for Nonalcoholic Fatty Liver Disease-Associated and Hepatitis B Virus-Associated Hepatocellular Carcinoma”

“…We would like to express our gratitude for the valuable comments that the authors gave in response to our manuscript entitled: "NAFLD-Associated Comorbidities in Advanced Stage HCC Do Not Alter the Safety and Efficacy of Yttrium-90 Radioembolization" [1]. We fully agree with the colleagues that propensity score analysis is potentially capable to reduce a selection bias and thus decreases the likelihood of confounding when analyzing nonrandomized data [2][3][4][5][6].…”