Comparative study of adjustement methods for confounding variables

• Autor(a) principal: Silva, Inês Fortuna Alves da
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.22/21468
• topic: Brest cancer; Propensity score; IPTW; Confounders; Observational studies; Treatment efficacy; Neoadjuvant pertuzumab

Observational studies provide relevant evidence; however, they have an inherent lack of balance of baseline variables distribution between the study groups, making it difficult to understand the real treatment effect. There are many methods to balance the confounders. Traditional covariate adjustment is the most used however, currently, it is also common to apply techniques based on propensity score (PS). One of them is Inverse Probability of Treatment Weighting (IPTW). The application of IPTW involves comparing two groups of samples weighed by inverse probability of treatment. The main advantage of using IPTW, compared to other PS techniques, is to allow all patient data to be preserved, and compared to classical adjustment methods, it allows balancing and evaluating this balance of confounders before assessing the outcome. In this study, the effect of two neoadjuvant treatments for HER2-positive breast cancer was analysed. The treatments differed in four additional cycles of pertuzumab. Two methods of balancing the distribution of variables were applied, the IPTW and the traditional regression adjustment methods. The results after the application of both mentioned techniques permitted to conclude that the therapy with double-block anti-HER2 seems more favourable. Besides, this treatment enabled a greater number of patients with pathologic complete response (pCR). It also allowed a reduction in the number of radical mastectomies. Although there were statistically significant differences in the type of surgert between the study groups, the difference in pCR was not significant (p > 0.05). This work had some limitations, such as the low number of patients with certain characteristics, among other factors, which conditioned a clear perception of the results. In this sense, it will be useful to expand this study to include more patients with heterogeneous features, allowing to get more robust conclusions.