Predictive Modeling of Endovenous Laser Ablation Treatment Outcome in Varicose Veins

Authors : Steve Chung, Serin Zhang, Sanjay Srivatsa

Pages : 1-10

View : 46 | Download : 46

Publication Date : 2024-06-28

Article Type : Research Paper

Abstract :Varicose veins afflict a significant portion of adults, with approximately 30% experiencing this condition, which often necessitates medical treatment like endovenous laser ablation (EVLA). EVLA has emerged as a highly effective and minimally invasive treatment. However, despite its efficacy, there is a lack of literature on predictive modeling of EVLA treatment outcomes considering both surgical settings and patient characteristics. In this study, we present a comprehensive analysis employing logistic regression under both maximum likelihood (ML) and Bayesian frameworks, as well as support vector machine (SVM) regression. Our results indicate that Bayesian logistic regression with uniform prior demonstrates superior performance. Furthermore, through repeated random sub-sampling validation, we confirm the robustness of our models in predicting successful EVLA outcomes. These findings provide the potential of machine learning techniques in augmenting predictive capabilities in medical decision-making. Our study contributes to the burgeoning literature on predictive modeling in medical contexts, offering insights into the optimization of EVLA treatment outcomes.
Keywords : Bayesian logistic regression, Logistic regression, Support vector machine, Endovenous laser ablation, Varicose veins