The utilization of the Bayesian method in drug development offers several advantages. One of these is the ability to continuously update knowledge instead of restricting modifications to research design to major, isolated stages assessed in trials or phases. Additionally, the Bayesian approach is closely tied to decision-making within individual trials, drug development programs, and the broader context of developing a company's portfolio of medications. The future is expected to bring rapid advancement in clinical trial designs and analytics utilizing Bayesian methods. With political organizations and consumer advocacy groups calling for faster, safer, and more effective drug development, there is a risk of neglecting fundamental scientific concepts. However, adopting a Bayesian strategy can accelerate medication development and save money while maintaining sound research practices. The Bayesian approach is already gaining popularity in drug research and several therapeutic areas of medical device development, with variations influenced by the personalities involved. Notably, therapeutic areas where the clinical endpoint is detected early stand to benefit the most. Cancer and other diseases that have an increasing number of biomarkers available for modeling disease progression could benefit from the Bayesian approach. These biomarkers allow for more accurate tracking of a patient's progress and outcome determination. The use of Bayesian modeling is particularly useful in treatment areas where early signs of therapeutic effectiveness are evident. Introduction: The trend in oncology treatment is shifting towards personalized medicine, where patients are matched with the most suitable treatments based on their prognostic factors [1,2]. This personalized approach has the potential to be highly beneficial for both patients and drug development. The initial step in evaluating the efficacy of a novel medication for a particular patient population in early Phase II trials is to determine whether the appropriate degree of efficacy has been achieved. In oncology, it is common to conduct a series of small screening trials in different patient subgroups, based on factors such as histology or a biomarker signature. However, these trials are often conducted independently of one another, without considering the possibility that some patient subpopulations may have similar therapeutic responses. The results of the trials in different subpopulations can provide insight into the treatment outcomes in other subpopulations. In Phase II cancer trials where a novel medication is being tested on various patient populations, Bayesian hierarchical models are used. Hierarchical modeling allows for the "borrowing" of information about the treatment effect in one group when predicting the treatment impact in another group [3]. Essentially, the estimated treatment effect for each group is reduced towards the average [4]. The degree of shrinkage is determined by the results, including the relative accuracy of the estimations in the various groups.