A recent Cytel paper, published in JCO Clinical Cancer Informatics, uses a Bayesian Network Model to accurately predict outcomes in cancer patients. This paper provides support for researchers seeking to use Bayesian methods instead of other machine learning techniques in clinical trial design and analysis. Research and Communications Specialist Dr. Esha Senchaudhuri notes that Bayesian methods may also directly improve patient care by identifying prognostic variables.
According to Dr. Senchaudhuri, “The Bayesian Network Model condenses a number of statistical relationships into a single mathematical entity, including information about biomarkers, treatment and outcomes. In doing so, these models can potentially also identify interpretable prognostic variables; prognostic variables that can be used by clinicians for improved treatment. Therefore, in addition to constructing a scientifically valid model, there is potential for immediate benefit within clinical practice and medical decision-making.” Read more here.
(Source: Esha Senchaudhuri, Cytel, 4/2/21)