Brian Denton, Ph.D.

Denton, Brian
Professor
EngineeringIndustrial Operations Engineering

Biography

Dr. Denton’s work involves the development of mathematical models for studying ways to improve prevention, early detection, and treatment of chronic diseases, including cancer, diabetes, and heart disease, and using these models to design individualized clinical pathways that recognize different patient screening and treatment needs. His research group is developing new approaches using machine learning, simulation and computational optimization methods to tailor decision-making on the basis of individual patient risk factors and preferences, with the goal of balancing the benefits of early detection and treatment with the harm and cost of invasive testing and overtreatment.

  • Ph.D., Management Science, McMaster University
  • M.Sc., Physics, York University
  • B.Sc., Chemistry and Physics, McMaster University

U-M Academic Affiliation(s)

Urology

IHPI-Affiliated Centers and Programs

Featured Member Profile

What are you thinking about?

My research involves the development of mathematical models for studying ways to achieve early detection and treatment of chronic diseases, like diabetes and cancer. Right now I spend a lot of my time thinking about how to use these models to design individualized clinical pathways that recognize different patient screening and treatment needs. My research group is developing new approaches using machine learning, simulation and computational optimization methods to tailor decision making on the basis of individual patient risk factors and preferences, with the goal of balancing the benefits of early detection and treatment with the harm and cost of invasive testing and overtreatment. This video from the National Science Foundation features an example of such a project involving our Departments of Urology and Pathology.

 

Why is this interesting to you?

There are so many open questions about how to integrate new interventions, like molecular biomarkers, imaging procedures, and new drugs to help patients avoid complications. Chronic diseases are complicated, and detection and treatment requires optimizing the sequence and timing of interventions into a clinical pathway that is ideally suited to a patient’s needs. The large number of new interventions makes it infeasible to test all the possible clinical pathways using randomized trials. The models my group is developing help fill an important gap by helping to guide decision making about how and when to use new interventions.

 

What are the practical implications for healthcare?

Chronic diseases are the most common causes of death and disablement in the United States, and they account for the majority of costs to the health system. A lot of research is focused on discovering new interventions, but less is focused on how to combine these discoveries in a way that factors in individual patient risk factors, preferences, and the importance of using valuable resources efficiently. Models that can predict outcomes for various clinical pathways can help predict which ones have the greatest potential for impact and help understand design principles that can streamline the translation of these new discoveries into clinical practice. 

Search our members by typing in names or keywords, or use the category filters at the left