Campuses:

clinical trial

Thursday, November 8, 2018 - 4:00pm - 4:30pm
Peter Song (University of Michigan)
Identification of subgroups in a biomedical study with subjects sampled from a heterogeneous population has attracted considerable attention in recent years. Technically, subgroup group analysis may be formulated as a type of supervised clustering analysis with group labels being latent. The method of finite mixture model is the most widely used approach in biomedical studies due to its interpretability and reproducibility, in which the Expectation-Maximization (EM) algorithm plays a central role in handling related optimization.
Wednesday, November 7, 2018 - 9:20am - 10:10am
Xuming He (University of Michigan)
Subgroup analysis is frequently used to account for the treatment effect heterogeneity in clinical trials. When a treatment is seen marginally effective for the population of the original study, it is tempting to consider post hoc subgroup identification. When a highly promising subgroup is selected this way, serious questions have to be asked about the potential risks and rewards of the subgroup pursuit.
Wednesday, March 7, 2018 - 11:30am - 12:30pm
Adam Himes (Medtronic)
Medical device manufacturers are increasingly using predictive computer models, also called virtual patient models, that simulate clinical outcomes. In some cases, these virtual patient models can be incorporated into a study in a way that is analogous to how some Bayesian clinical trials incorporate historical data as prior information. Benefits of this approach may include increased information from the clinical study, more confidence in the clinical outcome, and in some cases smaller or shorter duration studies.
Wednesday, March 7, 2018 - 10:00am - 11:00am
Drew Pruett (University of Mississippi)
Human physiology is a complex system composed of many interacting negative feedback loops involving hormones, nerves, transporters, physical anatomy and other factors. Redundancy in physiology complicates accurate prediction of a patient’s response. For any given medical therapy or intervention, 10-90% of potential patients are resistant, achieving less than half of the expected response. Prediction of nonresponse is a necessary step in minimizing inefficiencies in health care and biomedical product evaluation and regulation.
Subscribe to RSS - clinical trial