Faculty Profile

Philip Boonstra

Philip S Boonstra, PhD

  • Associate Professor, Biostatistics

Is extracorporeal membrane oxygenation (ECMO) a worthwhile and life-saving treatment for patients with severe Covid-19? Is this new cancer treatment safe for patients, and does it actually treat the cancer? Is this new prediction model worthwhile? How can I best teach the R programming language to new students who have never used it before? These are some of the questions that Phil, working with students, colleagues, and collaborators, tries to answer. The questions are varied in their specificity, scope, and context but hold in common Phil's desire to use science, directly or indirectly, to improve public health and quality of life.

  • PhD, University of Michigan, 2012
  • MS, University of Michigan, 2009
  • BA, Calvin University (formerly Calvin College), 2006

Research Interests:
Data and model integration, ECMO support, Bayesian methodologies, early-phase oncology trial design

Research Projects:
Working with the Extracorporeal Life Support Organization (ELSO) to estimate the mortality of patients with several Covid-19 who are treated with ECMO, and determining which pre-ECMO characteristics portend better or worse outcomes

Developing statistical methodology for combining heterogenous prediction models

Designing 'seamless' oncology trials that are able to assess both the safety and efficacy of new cancer treatments within a single protocol

Extracorporeal membrane oxygenation support in COVID-19: an international cohort study of the Extracorporeal Life Support Organization registry RP Barbaro, G MacLaren, PS Boonstra, TJ Iwashyna, AS Slutsky, E Fan, ... The Lancet 396 (10257), 1071-1078 https://www.sciencedirect.com/science/article/pii/S0140673620320080

Extracorporeal membrane oxygenation for COVID-19: evolving outcomes from the international Extracorporeal Life Support Organization Registry RP Barbaro, G MacLaren, PS Boonstra, A Combes, C Agerstrand, ...The Lancet 398 (10307), 1230-1238

Incorporating historical models with adaptive Bayesian updates
PS Boonstra, RP Barbaro Biostatistics 21 (2), e47-e64

Inferring a consensus problem list using penalized multistage models for ordered data PS Boonstra, JC Krauss The annals of applied statistics 14 (3), 1557

A modular framework for early-phase seamless oncology trials
PS Boonstra, TM Braun, EC Chase Clinical Trials 18 (3), 303-313

4632 SPH I
1415 Washington Heights
Ann Arbor, MI 48109

Email: philb@umich.edu
Office: 734-615-1580

For media inquiries: sph.media@umich.edu