Meet the Team: Dr. Mike Becich

Mike Becich, MD, PhD, is a distinguished university professor and the inaugural chairman of the Department of Biomedical Informatics (DBMI) at the University of Pittsburgh School of Medicine. Dr. Becich’s research interests are focused on the interface between clinical informatics, imaging informatics and bioinformatics and include clinical phenotyping of patients for genomic/personalized medicine and tissue banking informatics with a special emphasis on data sharing. Dr. Becich recently sat down to share more about his interests and his team’s role within the Pittsburgh Health Data Alliance. ­­­

How did you get involved in healthcare and informatics?

I grew up fascinated with imaging – what it was, how it worked, and what it could tell us about things we couldn’t see with the naked eye. It was this interest that led me to become a pathologist. From my work in pathology, I saw how interconnected technology, science, data, and engineering is and what could be accomplished when you bring together all the right people and pieces. That’s what I really enjoy about working at DBMI – we have a team dedicated to improving research and patients’ lives through innovative informatics.

Tell us more about your role and your teams’ work at DBMI.

 I oversee the work that our teams do at DBMI. As a part of the Pittsburgh Health Data Alliance, we have the opportunity to bring together healthcare physicians and innovative academics to work on some of the most cutting-edge science. As our name suggests, we’re focused on biomedical informatics where a majority of work incorporates machine learning, particularly causal machine learning, artificial intelligence and discovery biology. We’re gathering data and looking for patterns to define causality for translational medicine.

You’ve said before that what you do at DBMI is closely related to philosophy, how?

Philosophy, simply put, is the science of thinking. At DBMI, we’re using algorithms to teach machines to think. When it comes to healthcare data, it’s impossible for a person to process every case they’ve seen and identify all the causal links between them. We’re building models that can consume large amounts of data to help spotlight causality. An example is our TDI project, led by Gregory Cooper and Xinghua Lu (both MD PhDs), where we’re feeding machines tumor data and then training them to output what treatments cause specific reactions. Using this information, we can help oncologists achieve better outcomes based on causal machine learning.

What do you enjoy most about your work?

Personally, I love being able to serve my students and my teams. There’s nothing better than helping a student find their calling within medicine and science. At DBMI, the work we’re doing is transformative, and being able to support the innovation and breakthroughs that we’re making fuels my passion for my job.