[Foreword by CBMM's Mandana Sassanfar]

Taylor Baum first became involved with CBMM when she was selected to participate in the 2017 CBMM Undergraduate Summer Research Internships in Neuroscience. Taylor was invited to return to MIT as an undergraduate visiting student and continue her research project in Prof. Emery Brown's lab in the Brain and Cognitive Sciences Dept. (MIT BCS.) In 2019, Taylor was accepted into the extremely competitive MIT EECS PhD Program.

From the start of her graduate studies, Taylor has pursued one of her passions: teaching computer science and data science to under-represented and disadvantaged students. She has taught with great success machine learning and signal processing in the annual CBMM Quantitative Method Workshop since 2019. Taylor taught machine learning at a neuroscience workshop in Puerto Rico, co-sponsored by CBMM and the NSF funded IBDK initiative. She has participated in the IQ BIO Hackathon held at UPR. Both the Neuroscience Workshop and the IQ BIO Hackathon were organized by CBMM collaborator Prof. Patricia Ordonez (Computer Science Dept., UPR.)

Taylor has also been active in other outreach activities through MISTI | MIT Global Experiences. In addition, has a served as a judge at the annual Massachusetts Junior Academy of Science fall symposium. At this symposium, select high school students are invited to present their wining science fair projects at the AAAS annual meeting.

Impressively, Taylor is currently developing Sprouting Programa Piloto - a new pilot initiativeprogram to stimulate STEM education in Puerto Rican middle and high schools. TheSprouting Programa Piloto is partially supported by CBMM. In the 2022 pilot phase,Sprouting Programa will provide two project-based STEM lessons which are designed to be accessible to teachers of all backgrounds. The first workshop for middle school STEM teachers will be held in Puerto Rico in April 2022.  We look forward to seeing the progress with the Sprouting Programa initiative.

Please see the link below to article describing Taylor's work with MISTI Uruguay.

[Article originally posted in Spanish, translated to English here by Google Translate]

American Taylor Baum, a control engineer and graduate student at MIT, is in Uruguay as a professor.

This is the second time that Taylor Baum is in Uruguay in her role as a data science instructor from the prestigious Massachusetts Institute of Technology.

Her task is to guide the Uruguayan students of the master's degree in Data Science at the Technological University of Uruguay (UTEC) and MIT in an intensive week of implementation of their final projects.

A control engineer, Baum works in the area of ​​biological systems using data science and is excited to talk about the potential this area has in Uruguay.

—Research applying data science to health issues. What is this job about?
—One of the areas I'm researching at MIT is blood pressure control. Instead of having a doctor in the operating room decide and apply medication to control the patient's blood pressure, I built a system that makes decisions about, for example, how much medication to give the person in the operating room during a surgical procedure. It is something like an anesthetist-computer, rather than the anesthesiologist-doctor making the decision to administer the drug.

—The doctor is the one who defines how much medication that patient needs and when. What stage is his investigation at?
—Yes, the doctor looks at the patient's blood pressure, among other variables, and makes decisions about whether he needs more medication to control it, to increase or lower his blood pressure. He has to pay attention to many aspects during a surgical procedure and the pressure issue is sensitive. Instead of the doctor doing that, I'm building a computerized system to do what the doctor does with the idea of, ideally, doing it better than the doctor. Surely we have much more to do, but we have already made very good progress. I have run simulations and a blood pressure pad that I'm giving drugs to in a computer simulated system. We will do experiments on animals to see how the system works. As my project takes ideas from many areas,

—How did you come from engineering to solve a health issue such as blood pressure control?
—I always loved studying something related to medicine and biology. In my early work in the lab we applied math and data science to engineering concepts in the brain. The brain is a really difficult organ to study because it's so complex and I started to move towards the heart because we understand it a little bit more than the brain so we can do cool things because we understand it better. I work with the central objective of helping people in matters that have an impact on their quality of life.

—We are talking about data science and health. How do you see the integration of these two areas in the future?
—I work on another project in which data science and machine learning are also relevant. It is about taking measurements of the heart to be able to indicate if a tissue is healthy or not. Currently you have to use a catheter that travels through a vein to the heart and with the use of electrical signals the doctors analyze and study the state of the tissue. Ultimately, they do their best to identify the state of the tissue, it can be dangerous. Instead, you can have an algorithm that can more reliably return information about that tissue. We are making progress. I see data science and machine learning helping clinicians make many better decisions in patient care.

—Culturally, doctors are not used to considering that a machine can make better clinical decisions than they are.
It's the biggest problem I've ever had to deal with. Often the doctors who are doing the procedures and treating the patients do not understand the research that is being done and how big an impact it could have on their practice. Doctors are trained to be confident, and when someone comes along and says, look, we can do this better, a conflict occurs. The advances are going to depend on a lot of collaboration between the medical industry and engineers and data scientists who are well trained in biological systems. We need to work more together to make things change because the medical industry moves too slowly and culturally with more collaboration we are going to pick up the pace.

—What do you like most about your teaching job guiding teams to set up these systems?
—This program would not work without the enthusiasm of the students. They are difficult topics to work on and you have to put effort into learning it, but once you get the models to work, you do it faster. I love to see people learn and that's why I teach all the time. In addition, the bonds that I generate here later are maintained. I have collaborated on projects of students who have already graduated from the master's degree at UTEC and MIT who contacted me. For example, a UTEC professor, Lucas Baldezzari, who made a tutorial for a brain-computer interface. I also mentored a group that continued to work on assisting people who are dedicated to providing treatment for autism.