Fernando A. Acosta Pérez

MIT Department: Electrical Engineering and Computer Science
Faculty Mentor: Prof. David Sontag
Undergraduate Institution: University of Puerto Rico at Mayagüez
Website: LinkedIn
Research Poster
Lightning Talk



My name is Fernando Acosta Pérez, and I am an industrial engineering student from the University of Puerto Rico at Mayagüez. My research experience is mainly in the area of machine learning and operations research applied to transportation systems. Since my sophomore year, I have been actively pursuing undergraduate research and have won awards like the Dwight David Eisenhower Fellowship. In summer 2019, I worked as a data analytics intern at NASA Glenn Research Center, and in 2020 I worked in the biotechnology industry as a supply chain analytics intern. In addition to my research and professional aspirations, I am passionate about education and have lead community outreach programs to motivate kids to pursue careers in science and technology. This summer, I worked at the MIT Clinical Machine Learning Lab, looking for ways to use machine learning and data science to improve the treatment selection process in Multiple Myeloma. My immediate career goal is to pursue a graduate degree and continue my research and professional efforts to inspire future scientists and engineers worldwide.


2021 Abstract


A Data Driven Decision Support Tool for Treatment Selection
in Multiple Myeloma

Fernando Acosta Pérez, Zeshan Hussain, David Sontag PhD
Department of Electrical Engineering and Computer Science,
Massachusetts Institute of Technology

Increasing the quality of life of cancer patients while making clinical practice more effective is a challenging problem in incurable progressive cancers like Multiple Myeloma (MM). One of the main concerns for MM is the lack of data-driven treatment selection techniques to make targeted decisions for specific patients. As part of this study, a discussion group with a set of oncologists was conducted to gather data about current needs within the treatment selection process in MM. Employing expert recommendations, a web-based decision support tool (DST) was designed using data from CoMMpass. The tool consists of a set of visualizations that can be stratified by patient demographics and medical records. It contains information about progression-free survival, adverse events, and longitudinal data from lab tests. Survival analysis models were parameterized using a Kalpan Meir estimator and survival curves were plotted as a function of different treatments. To ensure statistical overlap when comparing different treatments, OverRule, an algorithm that finds overlapping groups by generating a set of boolean rules was fitted. Results from the discussion group confirm statements from the literature that claims that treatment selection for MM relies mostly on the physician’s clinical acumen. In addition, preliminary results indicate that a decision support tool like the one developed in this study may lead to better clinical practice but experiments to test this hypothesis remain a subject of future research.