The growth of antibiotic resistance is one of the most pressing medical problems facing the world, placing the lives of millions at risk. Currently, antibiotic prescription for patients is largely based on manual assessments of medical data and a doctor’ s past experience. These decisions do not always produce the optimal choice given a patient’ s condition and past antibiotic exposure. However, the abundance of electronic records and data about patients’ antibiotic resistance profiles may make it possible to construct a more rigorous framework for predicting antibiotic resistance. In this project, we plan to use machine learning techniques to develop accurate models of antibiotic resistance in patients that will help doctors make decisions about antibiotic usage in a more systematic manner.

“I am participating in SuperUROP to gain experience working on an applied machine learning project that will allow me to use some of the theoretical concepts I have learned while taking 6.867 (Machine Learning) last year. I hope to get a better understanding of working on a long-term research project with many open-ended directions for exploration. I’ m very excited to work on a project that could potentially have tremendous applications in the medical world.”