Biomedical Informatics PhD & MS
Methods Track: Biomedical Natural Language Processing
Biomedical Natural Language Processing (NLP) blends skills in algorithm development with practical knowledge of applications of NLP in biomedicine and health care, biomedical knowledge resources, and characteristics of biomedical text. Students will demonstrate competency in (a) implementing natural language processing and machine learning algorithms to solve problems in the biomedical and health domains, (b) processing text data from different genres including clinical narrative, social media, and the biomedical literature, (c) creating reference standard datasets for evaluating NLP performance, and (d) integrating NLP tools with biomedical informatics applications, such as clinical decision support, surveillance, and literature-based discovery.
Recommended Course of Study
This is a recommended schedule for this track (numbers in parentheses indicate credit hours). Courses can be waived or tested out of with permission of the course instructor and the student's advisor. Ultimately, the courses a student takes should be determined and approved by the student and the graduate committee.
Grey = bridge course for those without background in genomics and medicine; light blue = DBMI core course; dark blue = DBMI course for this track; white = electives and research hours.
PhD students are required to attend at least one SIG (all students are encouraged), which bring people with similar interests together to learn, share, and experiment.
Sign up for at least one practicum to gain hands-on experience and work with a team on a project.
Data Science Scholars--Applied NLP (Fall 2017)
This practicum is an extended research-in-progress course for natural language processing. Students in this course will either lead their own project as a data science scholar or participate in an existing project applying NLP to a health-related problem. The course offers 1) mentored guidance and peer review for your NLP project and 2) the opportunity to present research results, manuscript drafts, and grant proposals ideas to peers, mentors, and informatics faculty for feedback. Students not leading an NLP project will have ample opportunity to work on an NLP team and participate in an existing project.
Review and discuss literature in this area.
NLP Journal Club (Fall 2016)
Feel free to meet individually with faculty and/or to attend their weekly lab meetings.
Samir AbdelRahman; Wendy Chapman; Brian Chapman, Radiology; Michael Conway; Jeffrey Ferraro, Intermountain; Jennifer Garvin; Peter Haug, Intermountain; John Hurdle, Olga Patterson, Epidemiology.
Ellen Riloff, Computer Science; Vivek Srikumar, Computer Science.