Computationally-Enabled Medicine

AISC 610 Subject & Catalog Number

Description

Computational approaches to analyzing large data sets and applying the resulting insights to clinical decision-making are central to the present and future of biomedicine. Through this course, students will acquire the computational framework and toolkit necessary to address this growing analytic challenge. Students will explore this computational framework through selected examples of clinical decision-making and epidemiologic studies informed by electronic healthcare data. Students will also experience the application of these approaches to address a multitude of current research questions through mentored experiences on medical innovation projects. Focused on the application of AI in medicine, students will become familiar with different types and flavors of AI / LLMs, build effective prompts for LLMs used for research or analysis, and access and apply AI models that could be translated to real clinical scenarios. Format of classroom-based sessions: Classroom sessions are generally divided into two parts. The first part will include student presentations of journal articles, with an accompanying discussion led by the course directors. The second part of class will be devoted to completing in-class assignments, where students will apply and develop their R programming skills to the computational problems discussed in class, with individual guidance from data science mentors. Four sessions will be led by guest lecturers. Anticipated schedule: All AISCs are full-time courses. Students are expected to devote at least 50 hours per week to scheduled sessions and preparatory work. This course will consist of three half-days per week in classroom sessions, an additional two 2-hour sessions per week to complete homework assignments using R programming skills (these sessions are run by a dedicated team of data science mentors, and are meant to support students as they work through the material at their own pace), and two half-days per week for medical innovation projects lead by data science mentors experts on the field. Effective learning in this course will require that students have prior basic knowledge of the R programming language. Students missing this background should take the short & effective online course https://www.edx.org/course/data-science-r-basics before the course starts. This would also be reinforced with 4 introductory R sessions during the first two weeks of the course.

Course Manager: Shannon Reilly