Syllabus

Course Summary

Biomedical Data Design (BDD) is a year-long project-based course where students work in teams of four to six. We offer two different levels: 4xx and 6xx. The 4xx is designed for undergraduates with background in engineering and data science and the 6xx is designed for more advanced undergraduates and graduate students. Teams are encouraged to include students at both levels, as each level brings a unique and valuable perspective. The goal of the course is to create an inspirational environment in which each of the students works on a team to build a data science product “soup to nuts”, starting with ideation and ending with publication. Specifically, we aim for every student in BDD to complete a research artifact (code package, data analysis, manuscript, publication) that they are responsible for by the end of the year. Along the way, students learn skills that will serve them well in industry, academia, or government. To facilitate these goals, the course is divided into Sprints.

Goals by Sprint

The duration and major goals of each sprint is detailed below:

• Semester 1
  • Sprint 0
    • Pick a biomedical data science problem
    • Describe how you will address problem according to Heilmeier Catechism and make plan a list of deliverables.
    • Note: Sprint 0 is meant to be a little confusing! Fully understanding and scoping a yearlong project is hard. It’s important to take this time with your team and instructors to synthesize as much background as you can.
  • Sprint 1
    • Replicate numerical results previously published solutions
• Semester 2
  • Sprint 2
    • Develop novel solution to address problem
  • Sprint 3
    • Technical communication and knowledge transfer: Manuscript submitted to arxiv detailing your contributions.

Forming Teams

Teams will be formed prior to joining the course. Students will rank projects in a public survey (meaning all students will be able to see the project preferences of their peers). Based on these results, students will self-organize into teams. Once a team has been finalized, I will approve all members to enroll in BDD.

Weekly Structure

We have class two times per week. The bulk of the classroom time, however, is spent with student presentations. Each week each student presents their progress from the previous week, and their plan for the next week. Please see this slide deck for an example of what slides are expected to look like, along with written explanations of why these are good slides.

These presentations are specifically for instructors to provide students feedback on how students can improve. Presentations are not intended to be status updates or final reports — they are meant to encourage iteration and progression to the correct goal. Feedback is provided in written form to each student for each presentation, and verbal feedback is provided whenever it seems generally useful for other students. Please note that the feedback we voice is intended for everyone. Students are encouraged to take notes during presentations directly on the slides so that instructors/team/student are all on the same page.

Each team also meets at least once more per week to prepare their presentation, and work together. About once per week we provide a lecture on some relevant data science content, typically content not available otherwise online. This year, for Fall 2024, the teams will present on the following days:

• Tuesdays: TBD
• Thursdays: TBD

Motivation

This course is based on my experience as an academic, and entrepreneur, an advisor, and an instructor. It is designed to be the best class you’ll ever take. You will learn (by doing and getting feedback) the skills that I have found particularly useful in my endeavors. It will be organized into weekly sprints. Weekly progress will be reported documenting goals towards your team sprints, with sprint demo’s to happen at the close of each sprint. Each team will be graded jointly on the basis of meeting the sprint goals, as well as providing clear and concise weekly progress reports.

The main “skills” you will learn in this class include:

• How to choose a project significant for the world, feasible for you, and that you are intrinsically motivated to complete (see my blog post).
• How to scope work so that you can achieve weekly progress towards quarterly goals (see smart goals).
• How to effectively communicate technical content.
• How to generate publication quality figures (see figure checklist).
• How to complete a wide set of data science tasks, spanning from data wrangling to statistical modeling.
• How to peacefully and productively work with a diverse team of passionate individuals.

Credits

The 4xx and 6xx course will provide 4 credits in both the Fall and Spring. For BME undergraduates, these count towards your Design requirements.

Course Requirements

Admittance to this course requires approval from the instructor, to ensure the students in the course are sufficient diverse along a number of dimensions. To gain admittance, you must:

1. Be more excited about this course than any other academic endeavor for the year. Nobody is required to teach or take this course, and since so many people want to take it each year, preference is given to those that are most passionate about the material.
2. In practice, people commonly spend up to 20 hrs per week in this class, or more. It is often rated one of the most challenging courses, so please consider that when making your course schedule. Priority will be given to students that certainly have room to be successful in the course.
3. Background in numerical programming is required. Particularly, the more experience a student has in numerical programming, the better. Prior experience with GitHub is highly encouraged.
4. See the Join page for more information on how to get enrolled.

Code of Conduct

Everyone taking the course is required to abide by the NeuroData Code of Conduct. If you have questions or suggestions for making the code of conduct better, let us know.

Communication

This class communicates largely in Slack. Please join our Slack workspace at to get involved. Regular updates are provided in Slack, and the instructors will assume you have received them. TA will answer questions from slack approximately within 48 hours.

Extra Feedback/Guidance

• On days when teams are not presenting, we encourage students to meet (either with or without their TA) and discuss their project.
• TAs may be available outside of class for office hours.

Grading

In general, it is expected that all students will be most excited about this class, and therefore invest a minimum of 12 hours of effort per week in the fall and spring. You should expect an A only if you address the weekly feedback from PIs and TAs and finish the DoD of the semester. Anybody not receiving an A in the first semester will not be invited back for the second semester.

Weekly Tasks

Each week students will be graded on the degree of completion of their deliverables, typically including both a qualitative and quantitative result. After your presentations, instructors will provide detailed feedback on your slides, with instructions on how to improve them. Grades will be provided on the basis of your ability to complete the tasks you set out to perform, and update slides on the basis of other’s input. In addition, slides should have research artifacts for each task (whether completed or not).

Make sure your weekly tasks are SMART goals, and that all goals have a Definition of Done (DoD).

Open Source Projects

The list of projects for previous academic years can be found here. The repos we typically contribute to include

• hyppo
• kfg
• proglearn
• rf-dn

Feedback

Steven Covey, author of “Seven Habits”, states that the 7th habit is “sharpening our sword”, which means (for this class), getting feedback and seriously considering it. Every person involved in the class will therefore be required to provide feedback to others, including the instructor. Students will also identify properties of the class which gruntle or disgruntle them, so that we may make adjustments.

Course reviews

So far, the students have determined that the class is quite good, with an average overall quality of 4.71, as compared to the department’s average of 3.95, and the schools average of 4.09 (see Table 1 for details). This is despite the fact that course is also typically ranked one of the most difficult and time-consuming courses.

Quantitative teaching evaluations for all Biomedical Data Design courses is shown below. Numbers represent “overall quality” of the course. Scores out of 5 (4 = “good”; 5 = “excellent”). Response rates: All but 2 students ever responded. The mean number of students is per semester (ignoring winter session and joining across multiple course levels if they met during the same time. Note that course evaluations for several course numbers are not available online, including 638.SP18 and 497.FA18.

Reviews for every course that Jovo has ever taught can be found here.

ABET Student Outcomes

• (SO1) an ability to identify, formulate, and solve complex engineering problems by applying principles of engineering, science, and mathematics.
• (SO2) an ability to apply engineering design to produce solutions that meet specified needs with consideration of public health, safety, and welfare, as well as global, cultural, social, environmental, and economic factors.
• (SO3) an ability to communicate effectively with a range of audiences.
• (SO5) an ability to function effectively on a team whose members together provide leadership, create a collaborative and inclusive environment, establish goals, plan tasks, and meet objectives.
• (SO6) an ability to develop and conduct appropriate experimentation, analyze and interpret data, and use engineering judgment to draw conclusions.
• (SO7) an ability to acquire and apply new knowledge as needed, using appropriate learning strategies.