Students taking the course for 3 credit units will participate in a quarter-long research project in collaboration with engineering students from BIODS220 and submit a 5-6 page paper describing the research project in the format of a non-technical clinical journal manuscript formatted as a Nature Medicine Article.

Students taking the course for 3 units, will not be required to submit the second scientific review assignment!

Submission 1: Project Proposal

Your proposal should be a 0.5-1 page document (max 500 words) and is due Oct 9 (Fri). You may include figures if appropriate. The proposal should include the following (with grade breakdown):

• Title, Authors(s)
• (25%) What is the problem that you will be investigating? Explain the task thoroughly. Why is it interesting?
• (25%) What is the data you will be using? Please include relevant characteristics such as the source of the data, the size of the dataset, and a sample of the data. Explain clearly which parts of the data will be used, the nuances of the data, as well as potential obstacles.
• (25%) What methods do you plan to experiment with? Please thoroughly describe them. If there are existing related implementations, will you use them and how? How do you plan to improve or modify such implementations? This can be subject to change, but you should have a general sense of how you plan to approach the problem you are working on.
• (25%) How will you evaluate your results? Qualitatively, what kind of results do you expect (e.g. plots or figures)? Quantitatively, what kind of analysis will you use to evaluate and/or compare your results (e.g. what performance metrics or statistical tests)? What is your hypothesis regarding your results compared to baselines?

Submission: Submission: Please submit your proposal as a PDF on Gradescope.

Submission 2: Project Milestone

Your milestone should be a 3-4 page document (max 1,500 words) preparing you towards the final submission which is a report in Nature Medicine Article format. The milestone is due Oct 30th (Fri), and should include the following (with grade breakdown):

• Title, Authors(s)
• (20%) Introduction. Introduce your problem, and the landscape for why the problem is interesting from a healthcare perspective and what has been done before in this space. Describe your overall plan for approaching the problem, what contributions you expect to make, and why this is interesting in the context of the described landscape.
• (20%) Preliminary Results. Describe any preliminary results up to the time of the milestone. You should show the results of training at least one deep learning model. (It is fine if the model has not yet attained good performance.) You should also describe anticipated next steps and any obstacles that have come up.
• (25%) Related Work (for Discussion). Describe in detail existing work related to your problem, how they are related to each other, and how your work relates to these. We expect this to be comprehensive and thorough, and with at least 5 citations discussed. Note that previous work relating to your healthcare problem may not necessarily have applied AI or Deep Learning, but if AI efforts have been made in this or a very similar and comparable space they should be described.
• (25%) Methods. Describe in detail the medical data that you are using, including the source(s) of the data, relevant statistics, and qualitative examples if appropriate. Then describe the methods that you intend to use in your approach. Make sure to include AI techniques such as type of Deep Learning or Machine Learning, model architecture, training procedures and methods for acquiring final results.

Submission: Please submit your proposal as a PDF on Gradescope.

Submission 3: Project Report

Your final submission will be a report describing the research project in the format of a non-technical clinical journal manuscript. The report is due Nov 18th (Wed). You will be required to follow the formatting guidelines for a Nature Medicine Article which can be found here. You may reuse relevant sections from your Milestone with or without modifications.

Example 1: Yim, J., Chopra, R., Spitz, T. et al. Predicting conversion to wet age-related macular degeneration using deep learning. Nat Med 26, 892–899 (2020). here

• Title, Authors(s)
• (10%) Abstract. A paragraph overview of the problem, methods, clinical impact, and key results. 90-150 words and no references.
• (10%) Introduction. Introduce your problem, and the landscape for why the problem is interesting from a healthcare perspective and what has been done before in this space. Describe your overall plan for approaching the problem, why this is an interesting contribution in the context of the described clinical landscape. Finally include a very short summary of your results (1-2 sentences) avoiding listing many numerical results. Take inspiration from previous Nature Medicine manuscripts.
• (20%) Results. Describe all the relevant results achieved. You should include graphs, tables, or other figures to illustrate the experimental results. If your project had many results but not all results were immediately relevant to the reader, you can add the remaining results to Supplementary Information.
• (30%) Discussion. Make comparisons between key findings from your research and how they relate to existing work in your problem space. Describe and cite previous work. Discuss differences and similarities. Describe the contributions to medicine your work makes, and the clinical impact your research can have. The second-last paragraph should describe limitations of your study. The last paragraph should be a summary of key results, what has been learned, conclusions and avenues for future work
• (25%) online Methods. The methods section should contain sufficient information for others to reproduce your results (if they had your data). Describe in detail the medical data that you are using, including the source(s) of the data, relevant statistics, and qualitative examples if appropriate. Then describe the methods that you use in your approach. Make sure to include all relevant AI techniques and all the experiments that you performed to support your approach. The exact experiments will vary depending on the project, but examples may include performing comparison of your main approach with other baselines or methods, error analyses to investigate the performance of the model, ablation studies to determine the impact of various components of the approach, analyses to provide insight into the effect of different hyperparameter choices, techniques to interpret how the model is working, etc.
• (5%) Writing / Formatting. Your paper should be clearly written and nicely formatted, comparable to a published Nature Medicine Article. Make sure to have References nicely formatted in Nature style. We recommend using a reference manager (Zotero, Mendeley etc.)

Additional Submission Requirements: We also ask you do the following when you submit your project report:

• Authors Contributions. Your report PDF should list all authors who have contributed to your work; enough to warrant a co-authorship position. This includes people not enrolled in the course, such as faculty/advisors if they sponsored your work with funding or data, and significant mentors (including PhD students or postdocs who coded with you, participated in data collection, or helped draft your model on a whiteboard). All authors should be listed directly underneath the title on your PDF. Include a footnote on the first page indicating which authors are not enrolled in the course. All co-authors should have their institutional/organizational affiliation specified below the title, and their role should be described in the Contributions section of the paper.
• Specify the contributions of each author on the paper (section placed after the References). This includes discussion, implementation, and writing for each part of the paper. You should also describe the contributions of any contributors not enrolled in the course.
• Supplementary Material. This should be submitted as a separate file from your paper and is not counted in the max 4,000 word requirement. You may put additional results, visualizations etc. that you wish to share with the teaching team. You may also include a link to the Github repo built for this project.
  What you should not put in your supplementary material:
  • Any of the source code.
• Any code that was used as a base for projects must be referenced and cited in the body of the paper. This includes course assignment code, and fine-tuning example code, open-source, or Github implementations. We recommend using a bibliography entry in the References.
• If you are using this project for multiple classes, submit the other class PDF as well. Remember, it is an honor code violation to use the same final report PDF for multiple classes.

Submission: You will submit your final report as a PDF and your supplementary material as a separate PDF or ZIP file. We will provide detailed submission instructions as the deadline nears.

Project Final Presentation

We will be holding a virtual final along with students from BIODS220 to share the work that you’ve done in your projects, on Nov 18 (Wed). Each project group should present a 4-5 minute slidedeck during the session and will have a choice to present live or record a video. More details will be provided closer to the date.

Grading Breakdown

(10%) Project Proposal
(20%) Project Milestone
(60%) Project Report
(10%) Project Final Presentation

Honor Code

You may consult any papers, books, online references, or publicly available implementations for ideas, knowledge and code that you may want to incorporate into your project and final report, so long as you clearly cite your sources in your submission. However, under no circumstances may you copy or plagiarize another person's text or material. If you are combining your course project with the project from another class, you must also follow all guidelines for this as specified above.If you are combining your course project with the project from another class, you must also follow all guidelines for this as specified above.