SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

ACKNOWLEDGEMENT
UBC’s Point Grey Campus is located on the traditional, ancestral, and unceded territory of the
xwməθkwəy̓əm (Musqueam) people. The land it is situated on has always been a place of learning for
the Musqueam people, who for millennia have passed on their culture, history, and traditions from one
generation to the next on this site.
COURSE INFORMATION
Credit
Course Title Course Code Number
Value
Health Data • Integrated Seminar & Hands-on Activities: 1 Session per week (3
Science: AI and hours)
3
Knowledge • Time: Thu 11 am – 2 pm (Sept–Dec 2026)
Translation • Room: TBD (In-person)

PREREQUISITES
No Prerequisites: Zero to AI Co-Pilot. This course has no official prerequisites. We welcome students
from all disciplines. You do not need prior experience with R, Python, or Statistics. Instead, we teach you
to use AI-Augmented Workflows (e.g., Large Language Models [LLMs]) to bridge the technical gap. You
will learn to use AI as a “coding co-pilot” to generate, debug, and translate code, allowing you to focus
on the high-level logic of health data science. Whether you are a total beginner or a coding expert, this
curriculum is designed to help you build a professional portfolio from the ground up.
CONTACTS
Course Instructor(s) Contact Details Office Location Office Hours
Ehsan Karim [Link]@[Link] By By appointments, or as posted on
The typical response time appointments canvas.
is within 48 hours on
weekdays.

COURSE INSTRUCTOR BIOGRAPHICAL STATEMENT

Dr. M. Ehsan Karim is an Associate Professor in Health Data Science at the UBC School of Population
and Public Health (SPPH), a Scientist at the Centre for Advancing Health Outcomes, an associate
member of the Department of Statistics (UBC) and a previous Michael Smith Foundation for Health
Research (MSFHR) Scholar. He obtained his PhD in Statistics from the University of British Columbia,
and completed his postgraduate training in the Department of Epidemiology, Biostatistics, and
Occupational Health at McGill University. His current research focuses on causal inference, real-world
observational data analyses, and applications of machine learning approaches in epidemiologic
studies.
OTHER INSTRUCTIONAL STAFF
The teaching team: TBA.

To communicate with the computing TA, come to weekly classes and specified office hours (as
announced in Canvas).

University of British Columbia

SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

COURSE DESCRIPTION
This interdisciplinary course bridges the gap between traditional epidemiology and modern data science,
guiding students from basic literacy to advanced AI-augmented workflows without requiring prior coding
prerequisites. Adopting a “Zero to AI Co-Pilot” pedagogy, students will utilize cloud-native computing
environments to ethically leverage Large Language Models for generating and auditing code in both R
and Python, while mastering reproducible research methods using GitHub. The curriculum emphasizes
the “last mile” of knowledge translation, equipping learners to transform real-world health data into
professional portfolios featuring dynamic scientific writing, interactive web dashboards, and data-driven
visual stories.

COURSE STRUCTURE
This course integrates theoretical foundations with the practical realities of modern health data science.
By leveraging advanced computational tools, including LLMs for coding assistance and git-based
workflows for collaboration, students will learn to navigate the full lifecycle of a research project.
Through engaging lectures and integrated hands-on activities, you will move beyond simple analysis to
master the art of communication: transforming complex health data into interactive dashboards, visual
stories, and publication-ready reports. The course equips students with the skills to audit AI-generated
code, manage secure data environments, and effectively communicate findings to diverse healthcare
audiences. Features of this course include:

• The Full Data Lifecycle: This curriculum covers the entire research pipeline—from ethical data
access and cleaning to secure cloud computing and final publication.
• Reproducible Science: A dedicated focus on modern auditability tools, including Git and
environment management, ensuring students learn how to build analyses that are transparent,
shareable, and robust. We utilize a Literate Programming methodology where analysis, code,
and interpretation are interwoven into a single reproducible document (Quarto/RMarkdown).
• AI-Augmented Workflows: Students will learn to ethically leverage LLMs as coding co-pilots to
debug, refactor, and translate code between R and Python. Develop Critical AI Literacy by
rigorously auditing LLM-generated code for security vulnerabilities, ‘hallucinations,’ and
reproducing systemic health biases.
• Knowledge Translation (KT): A strong emphasis on the “last mile” of data science, teaching
students to transform raw results into interactive dashboards, visual stories, and policy-ready
reports.
• Real-World Health Data: Hands-on activities utilize messy, real-world datasets (e.g., NHANES)
rather than toy examples, forcing students to navigate actual challenges in privacy, cleaning, and
interpretation.

SCHEDULE OF TOPICS
Week # Integrated Seminar Topics Activities Weekly deadlines (Fri)

# 1 (Sept Introduction to Health Data and • Introduction to open (no assignment

10th) Open Data Sources data sources (NHANES, submission)
Kaggle, WHO, WBOD,

University of British Columbia

SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

Week # Integrated Seminar Topics Activities Weekly deadlines (Fri)

• Overview of health data BC data) and the

research available data formats
• Importance of knowledge • Demonstration of
translation health data access and
• Privacy, and Security usage
• Indigenous Data • Hands-on session on
Sovereignty: OCAP® and navigating these data
CARE Principles sources and
• Ethics of Generative AI in downloading datasets
Health (Hallucinations and
Bias)
# 2 (Week Overview of IDEs and Notebooks • Setting up and using Submit assignment 1
of Sept • Navigating and using RStudio Notebooks by Friday 4 pm.
17th) Integrated Development • Creating and organizing
Environments (IDEs) a project
effectively • Writing and publishing
• Project organization and a simple notebook with
GUI tools markdown in Google
• Basics of markup languages Colab, Kaggle notebook
• Creating and publishing Toolkits: RStudio,
notebooks using RMarkdown, Quarto,
RMarkdown/ Quarto, Google Colab, Kaggle
Google Colab, Kaggle notebook
notebook
# 3 (Week Understanding R • Writing basic R scripts Submit assignment 2
of Sept • Introduction to R for data import/export by Friday 4 pm.
24th) programming language • Practical exercises on
• Data import/export conditions, loops, and
techniques in R functions in R
• Basic programming • Exploring LLM tools to
constructs: conditions, assist with R
loops, functions programming
• Seeking help from different Toolkits: R, RStudio, Local
sources to debug LLM
• Using LLMs to navigate R
# 4 (Week Introduction to version control • Creating and managing • Milestone 0:
of Oct 1st) • Introduction to version a GitHub repository form group for
control (VC) systems and • Hands-on practice with the term
their importance commit, push, and pull project.
• Working with VC GUIs (e.g., operations • Submit
GitHub Desktop) • Collaborative project assignment 3
• Setting up repositories and setup with branching by Friday 4
understanding commit, and merging pm.
push, pull operations

University of British Columbia

SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

Week # Integrated Seminar Topics Activities Weekly deadlines (Fri)

• Managing project history Toolkits: GitHub Desktop,

and collaboration: GitHub
branching, merging, forking,
peer-review
# 5 (Week Working with Python • Translating R code to • Submit
of Oct 8th) environments Python with LLM assignment 4
• Understanding difference assistance by Friday 4
between Python and R • Setting up and pm.
• Using LLMs to navigating Python IDEs • Milestone 1:
translate/update code to (PyCharm and VS Code) select data
Python • Writing, executing, and source.
• Introduction to Python IDEs publishing Python Proposal
(e.g., PyCharm, VS Code) scripts in Jupyter submission by
• Working with Jupyter Notebooks Friday 4 pm.
Notebooks in Python • Working with the
• Working with reticulate reticulate package to
integrate R and Python
Toolkits: renv, conda,
PyCharm, VS Code,
reticulate, Jupyter
Notebooks, Local LLM
# 6 (Week Principles of data visualization • Creating basic and Submit assignment 5
of Oct 15th) • Understanding encoding advanced plots in R by Friday 4 pm.
channels and designing using ggplot2
plots • Creating interactive
• Creating effective visual charts in Python using
stories and interactive Plotly and Bokeh
charts • Mapping data using
• Mapping and layout design Folium (Python) and
for data visualization customizing map
layouts
• Using Altair for
declarative statistical
visualizations in Python
Toolkits: ggplot2 (R), Plotly
(Python), Bokeh (Python),
Folium (Python), Altair
(Python)
# 7 (Week Exploratory Data Analysis (EDA) • Performing EDA using R • Submit
of Oct 22th) • Introduction to Exploratory and Python assignment 6
Data Analysis • Practical exercises on by Friday 4
• Data analysis workflow identifying patterns pm.
and relationships in • Milestone 2:
datasets Initial data

University of British Columbia

SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

Week # Integrated Seminar Topics Activities Weekly deadlines (Fri)

• Techniques for • Tabulating data and exploration by

understanding relationships cross-tabulate Friday 4 pm.
in data • Documenting EDA
• Creating Table 1 processes for
• Ensuring reproducibility and reproducibility
transparency in research Toolkits: R, Python,
Pandas, Matplotlib,
Seaborn
# 8 (Week Introduction to Shiny apps and • Creating a basic Shiny Submit assignment 7
of Oct 29th) Dashboards app by Friday 4 pm.
• Building interactive • Customizing Shiny apps
dashboards with Shiny (R) with interactive
and Dash (Python) elements
• Customizing and deploying • Deploying Shiny apps
Shiny apps on the web
• Best practices for dashboard Toolkits: Shiny (R), Shiny
design Server, GitHub pages
# 9 (Week Communication of Scientific • Creating presentations • Submit
of Nov 5th) Findings using Quarto assignment 8
• Interpreting and presenting • Dynamic presentation by Friday 4
data science findings to to run code live and pm.
various audiences show updated results • Milestone 3:
• Effective oral and written on the spot. Project update
presentation of scientific • Peer-review session for (polished
results draft presentations output, e.g.
• Using LLMs to draft plain- Toolkits: Quarto, Zotero dashboard) for
language summaries for and bibtex peer-feedback
non-technical stakeholders by Friday 4
• Using citation managers pm.
effectively
• Peer-review practices
# 10 (Week Writing and Publishing Reports • Formatting and writing • Submit
of Nov • Formatting reports for a report using assignment 9
12th) scientific journals RMarkdown/Quarto by Friday 4
• Dynamic reporting and and rticles package pm.
automated workflows • Integrating citation • Milestone 4:
• Publishing with managers into the learn from
RMarkdown/Quarto and workflow others. Submit
embedding interactive • Embedding interactive peer-feedback
elements charts and dashboards by Friday 4 pm
• Inform the public with in reports (provide clear
interactive dashboards. Toolkits: RMarkdown, direction of
• Use Distill to update results bookdown, Quarto what to
in a web-friendly format. improve).

University of British Columbia

SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

Week # Integrated Seminar Topics Activities Weekly deadlines (Fri)

# 11 (Week Going beyond EDA toolkits for • Building and Submit assignment 10
of Nov Health Data Analysis evaluating by Friday 4 pm.
19th) Advanced topics (selected topics predictive models
may be focused) in R and Python
• Moving beyond manual • Using AutoML tools
tuning: how to use in R and Python to
Automated Machine automate model
Learning (AutoML) to selection and
select and optimize tuning
models efficiently. Toolkits: scikit-learn, SciPy
• Difference between and Statsmodels (Python),
prediction and causal tidymodels (R), H2O
inference goals in health AutoML (R)
data analysis.
• Introduction to cloud
computing resources for
health data (commercial
platform, Digital
Research Alliance of
Canada, UBC ARC,
Docker).
# 12 (Week Milestone 5: Term Project
of Nov presentations (part 1), Live
26th) Q&A and peer review.
# 13 (Week Milestone 5: Term Project Peer-review feedback
of Dec 3rd) presentations (part 2), Live by Friday 4 pm.
Q&A and peer review.
Data Science Portfolio
Project / Term project
submission deadline:
Dec 11th (Fri 4 pm).

LEARNING OUTCOMES
• Describe the fundamental concepts of health data research and the role of knowledge
translation.
• Recognize ethical, privacy, and security considerations in handling health data and AI tools.
• Identify and access open data sources such as NHANES and Kaggle.
• Navigate and use Integrated Development Environments (IDEs) like RStudio and Jupyter
Notebooks.
• Create and publish dynamic, reproducible notebooks using markup languages.
• Write and execute basic scripts in R and Python for data manipulation and interoperability.

University of British Columbia

SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

• Set up and manage version control systems using GUIs like GitHub Desktop. Manage
reproducible software environments to ensure analyses are portable and auditable.
• Critically evaluate and audit AI-generated code for errors, bias, and security vulnerabilities.
• Create effective visual stories and interactive charts using R and Python.
• Perform exploratory data analysis (EDA) to identify patterns and relationships in health data.
• Present data science findings clearly to diverse audiences and prepare scientific reports for
publication.
LEARNING ACTIVITIES
Weekly Activities / Assignments:
Each week, students will complete assignments that provide hands-on experience with the tools and
concepts discussed in the lectures. These assignments will include tasks such as accessing and navigating
open data sources, using IDEs, programming in R and Python, implementing version control, creating
data visualizations, conducting exploratory data analysis, and developing interactive dashboards.
Weekly assignments are designed as low-stakes formative assessments. To support your learning curve
and mental health, we adopt a ‘Best 5 of 10’ policy, allowing you to prioritize depth of learning over
weekly perfection.
Final Term Project:
In the final weeks of the course, students will engage in a term project designed to synthesize all the
skills and knowledge acquired throughout the term. The project will involve:
• Proposal submission by the end of Week 5.
• Initial data exploration by the end of Week 7.
• Project update review for peer-feedback by the end of Week 9. Reproducible and transparent
codes should be included in this submission so that the peer-reviewers can verify and comment.
• Receive feedback by the end of Week 10.
• Presentation of nearly final work by the end of Week 13 and receiving more specific instructor
and peer-feedback.
Scope & Expectations:
Focus: This project prioritizes visualization and reporting (Weeks 8–10) and reproducible
workflows.
Undergraduate Students: Are not expected to invent a novel machine learning algorithm or
prove a new medical causal link.
Graduate Students: Are expected to interpret the results, contextualizing their findings within
existing epidemiological evidence.
Auditability: A significant portion of the grade is dedicated to reproducibility. The code must run
from start to finish on a fresh machine (or the TA’s machine) without errors and without manual
intervention.

Students will be required to identify a relevant health data research question, apply appropriate data
science techniques, and effectively communicate their results through a final presentation and written
report. Detailed milestones and guidelines will be provided to ensure structured progress and high-
quality outcomes.

University of British Columbia

SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

Open Science & Portfolio Policy: A key goal of this course is to ensure you leave with more than just a
grade. By the end of the term, you will build a public-facing Data Science Portfolio (hosted on GitHub
Pages) featuring real-world health data analysis. This is a tangible asset you can link on your CV/LinkedIn
to demonstrate your skills in reproducibility, visualization, and AI-assisted coding to future employers or
research supervisors. The Default: We encourage all students to publish their final projects as public
repositories (e.g., GitHub Pages) or dashboards. Your Privacy: We recognize that some students may
prefer to keep their work private. If you do not wish to publish your work publicly, you may submit your
project as a private repository (shared only with the teaching team) for grading purposes without any
penalty. Please communicate with the instructor early on (week 4) if you opt for this.
LEARNING MATERIALS
There is no required textbook to buy. The course will offer online texts.

ASSESSMENTS OF LEARNING
• Weekly Activities / Assignments (50%): There are 10 weekly assignments scheduled throughout
the term. These Canvas-based assignments mirror the format of the OER’s embedded
“Knowledge Check” quizzes and coding exercises to reinforce weekly concepts. To provide
maximum flexibility, only your best 5 assignment grades will count toward your final grade. You
may choose to complete only 5, or complete all 10 to drop your lowest scores. Each counted
assignment is worth 10%.
o In data science, code that only runs on your machine is not finished. We grade on
reproducibility. Your code must run smoothly on a fresh machine (e.g., the TA’s) without
manual fixes.
o Tip: Avoid absolute paths such as “C:/Users/Me/Downloads”. Use relative paths!
o Policy: Assignments that break this rule will be returned for a “Reproducibility Fix” and
may incur a grade deduction. We want you to master this skill early!
• Term Project / Data Science Portfolio: A major capstone project broken into the following graded
milestones to ensure steady progress:
o Milestone 1: Project Proposal (5%): Identification of dataset, research idea, and
feasibility check.
o Milestone 2: Preliminary Analysis (5%): Initial data cleaning, exploratory visualizations,
and a runnable GitHub repository.
o Milestone 3: Report (5%): A “nearly final” version of your analysis and slides submitted
for peer review.
o Milestone 4: Peer-Review Contribution (5%): This milestone emphasizes collaborative
learning. You will be graded on the quality and constructiveness of the feedback you
provide to your peers on their Milestone 3. Full marks are awarded for completing the
rubric with specific, actionable comments. Note: Generic feedback (e.g., 'Good job') will
not receive credit.
o Milestone 5: Presentation (5%): Communicating findings to peers in a scientific seminar
format, with a focus on clear Knowledge Translation. Presentations will take place in-
class during Weeks 12 and 13.
o Final Portfolio (25%): The final report, and fully auditable code repository.

University of British Columbia

SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

Late Submissions: Assignments: Due to the flexibility of the ‘Best 5 of 10’ grading scheme, late
submissions for weekly assignments are not accepted. Missed assignments will simply count as one of
your dropped grades. Final Project: The Final Portfolio must be submitted via Canvas by the deadline.
Late submissions will be penalized 10% per day (e.g., 1 day late = 10% deduction; 2 days late = 20%
deduction). Submissions more than 5 days late will not be accepted without prior arrangement.
Extensions are only considered for documented extenuating circumstances. Academic Concession:
Requests for extensions due to conflicting responsibilities or unforeseen events will be handled in
accordance with UBC Policy V-135 (Academic Concession). Please contact the instructor as soon as the
need arises.
UNIVERSITY POLICIES
UBC provides resources to support student learning and to maintain healthy lifestyles but recognizes
that sometimes crises arise and so there are additional resources to access including those for
survivors of sexual violence. UBC values respect for the person and ideas of all members of the
academic community. Harassment and discrimination are not tolerated nor is suppression of
academic freedom. UBC provides appropriate accommodation for students with disabilities and for
religious observances. UBC values academic honesty and students are expected to acknowledge the
ideas generated by others and to uphold the highest academic standards in all of their actions.
Details of the policies and how to access support are available on the UBC Senate website.
OTHER COURSE POLICIES
Plagiarism: Students are expected to review the Student Discipline section of the UBC Calendar and
know what constitutes plagiarism and academic misconduct, and that such activities are subject to
penalty.
Generative AI Policy (Permissive but Regulated): Generative AI tools (e.g., ChatGPT, GitHub Copilot) are
permitted and encouraged in this course. However, you must adhere to the AI-Augmented Workflow
guidelines: Attribution: You must acknowledge the use of AI tools in your submission (e.g., ‘Code block X
was generated by Copilot and debugged by me’). Accountability: You are fully responsible for any errors,
biases, or security flaws in the code you submit. ‘The AI made a mistake’ is not a valid excuse.

LEARNING ANALYTICS
Learning analytics includes the collection and analysis of data about learners to improve teaching and
learning. This course will be using Canvas that capture data about student’s activity and provide
information that can be used to improve the quality of teaching and learning. In this course, the
instructor plans to use analytics data to:
• View overall class progress
• Track students’ progress in order to provide them with personalized feedback
• Review statistics on course content being accessed to support improvements in the course
• Assess the student’s participation in the course.

LEARNING RESOURCES
• All course materials will be available on the course website.

University of British Columbia

SPPH_V 381H Syllabus w2026

Selected Topics - Health Data Science: AI and Knowledge Translation

• Required Hardware (BYOD Policy): This course adopts a 'Cloud-First' approach to ensure
technological equity. Because we utilize cloud-native environments (Google Colab, Kaggle) for our
advanced AI and data science workflows, you do not need a high-performance computer. Any
device capable of running a modern web browser (including Chromebooks, older laptops, or
tablets with a keyboard) is sufficient to complete all course activities. BYOD: Please bring your
device to every class. Come fully charged, as classroom outlets may be limited. Need a Device?
Students who do not have access to a portable device can borrow one from the UBC Library.
Please review the borrowing policies and availability here:
[Link]

COPYRIGHT
All materials of this course (course handouts, lecture slides, assessments, course readings, etc.) are
the intellectual property of the Course Instructor or licensed to be used in this course by the copyright
owner. Redistribution of these materials by any means without the permission of the copyright
holder(s) constitutes a breach of copyright and may lead to academic discipline.
The instructor/TAs do not permit students to record class sessions/activities. The class/TA sessions
will be recorded by the instructor/TAs, and only the necessary parts will be released within the class
for viewing outside of the class sessions. If you have an objection about parts of these recordings,
contact the instructor immediately.
Version: Jan 13, 2026

University of British Columbia