Data Science
This course provides a foundational understanding of how data science integrates into interdisciplinary medical science research, focusing on its application to real-world healthcare challenges. Students will learn to apply principles of research design, academic integrity, and ethical research practices to data-driven methodologies. The course emphasizes the importance of data visualization and effectively communicating research findings to diverse audiences, ensuring clarity and impact. Additionally, students will critically evaluate data sets, using their analysis to inform decision-making while identifying the limitations and potential improvements in current research practices.
Meet the Prof
Course Objectives
01
Commenting on Code Assignment
We were tasked with adding detailed comments to the code we learned in class to demonstrate our understanding of each function and its purpose. This exercise involved explaining every line of code, from basic operations like creating vectors and data frames to more complex analyses like regression and visualization. By commenting on the code, we ensured that we not only knew how to run it but also understood its logical flow and the rationale behind each step. This process reinforced my ability to communicate the technical aspects of data analysis clearly and concisely.
02
Oral Exam
We had an oral exam focused on understanding the codes we learned throughout the course, including data manipulation, statistical analysis, and visualization in R. To prepare, I compiled a comprehensive cheat sheet that outlined each code, its purpose, and the syntax used. This helped me grasp the logic behind functions like linear regression, data frame operations, and matrix manipulations. The cheat sheet was an essential tool for quick reference, ensuring I could effectively explain how each code worked during the exam.
03
Research Presentation
We were tasked with developing a research question and we decided to compare health outcomes and quality of life (QOL) between individuals prescribed Ozempic for on-label (type 2 diabetes) versus off-label (weight loss) use. We designed a prospective cohort study involving adults in Canada, intending to use electronic health records (EHRs) for data collection. Our approach included measuring BMI changes and QOL scores, using linear regression to predict how weight loss might influence QOL while adjusting for baseline differences. The aim was to compare the impact of weight loss on QOL for on-label versus off-label Ozempic users.
Reflection
1
What I learned
learned how data science can be applied to medical research, with an emphasis on using R for data analysis, visualization, and statistical modeling. I gained a deeper understanding of research design, ethical research practices, and data interpretation, especially in the context of healthcare.
2
Skills I developed
I developed skills in analyzing and visualizing data using R, understanding statistical concepts like p-values, power, and bias-variance tradeoff, and critically evaluating datasets for data-driven decision-making. Additionally, I enhanced my ability to effectively communicate research findings to different audiences.
​
​
​
​
​
3
How will I use it in the future
In the future, I will use these skills to design robust research projects, analyze healthcare data, and communicate insights clearly. Specifically, for my capstone project, I plan to use my knowledge of data analysis and research design to evaluate diagnostic gaps in Alzheimer’s disease, ensuring that my findings are both statistically valid and practically meaningful for improving healthcare outcomes.