I describe myself as a health data scientist and analyst with a passion for turning data into actionable insights that improve healthcare outcomes. My expertise lies at the intersection of programming, statistics, and public health, with strong skills in Python, R, SAS, SQL, Tableau, Power BI, and Excel. I thrive on tackling complex challenges collaboratively, designing innovative solutions, and creating user-friendly visualizations to empower data-driven decision-making. As an MPH candidate in Public Health Data Science at the University of Minnesota, I focus on leveraging machine learning, artificial intelligence, and advanced analytics to address pressing public health issues. I’m particularly passionate about using data to promote health equity and building tools that make quantitative analysis accessible to everyone, regardless of their technical background. When I’m not immersed in data, I enjoy exploring and watching creative videos on the internet, engaging in thought-provoking conversations with friends, and diving into my favorite books. I also find joy in connecting with others who share my vision for a healthier, more equitable world. Explore my work on GitHub and connect with me on LinkedIn. Follow me for updates on X.
In this project, we built and evaluated stroke risk prediction machine learning models (Logistic Regression, Random Forest, Support Vector Machine (SVM), Decision Tree, and XGBoost) in R Markdown and deployed using R Shiny.
This Python solo project focused on predictive modeling for liver disease diagnosis using a synthetic dataset sourced from Kaggle. The primary aim is to leverage machine learning algorithms to identify patterns and factors influencing liver health, aiding in research insights and potential healthcare interventions.
Will post the projects later.
Will post the projects later.
Will post the projects later.
This project explored the impact of allogeneic RBC storage duration on biochemical recurrence timing in prostate cancer patients' post-radical prostatectomy, using SAS for data analysis.
This ShinyLive Dashboard leverages CDC PLACES data to provide county-level health indicators in Minnesota, overcoming the state-level limitations of the CDC BRFSS. It enables actionable insights for targeted public health interventions and resource allocation, including in Quin County CHS, to strengthen local public health responses.
Will post the projects later.
This project utilized the BRFSS 2021 dataset, this project employs machine learning models to predict cardiovascular disease risk. Techniques include Logistic Regression, Decision Trees, KNN, and Random Forest, evaluated by AUC and Brier scores to enhance CVD prevention.
This solo project examined the impact of temporal factors on the outcomes of elective general surgeries. Utilizing a retrospective cohort study design, we explored how the timing of surgeries — including time of day, day of the week, month, and moon phases — affects in-hospital complications. The data analysis was done in SAS.