Long COVID Prediction
University Projects #Data Science#Machine Learning#Research
Featured
NOTEClick this link to view the code and original paper on GitHub.
Overview
A healthcare analytics research project that analyzed COVID-19 patient data to predict Long COVID cases using machine learning and data mining techniques. This collaborative work resulted in three IEEE-published papers, demonstrating the ability to translate complex analysis into actionable healthcare insights.
Key Concepts
- 3 IEEE publications as co-author on peer-reviewed conference papers
- Mined association rules achieving >0.8 confidence scores identifying patterns between demographics and Long COVID symptoms
- Identified that individuals assigned female at birth develop Long COVID at higher rates
- Discovered that cough, headache, and fatigue are the most prevalent symptoms for Long COVID
- Created publication-quality visualizations with Matplotlib supporting research findings
- Collaborated with 4-person research team on data analysis and academic writing
My Contributions
- Performed data mining using the Apriori algorithm in Python
- Preprocessed large datasets using Pandas
- Create data visualizations for data mining results using Matplotlib
Publications
-
“Mining Big Healthcare Data to Predict Long COVID Cases”
- IEEE International Conference on Industrial Technology (ICIT), 2023
- DOI: 10.1109/ICIT58465.2023.10143145
-
“A Data Science Solution for Analyzing Long COVID Cases”
- IEEE International Conference on Information Reuse and Integration (IRI), 2023
- DOI: 10.1109/IRI58017.2023.00046
-
“Data Analytics and Prediction of Long COVID Cases with Fuzzy Logic”
- IEEE International Conference on Fuzzy Systems (FUZZ), 2023
- DOI: 10.1109/FUZZ52849.2023.10309753
Technologies
Python, Pandas, NumPy, Matplotlib, mlxtend, Apriori Algorithm, Data Mining, Association Rule Mining