Welcome to my GitHub! I'm a Data Science student at Boston University with a passion for applying technology to real-world impact, especially at the intersection of AI and public health.
- 🎓 Undergrad @ Boston University | Computing & Data Science (CDS)
- 🤖 AI + Public Health experimenter, especially interested in how machine learning can drive equitable health outcomes
- 💡 Current experiences:
- Break Through Tech AI Fellow @ MIT x Cornell Tech
- External Outreach Director @ Women in Computer Science (BU WiCS)
- Pharmacy Technician @ CVS
- 💡 Past experiences:
- IT Intern @ Charles River Associates
- Underclassmen Rep @ BU WiCS
- AI for Early Disease Detection — using machine learning to identify patterns in medical imaging and clinical data
- Predictive Modeling in Public Health — forecasting outbreaks, risk factors, and long-term health outcomes
- Medical Data Science — working with EHRs, diagnostic datasets, and real-world health data
- Deep Learning in Healthcare — exploring CNNs for medical imaging and NLP for medical records
- Data-Driven Health Equity — designing tools that support accessible and inclusive care
| Project | Description | Tools |
|---|---|---|
| 🌍 Healthy Life Expectancy Prediction | Predicting healthy life expectancy at birth using the World Happiness Dataset. A supervised regression problem using Gradient Boosted Decision Trees to identify key national indicators that influence long-term health outcomes. https://github.com/RobaSr/health-life-expectancy-at-birth-prediction | pandas, scikit-learn, XGBoost, matplotlib |
| 🧠 AI Early Autoimmune Disease Detection Pipeline | An end-to-end AI pipeline for early detection of autoimmune diseases using NHANES health survey data. Includes data cleaning, feature engineering, model training, evaluation, and risk prediction to identify individuals at high risk before clinical diagnosis. Designed with a modular, scalable machine learning pipeline architecture. | python, machine learning, NHANES, data pipeline, healthcare AI |
| 📊 Public Health Dashboard (coming soon) | Visualizing regional health disparities using public datasets and geospatial analysis. https://github.com/RobaSr/Public-Health-Dashboard | Plotly, pandas, GeoPandas |
Python • Pandas • NumPy • scikit-learn • TensorFlow • Matplotlib • Seaborn
- 🔗 [LinkedIn] www.linkedin.com/in/roba-srour
- 📬 srourroba1@gmail.com
Thanks for stopping by! 🌱