Projects

This project automates the retrieval and processing of survey responses from SurveyMonkey using Python. The pipeline integrates with the SurveyMonkey API, extracts survey metadata and response data, and transforms it into a structured format for analysis. The processed data is then exported to Excel, making it accessible for stakeholders. The project leverages API requests, JSON parsing, and data transformation techniques to ensure accurate reporting.

This project chronicles the development of an Infection Prediction Model, assigning health risk scores, vaccine history scores, and a comprehensive infection risk score to patients. By analyzing patient demographics, chronic conditions, and risk factors, the model forecasts infection likelihood, enabling proactive prevention strategies to reduce infection rates and improve outcomes.

This project dashboard analyzes antibiotic use over time, showing prescribing trends, average treatment durations, top prescribed drugs, and resistant organism occurrences. All data is anonymized for privacy, supporting evidence-based decisions and effective antibiotic stewardship.

This project automates data cleaning for vaccination records in SQL Server. Stored procedures remove empty rows, drop irrelevant columns, rename fields, and standardize data types. The process transforms raw Excel imports into clean, analysis-ready datasets, enhancing efficiency and data accuracy in healthcare reporting.

This dashboard visualizes heart disease risk factors by geography. It correlates obesity, cholesterol, smoking, and blood pressure with location, revealing regional patterns. Ideal for guiding prevention strategies and tailoring public health interventions globally.

This project focuses on cleaning and standardizing a dataset about housing trends in Nashville, Tennessee. It involves resolving null values, standardizing inconsistent data formats, splitting and restructuring address fields, removing duplicates, and dropping unnecessary columns to prepare the data for analysis.

This project analyzes healthcare-associated infections across U.S. hospitals, leveraging statistical and machine learning techniques to identify high-risk facilities, benchmark performance against national averages, and uncover infection trends by type and location. These insights aim to support data-driven infection prevention strategies.