Resume

SEER-Medicare-Health Data Integration and Visualization Project

• Orchestrated the end-to-end integration of SEER cancer registry data, Medicare claims, and state-level public health datasets using ZIP and FIPS codes to unify disparate sources into a cohesive patient trajectory model from diagnosis through outcomes.

• Cleaned and preprocessed the data using SQL, PostgreSQL, and Python, standardizing formats and resolving inconsistencies across datasets.

Designed and implemented robust ETL pipelines using Apache NiFi, automating ingestion and transformation processes.

• The cleaned data was stored in Google Cloud Storage and then loaded into Google BigQuery, which served as the central data warehouse. Built interactive dashboards and visual reports using Metabase, enabling stakeholders to explore trends, disparities, and outcomes across demographic and geographic

dimensions. This solution facilitated evidence-based decision-making for healthcare researchers and policy planners.

• Unified Health Data Sources: Orchestrated the integration of SEER cancer registry, Medicare claims, and state-level health datasets using Zip and FIP codes, providing a comprehensive view of patient trajectories from diagnosis to outcomes.

• Enhanced Data Integrity: Addressed data quality issues by correcting missing values, eliminating duplicates, and standardizing column names to ensure a reliable dataset for analyzing breast cancer stages and survival times.

• Data Visualization Mastery: Utilized Matplotlib to produce scatter plots, bar charts, and heatmaps, revealing patterns and trends in the data to facilitate deeper insights into breast cancer research.

• In-depth Data Analysis: Employed SQL, Tableau, Excel, and machine learning tools to interpret visualized results, providing critical insights for research, reporting, and strategic oncology decision-making.

• Machine Learning Implementation: Applied various machine learning algorithms, such as Gradient Boosting Classifier and Ordinary Least Squares regression, to assess and correct biases in large-scale datasets, promoting model fairness.

• Predictive Model Development: Created predictive models using advanced machine learning methodologies to forecast cancer outcomes and responses to treatment.

• Transparency through Explainable AI/ML: Implemented explainable AI/ML approaches to ensure clarity and transparency in model predictions, aiding clinicians and researchers in decision-making.

• Rigorous Data Validation: Conducted thorough quality assurance and data validation to maintain the accuracy and reliability of the data utilized in analyses and modeling.

• Advanced Data Collection Techniques: Executed sophisticated data scraping methods to acquire extensive datasets from SEER, Medicaid, AHD, USDA, and CMS, vital for informed decision-making in health research.

• Contributions to Scientific Research: Played a key role in drafting research papers and communicating complex data analyses to the scientific community, enhancing understanding of public health impacts.

• Leadership in Cross-functional Collaboration: Worked closely with cross-functional teams to align data

initiatives with broader research objectives, ensuring successful project execution and impactful results.

• Expanded Scope: Data Governance, Epidemiology, and Public Health Integration In addition to technical accomplishments, this project had a strong emphasis on data governance, epidemiological analysis, and public health impact.

• Data Governance Excellence: Developed and enforced policies and procedures for managing data privacy, access control, and compliance with HIPAA and other regulatory frameworks. Led the creation of a public health data governance framework that defined clear roles, responsibilities, and processes for

ensuring data accuracy, consistency, and security.

• Epidemiological Analysis: Collaborated closely with epidemiologists to define cohort selection criteria, perform population-level health trend analysis, and calculate survival rates, disease incidence, and treatment response across various demographic and geographic groups.

• Public Health Impact: The project supported strategic decision-making for public health interventions by linking health data with geospatial and socioeconomic indicators. These insights were used to identify disparities in healthcare access and outcomes, guiding policy recommendations.

• Stakeholder Collaboration: Acted as a liaison between technical teams and public health officials, translating data requirements into scalable solutions and ensuring that analytical outputs aligned with real world healthcare priorities.

• Transparency and Reproducibility: Maintained comprehensive documentation of data transformation processes, pipelines, and modeling decisions to support reproducibility and knowledge transfer.

Additional Contributions and Innovations

• Proactive Problem-Solving: Applied expert problem-solving skills to address and resolve technical and data related issues as they arose, ensuring minimal downtime and maintaining high standards of data quality and system performance.

• Stakeholder Engagement and Communication: Regularly engaged with stakeholders through meetings and

presentations, providing updates on project status, explaining complex technical details, and gathering feedback to refine data solutions. Developed comprehensive documentation to assist users and technical teams in understanding and utilizing the data systems.

• Innovative Technology Integration: Explored and integrated new technologies and methodologies to enhance

the capabilities of the data infrastructure. This includes cloud computing solutions for scalable storage and processing, as well as advanced analytical techniques for predictive modeling and machine learning.

• Ethical Data Governance: Ensured that all data handling practices comply with ethical standards and legal requirements, particularly concerning data security and patient confidentiality. Implemented robust data governance frameworks to oversee the proper management of sensitive health data.