Data
SUMMARY
Data Management | Data Visualization | Health Economics & Outcomes Research (HEOR) | Health Informatics | Machine Learning | Meta-Analysis | Python | R | Real-World Data (RWD) | Statistical Analysis Plans (SAP) | SQL
Adept at using R, Python, and SQL to generate real-world-evidence (RWE), guide policy, inform decision-making, and test funded research questions.
Data Analysis
Skilled using R, Python, and SQL to wrangle, visualize, and analyze primary data, secondary data, and RWD, and developing SAPs that follow CDISC standards.
Examples include:
- Statistical modeling to optimize measurement outcomes.
- Using EHRs to screen and monitor patients.
- HEOR to generate policy for the American Heart Association (AHA).
- 20 meta-analyses in leading journals such as Sports Medicine and Sleep Medicine Reviews.
Data Modelling
Advanced ability to model research outcomes via an advanced understanding of upstream and downstream factors that may influence a statistical model, including interactions between effect modifiers and effects moderators.
One funded project uses machine learning to identify which behavioral phenotype is most associated with cardiometabolic disease risk in young adults, then use the outcomes to strategically an intervention.
Time-Series
Skilled at managing, reducing, analyzing, and interpreting large-scale, time-series physiological and behavioral data.
Such as tracking continuous blood pressure by statistically modelling data from impedance cardiography (ICG), electrocardiography (ECG), photoplethysmography (PPG) biotechnologies, and time-aligning with additional physiological data collected at differing temporal resolutions.