• Data wrangling, modeling data from electronic health records and public databases. Interpret and write results for publication. (Data cleaning in python, statistical modeling in R and SAS, and running data by distributed computing)• Project 1. Risk Prediction for Acute Kidney Injury in Patients Hospitalized with COVID-19. Monitor model drift and update models upon new COVID variants.• Project 2. Using Dipstick Urinalysis to Predict Development of Acute Kidney Injury in Patients with… Show more • Data wrangling, modeling data from electronic health records and public databases. Interpret and write results for publication. (Data cleaning in python, statistical modeling in R and SAS, and running data by distributed computing)• Project 1. Risk Prediction for Acute Kidney Injury in Patients Hospitalized with COVID-19. Monitor model drift and update models upon new COVID variants.• Project 2. Using Dipstick Urinalysis to Predict Development of Acute Kidney Injury in Patients with COVID-19. • Project 3. Association of Inflammatory Biomarkers with Immunosuppression Management and Outcomes in Kidney Transplant Recipients with COVID-19.• Manage clinical trial data in REDCap. Prepare reports for data and safety monitoring board meetings.• Provide statistical support to clinicians, including developing statistical analysis plans, performing statistical analysis, and interpreting the results. Show less

• Collaborate with the bioinformatics team to build models to reveal cell identity (R, unsupervised principal component and clustering analysis; Python, time series analysis, data analysis with NumPy, Pandas, and visualization with Matplotlib and Seaborn). • Extract data, conduct data cleaning, wrangling, and integration from disparate sources (e.g., csv, txt, xlsx, avi, etc). Troubleshoot data quality issues, apply statistical methods using software packages in R to build predictive… Show more • Collaborate with the bioinformatics team to build models to reveal cell identity (R, unsupervised principal component and clustering analysis; Python, time series analysis, data analysis with NumPy, Pandas, and visualization with Matplotlib and Seaborn). • Extract data, conduct data cleaning, wrangling, and integration from disparate sources (e.g., csv, txt, xlsx, avi, etc). Troubleshoot data quality issues, apply statistical methods using software packages in R to build predictive and prescriptive models to obtain insights and export data visualization in R (e.g., ggplot2) and Tableau. • Lead a team of 3 specialists to perform high-throughput screening of genetic deficits in learning and memory using operational metrics and reports. Develop analytical project plans and integrate information with collaborative teams from analytical efforts. Provide analytical reports for timely evaluation to leaders and collaborators and routinely give presentations to communicate ideas and findings across multiple functional groups.• Mentored 3 summer students on scientific projects. Show less

Applied hypotheses driven study to understand obsessive-compulsive behavior and obesity which resulted in a high-profile publication.

Studied therapeutic targets for diabetic neuropathy which resulted in a high-profile publication.