About Me
Data analyst and computational biology researcher with experience in public data analysis, data cleaning, statistical modeling, and machine learning workflows. Has worked on healthcare and histology image classification …
Data analyst and computational biology researcher with experience in public data analysis, data cleaning, statistical modeling, and machine learning workflows. Has worked on healthcare and histology image classification projects using Python, SQL, Excel, and related data analysis tools, and has presented findings to technical and non-technical audiences.
Experience
Data Analyst
• Obtained publicly available datasets from sources like the Census Bureau based on criteria of race and ethnicity data availability and language data availability for client projects
• Maintained a running list of data sources for the final product launch
• Scraped web pages to add for public use data
• Supported the building of key performance metric definitions and measures based on social determinants of
health outlined by the client’s needs
• Cleaned and joined large public datasets for data ingestion. Using that data, basic statistics and graphs were
generated to show relevant trends of the project to the client
• Used Medicaid data and HCPCS/CPT codes to determine sample population needed for HEDIS measures
• Prepared PowerPoint and Excel Workbooks for internal presentations
• Prepared client deliverables in the form of PowerPoints, Excel Workbooks or code to fit company Quality and Risk Management standards
Data Analyst Intern/Full-time
Obtained publicly available datasets from sources like the Census Bureau based on criteria of race and ethnicity data availability and language data availability for client projects.
Maintained a running list of data sources for the final product launch.
Scraped web pages to add for public use data.
Supported the building of key performance metric definitions and measures based on social determinants of health outlined by the client’s needs.
Cleaned and joined large public datasets for data ingestion.
Generated basic statistics and graphs to show relevant trends of the project to the client.
Used Medicaid data and HCPCS/CPT codes to determine sample population needed for HEDIS measures.
Prepared PowerPoint and Excel Workbooks for internal presentations.
Prepared client deliverables in the form of PowerPoints, Excel Workbooks or code to fit company Quality and Risk Management standards.
Junior Computational Biology Research Assistant
Obtained Glioblastoma Multiforme (GBM) data of glioma whole slide images (WSI) from The Cancer Genome Database.
Developed an annotation protocol for WSI for the pathologist and the engineer to maintain consistency during the annotation phase and training phase.
Initiated a design of experiments and an effective workflow with the pathologist to differentiate genetic mutations of gliomas through WSI.
Executed data cleaning, which included sectioning each WSI into predetermined sized tiles to remove white space, adipose tissue or other tissue tiles with no cellular information.
Normalized the stain coloring and explored preliminary features to be extracted before training phase.
Refactored model developed on soft tissue sarcoma (STS) data for GBM data.
Prepared detailed presentations and communicated key concepts of basic machine learning concepts and their relevance to the experimental setup to non-engineering personnel.
Undergraduate Student Researcher
Divided STS tissue image tiles into training, validation and testing data sets for initial experiments.
Visualized ROC, AUC, and confusion matrix of data to determine clustering based on features obtained after training.
Utilized training data feature clusters using tSNE after PCA was implemented globally.
Devised literature searches on weakly supervised models and FNCLCC grading system used in neural networks, including methods to generalize the model from image tile level to WSI level.
Data Analytics Intern
Isolated most recurrent water-borne disease from surveyed data from hospitals in six divisions of Mumbai, India investigating the presence of waterborne illnesses, such as diarrhea and cholera.
Created maps of surveyed data from hospitals in six divisions in Mumbai, India investigating the presence of waterborne illness in R.
Utilized theory of Ordinary Least Squares (OLS) regression and linear mixed-effects model to inform development of a future model.
Developed literature review and data sets on waterborne illnesses based on precipitation, infrastructure access, and climate changes.
Math and Statistics Tutor/Grader
Assisted students in understanding various math concepts ranging from pre-college math to Calculus II.
Assessed students’ knowledge and led them to understand concepts for themselves.
Worked with other tutors and professors to provide effective tutoring for various learning styles.