- Helped lead efforts to develop an automated pipeline to extract longitudinal clinical information from Electronic Medical Records (EMR), including unstructured clinical note texts, covering over 3M patients and 56M clinical notes- Used a combination of Deep Learning, NLP, classical machine learning, and rule-based algorithms to achieve an accuracy rate of over 90% in detecting Oncology and Rare Disease patients, and associating this with other meaningful clinical data (Medications, Phenotypes, Procedures, Lab Values, Lies of Therapy, Demographics, Genetics, etc)- Collaborated with clinical teams to author RWE and HEOR publications in various cancer TAs (Heme, Lung, Breast, Prostate, Myeloma), and served as a data consultant with Biopharma partners on research projects and licensing projects to facilitate early drug discovery efforts- Led a small team within a larger group working on this data pipeline, focused on expanding the data extraction pipeline to extract more specific clinical data elements (Cytogenetics, Cancer-Specific Biomarkers, Rare Disease-specific information)- Developed Predictive Analytics workflows to identify pre-diagnostic patients in Oncology, and to identify pediatric patients with GC-assessed incidations for genetic testing, to enable real-world clinical use cases for our datasets- Led efforts to maintain clinical datasets with clear mappings to known ontologies (HPO, LOINC, ICD10, RxNORM, MONDO, CPT, HGNC, etc) and standardizedfor interoperability (OMOP, FHIR, etc)

- Provide guidance (both career and curriculum-related) to students enrolled in NYCDSA's data science bootcamps- Provide resume review, interview preparation, and general career advice. While also advising students in project development, and homework and test preparation- Topics include general R and Python, R-Shiny, Statistics, Supervised Machine Learning, Unsupervised Machine Learning, Deep Learning, SQL and some Data Engineering principles- In the fall of 2018, I was enrolled in NYCDSA's 12-week data science fellowship providing training in Python, SQL, and R and their application and use in Data Visualization, Machine Learning algorithms and Parallel Computing. The intensive training provided in the program allows for attendees to both master the essentials of coding and grasp and understand the mathematics and theory behind machine learning algorithms. Chosen from the cohort to serve as a teaching assistant for the following bootcamp (Winter 2019)