Chee Lee Email and Phone Number

• Technical lead of a data science team mainly focused on developing NLP models to support consultants at SullivanCotter (parent company of Clinician Nexus)• Lead data science strategy at the corporate level• Establish best practices for delivering and maintaining models through the Data Science Development Life Cycle• Collaborate with Data Engineering, Software Engineering and DevOps to integrate models into new and existing tools

• Over the course of tenure at Cogitativo, helped build over a dozen disease progression models using a mix of EHR, claims, SDOH, and clinical notes data• Was one of the main developers of the company's flagship data science product, Visìon, which contributed to the majority of the revenue stream• Translated clinical requirements to technical roadmaps and worked closely with the clinical team to validate models and add additional features to the Visìon product to increase it's marketability and clinical interpretability

• Developed data science products to meet the needs of stakeholders1) Predict and reduce readmissions hospitalizations – delivered machine-learning-based risk scores to aid Transitions of Care team in discharge planning of patients at high-risk of 30-day readmissions, combining streaming EHR data from hospitals with claims/encounter data2) Forecast COVID-19 impact on financials, hospital utilization in membership base to predict peak infection, hospitalizations, and increase susceptibility due to geographic and demographic characteristics3) Generalized Program Evaluation Tool, a self-service tool for case-series and case-control study designs to assess program effectiveness during and post implementation4) Population health informatics tool to provide analytics and visualizations of vulnerable populations eligible for California for All (“CalAIM”) state-wide program, as well as other population health programs.• Developed data science “feature store” to standardize feature definitions across all data science projects, resulting in greatly reduced time spent in ETL and faster on-boarding of new team members• Led, mentored and trained data scientists and data analysts in all applicable stages of the data science life cycle. • Operationalized end-to-end data mining and analytical pipeline that allowed business stakeholders to (1) monitor financial and medical utilization trends, (2) identify performance anomalies by provider groups, hospitals, and utilization anomalies in different Medicaid segments, and (3) identify opportunities for process improvement.• Worked closely with different functional areas - including health services, utilization management, provider contracting, product development, finance, claims and operations - to translate business propositions into actionable items backed by a solid data foundation.

• Used machine learning and advanced statistical methods to study clinical utility and validity of medical tests, identify patterns in data leading to improved test precision and accuracy, and discover new avenues of research.• Expertise in leveraging millions of data points from different sources (e.g., electronic health records, patient and physician surveys, and medical test results) to discover insights and trends, and to develop and improve algorithms.• Produced high-quality graphics and wrote summaries of methods and results of findings from clinical studies for peer-reviewed journals, as well as reports for company commercial products.• Areas of research: opioid addiction, pain sensitivity, drug metabolism, and rheumatic diseases.

Developed statistical methods for epigenetic and gene expression data, including gene expression microarrays, RNA-seq, ChIP-seq, and methylation arrays and sequencing.

TA for course, "High-throughput Molecular Genomic and Epigenomic Data Analysis."

Responsible for wet and dry lab operations of the Wisconsin Longitudinal Study, from molecular analysis of thousands of samples to performing statistical analysis for discovery of social and health patterns in age-related diseases.

Provided statistical consulting for wide variety of projects: (1) machine learning to predict operons in the tuberculosis genome, (2) analysis of ecological migration and genetic markers of snapping turtles, (3) identification of speech patterns in Midwestern English speakers and Hmong speakers.