Myrela Bauman

Myrela Bauman

Data Engineer | Epidemiologist

About Me 👩🏻‍💻

I build the data systems that healthcare decisions run on. I started my career as an epidemiologist at the New York City Department of Health, and over the last 7 years I've moved from investigating population health trends to engineering the pipelines behind them. Today I build production PySpark and Databricks pipelines that process Medicare and Medicaid claims at national scale.

What I like most about my work is weaving different tools and languages into data systems that are scalable, tested, and easy for other people to run. I'm an investigator by nature, and my epidemiology background means I understand what the data is for, not just how it moves. I also have a knack for making technical and statistical ideas clear to any audience.

Outside work, you'll find me chilling with Euclid, hiking, reading, doing yoga and pilates, or gaming.

Projects

Most of my day-to-day work uses protected health data, so it stays private. What you see here are passion projects using public or synthetic data. Everything is open source and ready to run.

Glowing dot columns showing US Medicare prescribers of semaglutide growing from 1,065 in 2018 to 174,885 in 2024

Ozempic as an Outbreak: How Semaglutide Spread Through US and UK Prescribers In progress

Epidemiologists track who catches a disease first, how fast it spreads, and where. This project asks the same questions about semaglutide: when did each US prescriber and UK GP practice start prescribing it, and how quickly did adoption move across the map?

Follow on GitHub

Four maps of New York State showing when each county reached the middle of each COVID-19 wave compared with New York City

How COVID-19 Waves Traveled Across New York State 2023

Did every COVID-19 wave start in New York City and spread outward? Using daily positive tests for all 62 counties (2020-2023), I timed each county against NYC and related the delay to distance. Only the first wave followed that pattern. Python, scipy, geopandas, folium.

View on GitHub

London Bridge water levels 1911-1995 with anomalies flagged by an isolation forest model

River Thames Tidal Variation 2023

A century of digitized tide records (~650k readings from 13 gauges, 1911-1995), cleaned and merged with a reusable loading function. I measured tidal range and extreme-tide frequency at each gauge and used an isolation forest to flag anomalous readings at London Bridge. Python, pandas, scikit-learn, Bokeh.

View on GitHub

Terminal showing the renamer previewing four renames, skipping two problem files, and 15 passing tests

Medical Examiner Case File Renamer 2022

A command-line tool that reads the case number from each mortality case PDF and renames the files, cutting a monthly task from about 4 hours to 5 minutes. It previews before changing anything, skips and reports problem files, is safe to re-run, and has 15 automated tests that run on GitHub Actions.

View on GitHub

Portrait of James Joyce on a floral background

Named-Entity Sentiment Analysis of James Joyce's Ulysses 2023

Joyce's 800-page novel, scraped and analyzed for tone and sentiment. I mapped 88 name variations to 30 main characters, scored every sentence with VADER, and then tested whether the scores simply reflect each chapter's tone. Mostly they don't, though Joyce's style still sneaks in. Python, NLTK, BeautifulSoup.

View on GitHub

Stacked pulsar signal lines recreating the Unknown Pleasures album cover

Joy Division 'Unknown Pleasures' Plot 2023

Recreating Joy Division's iconic album artwork in Python with Matplotlib and pandas. The original artwork plots radio signals from pulsar PSR B1919+21, discovered by Jocelyn Bell Burnell in 1967, and this version is drawn from the same pulsar data.

View on GitHub

More on GitHub

Work Experience

Data Engineer - Mathematica (2023 - Present)

I turn more than 2 billion rows of Medicare, Medicaid, and administrative claims into evidence on how well health services and payment models work. This includes designing pipelines in Snowflake and AWS that handle over 1TB of healthcare data for client-facing reports, and building modular Python frameworks in Databricks that process data from 30 sources. On the analytics side, I helped build forecasting models for a national real-time overdose mapping app, and programmed a patient-level mixed-effects logistic regression model to identify high-risk skilled nursing facility residents.

Substance Use Epidemiologist - NYC Department of Health and Mental Hygiene (2019 - 2023)

Analyzed overdose deaths and drug-related hospital visits across New York City. My analyses of demographic and neighborhood disparities informed the distribution of 200k+ naloxone kits in 2022 and the launch of 10 harm-reduction vending machines. I automated daily surveillance reports in R, built a text-processing algorithm to detect novel drugs in emergency department data, co-authored the city's annual overdose reports, and advised health departments in 12 states on surveillance data.

Research Assistant & Teaching Assistant - Columbia University (2016 - 2018)

Co-authored a peer-reviewed paper on adolescent prescription drug misuse, led data collection for a needs assessment of opioid treatment gaps on Staten Island, and taught a weekly Nonprofit Financial Management section to 56 graduate students.

Selected Publications

Nonmedical Prescription Drug Use Among Adolescents: Global Epidemiological Evidence for Prevention, Assessment, Diagnosis, and Treatment Peer-reviewed

Perlmutter AS, Bauman M, Mantha S, Segura LE, Ghandour L, Martins SS. Current Addiction Reports 5(2), 120-127 (2018).

A review of the latest global evidence on adolescent nonmedical prescription drug use, covering prevention, assessment, diagnosis, and treatment.

Read now

Unintentional Drug Poisoning (Overdose) Deaths in New York City in 2022 Published report

Tuazon E, Bauman M, Sun T, Weitz A, DeWalt J, Mantha S, Harocopos A. NYC Department of Health and Mental Hygiene, Epi Data Brief 137 (September 2023).

In 2022, 3,026 New Yorkers died of a drug overdose, the highest number on record. We analyzed citywide demographic and geographic disparities to guide prevention and the distribution of resources.

Read now

Unintentional Drug Poisoning (Overdose) Deaths in New York City in 2021 Published report

Askari MS, Bauman M, Ko C, Tuazon E, Mantha S, Harocopos A. NYC Department of Health and Mental Hygiene, Epi Data Brief 133 (January 2023).

Overdose deaths in New York City in 2021 surpassed every prior year, mirroring national trends. We analyzed citywide mortality trends to highlight disparities and inform the public health response.

Read now

Unintentional Drug Poisoning (Overdose) Deaths in New York City in 2020 Published report

Nolan ML, Jordan A, Bauman M, Askari M, Harocopos A. NYC Department of Health and Mental Hygiene, Epi Data Brief 129 (November 2021).

Unintentional drug poisoning deaths in New York City in 2020, by drug, demographics, and neighborhood.

Read now