What first drew you to the intersection of technology, data, and healthcare, and how did that interest shape your career journey?

I started out as a somewhat aimless college graduate in the Bay Area, watching the farmland around me transform into global technology hubs for companies like Google, Apple, and Cisco. At the same time, my interest in science and healthcare never went away, so I began looking for a career that could bring those worlds together.

My first role was at a medical communications company. I then moved to a technology company that processed claims data, where I built my first ETL, before joining Kaiser Permanente’s Program Office as an analyst supporting the national network with business analytics. At Kaiser, I learned to think at the scale of observational data and saw how evidence could be used to guide better care. At this point in my career I was sure this was the place I wanted to be and the career I wanted as a data scientist.

Fourteen years ago, I joined Johnson & Johnson, and that is when my career trajectory really shifted. I discovered OHDSI, deepened my understanding of ETLs and standardized vocabularies, and began applying those skills to observational studies designed to produce transparent, reproducible research.

What have been the major research themes in your career, and how has the OHDSI ecosystem helped you turn those interests into practical, reproducible work?

At Johnson & Johnson, I developed my foundation in epidemiology while helping build internal infrastructure around the OMOP Common Data Model. At the same time, I watched the community’s HADES toolset evolve from a methods library into a standardized analytics stack for network studies. Those tools remain central to how I work today.

On the applied side, I have relied heavily on ATLAS to translate data into practical solutions, particularly for clinical trial feasibility and recruitment. Standardized cohort definitions and reusable concept sets allow us to examine how a proposed trial population appears in real-world data. Those insights can help teams refine eligibility criteria, assess feasibility, and support protocol design and execution.

Much of my research has focused on population characterization, oncology, phenotyping, and methods development. In oncology, that has included developing standardized approaches to representing lines of therapy across different treatments and procedures. Representing those clinical patterns consistently in the OMOP Common Data Model is essential for reliable research across a distributed network.

During the COVID-19 pandemic, I focused on making phenotyping more reusable, refined, and repeatable. More recently, our team developed a pregnancy algorithm in ATLAS, with a manuscript currently under review, and contributed to maternal health characterization and phenotyping across the network. Across all these areas, OHDSI has provided the common data model, tools, methods, and community needed to move from an individual research question to transparent, reproducible evidence.

As a longtime member of OHDSI, what change in the community’s approach to research has been most exciting for you to witness?

What excites me most is how OHDSI has made large-scale observational research both more standardized and more open to participation. When I first became involved, there were only a few core workgroups. Today, the community spans an extraordinary range of clinical specialties and methodological areas, and each year it contributes more science, more tools, and more expertise to the ecosystem.

The biggest technological transformation has been the ability to conduct network studies using common definitions, standardized methods, and a growing number of data partners. It has become much easier for an organization to transform its data to the OMOP Common Data Model and begin contributing to community research.

I still remember hearing the first LEGEND results and thinking, “This is one of the most amazing things I have seen.” Then, during COVID-19, I watched the same network-based approach generate evidence rapidly across multiple data sources. That showed what is possible when a global community shares standards, tools, and scientific practices.

I am also continually impressed by the community itself. We support researchers around the world, build knowledge together, and keep pushing the boundaries of observational research. We even wrote a book together. For me, that combination of strong science and an open, supportive community is the true transformation.

You recently stepped into a co-leadership role with the Perinatal and Reproductive Health Workgroup. What motivated you to take on that role, and what makes OHDSI well suited to advance maternal health research?

I have been part of the Perinatal and Reproductive Health Workgroup’s journey from its early stages. Gaps in pregnancy and maternal health evidence were frequent topics of conversation at the early OHDSI conferences, and the workgroup was ultimately formed by Allison Callahan, Stephanie Leonard, and Louisa Smith.

After completing the pregnancy algorithm in ATLAS, I saw an opportunity to contribute more directly and help move the workgroup’s research agenda forward. Over the years, I have built expertise in maternal health research, and I wanted to use that experience to support investigators who are entering the field and help translate promising ideas into executable studies.

The integration of the Johns Hopkins Maternal Health Fellowship, led by Paul Nagy and Sean O’Reilly, has made that opportunity especially meaningful. Through the workgroup, we can help fellows become comfortable with OHDSI tools and methods, connect with clinical and technical experts, and carry research questions into network studies.

OHDSI is particularly well suited to this work because it brings together standardized data, reusable methods, and a diverse international community. The workgroup now includes people with complementary clinical, epidemiologic, and technical expertise. By engaging other core workgroups and data partners, we can address questions that would be difficult for any one institution to tackle alone.

Looking ahead through the rest of 2026, what milestones is the Perinatal and Reproductive Health Workgroup focused on achieving?

For the rest of 2026, our workgroup is focused on four practical priorities. First, we are welcoming new maternal health fellows into an already engaged team and broadening the clinical and technical expertise within the group.

Second, we are continuing to support the transformation of U.S. birth certificate data into the OMOP Common Data Model, with an emphasis on data quality, standardization, interoperability, and research readiness.

Third, we are developing an inventory of pregnancy-related variables and data assets across the OHDSI network so researchers can better understand what information is available and where consistent, comparable analyses may be possible.

Finally, we are equipping the fellows to develop and complete network studies through targeted education, shared resources, mentorship, and hands-on guidance. The goal is not only to complete individual projects, but also to build lasting capacity for maternal health research within the OHDSI community.

Outside of your research, what do you enjoy doing, and what is something the OHDSI community might not know about you?

Growing up in Northern California gave me a lasting love of the outdoors. Give me a trail, a picnic spot, or simply a sunny day, and I am in my element.

I was also spoiled by California’s growing season, and by a dad who still maintains a mini farm in his backyard, so I developed a love of cooking with fresh ingredients. My other passions include Bollywood dancing and all kinds of art.

I spend a lot of time with my two girls, who share many of those interests, so we are often outdoors exploring or in the kitchen trying a new experiment. As a first-generation Southeast Asian American, I am also deliberate about preserving our culture by carrying forward family traditions, stories, and recipes for the next generation.