| OHDSI Home | Forums | Wiki | Github |
Hello OHDSI community! My name is Brady. I am developing innovative and advanced data engineering and data science projects in support of the HL7 and OHDSI community.
Currently I’m working on a few projects. Once project, Forge, will help create a scalable and seamless no-code solution to mapping FHIR to OMOP data. The second project, Avalon, is an advanced clinical intelligence platform built using FHIR data translated into OMOP schema.
Howdy Everyone,
I’m Brian, an epidemiologist at U.S. CDC working in national surveillance for notifiable diseases, with a focus on building and integrating large longitudinal datasets and supporting applied outbreak response and research.
I’m exploring the OHDSI/OMOP ecosystem, particularly cohort definition, longitudinal data handling, and distributed study design, and would like to get hands-on with a small end-to-end project (e.g., cohort definition, estimation, basic study design in ATLAS). If anyone has example workflows they’d recommend or would be open to a brief walkthrough, I’d really appreciate it.
Happy to share progress back with the community as I learn. Looking forward to connecting and contributing where I can.
Thanks!
Brian
Hello!
I’m Adi, a graduating medical student from UCSF with a strong interest in data driven healthcare analytics and improvement. I studied metabolic biology and physiology at Cal, also influencing my interest in SDoH and cardiometabolic risk prediction in urban underserved or rural populations. I’m excited and look forward to exploring OHDSI and its community for the sake of learning, contribution, and research 
Hello OHDSI community! My name is Mustafa Shukur. I am a medical graduate and currently doing an MPH with an epidemiology concentration.
I started exploring OHDSI and the OMOP Common Data Model, and I am very interested in learning more about ATLAS and collaborative analytics. I hope to expand my skills in health data science and contribute to ongoing projects within the community.
Thank you!
Hello everyone, my name is Azubuike Prince Chinazaekpere, and I am a lecturer in the Department of Computer Science at Nnamdi Azikiwe University, Awka. Over the years, my research has focused on Machine Learning and Natural Language Processing, particularly in developing models and resources for low-resource languages. Recently, I developed a growing interest in health data research and its potential to improve healthcare outcomes, which motivated me to join the OHDSI community.
I look forward to contributing to the community through collaboration in running studies, participating in research projects, and co-authoring impactful research papers. I am also excited to learn from other members and contribute my experience in AI, data science, and NLP to interdisciplinary health research.
Hi all,
My name is Jack Ringer and I’m a Data Scientist at the University of New Mexico (UNM). I maintain a private OHDSI ATLAS instance for researchers at UNM. At the moment most of my time is spent on system administration (e.g., configuring software for researchers), but I’m interested in learning more about observational health science!
I believe I can help out the community by providing assistance to new OHDSI Implementers and contributing to the documentation. I’d also be willing to help out the community with software development by contributing to OHDSI projects on GitHub.
Hello everyone!
My name is Louis-Etienne Messier and I’m a software engineer student at Laval University. I have a more Computer Vision focused background, but I have recently taken a new interest in observational health data. I’m especially eager to learn more about the data layer transformation technology used in this field.
I hope to contribute to the community with my enthusiasm and passion, and eventually also help out on the OHDSI Github projects.
Hi everyone!
My name is Skylar Rollins, and I’m a recent Master of Public Health graduate from Dartmouth. I have previously collaborated on projects analyzing hospital financial data using fuzzy-set qualitative comparative analysis, as well as survey data on patients enrolled in an autoimmune disease registry. I have also worked at Yale University studying macular degeneration in human microglia.
I have a strong interest in healthcare analytics, observational health data, and improving care access for patients with chronic disease.
Looking forward to exploring OHDSI and building more skills in health data science!
Hi everyone!
My name is Michael Gaile, and I’m a computer science senior at Cornell University. I build and maintain NY Health Watch (nyhealthwatch.org), a public health platform that pulls New York State and CDC data into county level infectious disease surveillance, so I’ve spent a lot of time working with messy real world health data, building pipelines, and thinking about data quality. I’ve also done research with Cornell’s Brooks School of Public Policy in collaboration with the NYCDOHMH on a large scale data linkage model.
I have a strong interest in real world evidence, observational health data, and the methods behind turning it into reliable conclusions. I’m currently starting to map some of my surveillance data into the OMOP Common Data Model, which is part of what drew me here.
Looking forward to learning from this community and contributing where I can, especially on the engineering and tooling side!
Hi everyone, I’m Hamid, joining from Vancouver, BC.
I’m a Principal Statistical Programmer at ICON PLC with 20+ years in real-world evidence. Most of my career has been with large non-OMOP datasets (claims, registry, hospital data), running observational studies and building prediction models. Lately I’ve been working more with OMOP-mapped data, which is what brought me here. Day to day, I’m mostly on the regulatory side now, producing TLFs and standard analysis outputs for agency submissions using CDISC standards (SDTM and ADaM).
I’m a bit obsessed with whether a cohort is actually fit for a study and can hold up to a regulator, so I’ve built a small open-source R package for validating RWE cohorts on the OMOP CDM. I’ll share it in the Developers category soon and would love feedback. Also happy to help out on anything around cohort validation and data reliability, so point me to a workgroup if one comes to mind.
Great to be here.
Hi everyone, I’m Magnus, joining from Aarhus, Denmark.
I’m a senior OMOP consultant at Aarhus University Hospital, where I’m leading our OMOP CDM rollout. We’re in the earlier stages of building a general OMOP model - our core domains (conditions, drugs, labs, procedures) are more or less in place, and our first concrete case is a national characterisation study on breast and lung cancer. A good part of the work is mapping Danish health data (NPU, SKS, ATC) on top of the international vocabularies, and we’re building federated-by-default so data stays local.
A bit on what I bring: I’ve spent the last ten years working with data both hands-on and in leadership, so I tend to sit between the technical and the strategic. On the technical side I’m curious how we get the most out of ETL and - lately - LLMs for mapping efficiency; AI-assisted vocabulary mapping is very relevant to the Danish/Nordic gaps we’re working through. On the strategic side, the threads I care about most are strategic direction in complex health-data environments, bridging business, technology and governance, capability building and organisational development, health analytics and decision support, and organisational adoption and international collaboration.
What really drives me, though, is how you make OMOP stick at a hospital — anchoring it as a sustainable, institutionally owned capability rather than a one-off project. So I’m here mostly to connect: to find people and network studies we can plug into as our model matures, and to learn from sites that have been through the institutional side of a rollout. Oncology is our primary focus for now, so I’ll be following the Oncology WG, but I’d love pointers on where else it makes sense to get involved.
Great to be here - looking forward to it.
Magnus
Hello everyone,
My name is Boris Teplitsky, I am an independent software developer based in Israel.
Lately I have been exploring the use of LLMs in systems based on natural language, often ambiguous prose, which require repeatable and traceable answers. Clinical trial eligibility criteria caught my attention as one of the hardest cases of prose-to-executable, which is what led me to OMOP, Circe and this community. I built a small proof of concept and plan to ask for your critique in the Researchers section. The part I most want checked by people who author cohort definitions by hand is where the method refuses to encode a criterion rather than guessing.
How I would like to help: I am not a clinician and will not pretend otherwise, but I bring build-system and validation-pipeline experience, and I am happy to contribute on the engineering side where it is useful.
Hi everyone, I’m Allen (Mingliang) Ge, joining from Philadelphia.
I’m a Research Coordinator in Joost Wagenaar’s group in the Department of Biostatistics, Epidemiology and Informatics at UPenn, working on the Pennsieve data platform and Epilepsy.Science. Most of my week is data standards and metadata. I migrated the NINDS Epilepsy Common Data Element catalog into a queryable registry (875 CDEs across 37 CRFs), and right now I’m authoring a submission specification that extends BIDS-iEEG for epilepsy datasets: which fields get upgraded to required, how provenance is recorded, what blank versus “n/a” actually means to someone reusing the data three years later. Before Penn I did an MS at Dartmouth and first-author work on continuous glucose monitoring.
So I’m arriving from a different corner of the standards world, file-level, research-domain, high-frequency signal data, rather than from OMOP. I’m here to learn the CDM properly. What I’m most curious about is where the community draws the line between research-domain elements and the standard vocabularies, and how device and signal-derived data fits.
On helping out: I’m starting by listening, community calls plus the Vocabulary and CDM workgroups. Where I could be useful before my OMOP knowledge catches up is documentation and data-quality review. Writing specs, and turning expensive debugging into onboarding material someone else can follow, is most of what I do at work. Happy to take a well-defined piece if one needs a pair of hands.
I’m also a little over an hour down the road from New Brunswick, so I’m hoping to make the October symposium. Would be good to meet people in person.
Hi all. I am Sandy Estremera-Zink, joining from California.
My background is in biopharma privacy and compliance law, with in-house work at Atara Biotherapeutics, Corcept and Abeona Therapeutics. I am a lawyer by training who has ended up doing informatics work, which is a slightly odd path into this community.
What I work on is cross-site semantic comparability. The question is whether a concept carries the same clinical meaning at each site before a network study runs. I joined the Evidence Network working group in June and I will be presenting at the Global Symposium in October.
What I can contribute is a privacy and data governance perspective alongside the technical side, which is the intersection I have spent most of my career in. What I am hoping to learn is how sites actually handle concept mapping differences in practice, since that is where the real answers live.
Good to be here.
Hi everyone, I’m Sohyeon Jeon, a medical informatics researcher based in Seoul. I started out in philosophy and cognitive science, and my earlier work involved brain imaging, language, and computational approaches.
My research focuses on semantic risk in computable clinical evidence, especially in clinical trial feasibility. I study how eligibility criteria are translated into OMOP cohorts, what populations those cohorts actually represent, and how differences in definition affect patient counts and site-selection decisions.
I use deterministic cohort logic and evaluate AI-assisted cohort construction by looking beyond counts to patient sets and downstream decisions. Rather than treating a patient count as a simple database output, I’m interested in whether the evidence behind it is clear, reviewable, and fit for the decision it supports.
Through OHDSI, I’m hoping to learn how others deal with the gap between cohort definitions and what can actually be observed in different CDM environments, and to exchange ideas around these problems. More broadly, I’m interested in how computable clinical evidence can support responsible decision-making.
Glad to be here!
Hello, I’m Krzysztof Żerdziński, a fifth-year medical student at the Medical University of Silesia in Katowice. ORCID
My research combines evidence synthesis and ICU outcome research, and I am developing a programme on rigorous evaluation of large language models in intensive care.
I am particularly interested in reproducible cohort definitions, external validation and methodological collaboration.
My immediate goal is to learn the OHDSI workflow and contribute, under appropriate methodological guidance, to an ICU-focused cohort definition or study package.
Hello everyone, I’m Ruth Lochan Winton from Uppsala, Sweden. I work as a Healthcare Business Architect at Uppsala University Hospital (Akademiska Sjukhuset), focusing on digital health, clinical informatics, interoperability, and health data standardization. I hold a PhD in Information Systems from Uppsala University, where my research explored the design of digital health solutions and ICT-supported healthcare communication.
My current work involves national and European initiatives in health data interoperability, cancer care, remote patient monitoring, and the secondary use of health data - with a particular focus on EHDS implementation, real-world data, and how OMOP/OHDSI, openEHR, and FHIR can be aligned rather than treated as competing standards.
I’m looking forward to learning from the OHDSI community and would especially welcome connecting with others working on EHDS readiness, OMOP adoption, real-world evidence generation, and practical clinical data standard alignment for research and patient care.
Hi OHDSI Community!
I’m Anastasiia, a data scientist and PhD researcher based in Dresden, Germany.
In my current research, I am focusing on prostate cancer treatment monitoring, which involves working directly with OMOP-ed data. Moving forward, I will also likely be participating in a mapping Aarhus health data to the OMOP CDM.
My background is in data science with a strong focus on Medical Imaging. I have a lot of hands-on experience dealing with messy PACS exports, standardizing DICOM data, and preprocessing longitudinal MRI datasets. Alongside imaging, my work involves Natural Language Processing, specifically leveraging LLMs and building RAG pipelines.
I am thrilled to join this community, learn about best practices, and connect with others working in the oncology and imaging spaces! ! I am also very keen on contributing technically and would love to help port some of the existing OHDSI packages from R to Python to support better AI and Agentic integration.
Looking forward to collaborating with you all!
Hi everyone! I’m Mamoun, a final-year medical student working at the intersection of clinical medicine and data science, with a focus on the OMOP Common Data Model.
I recently built a synthetic CKD dataset in OMOP format and published a data profiling notebook (Part 1) on Kaggle: SQL Data Profiling-part1 | Kaggle — I’m continuing that series and always looking to sharpen the work through community feedback.
I’m joining OHDSI because I want to build real, lasting skills in this space — and eventually put them to use in strengthening health data infrastructure in Syria, where that kind of work is still very much needed. Long-term, I’m working toward a career in Clinical AI, but that goal is tied to a broader hope of contributing something meaningful back home.
Hello everyone,
My name is Muni Rubens, MD, MPH, PhD, and I am an Internal Medicine resident physician at Baptist Health South Florida/Florida International University with a strong background in biostatistics, clinical research, real-world data analysis, and machine learning. Prior to joining residency I was working as a Biostatistician II on Phase I and II cancer clinical trials.
My research interests include clinical medicine, cardiology, health disparities, epidemiology, clinical outcomes, causal inference, and AI/ML-based prediction modeling. I have experience working with large observational datasets and EHR-derived data, including NIS, MIMIC-IV, and institutional electronic health records, using methods such as propensity-score approaches, survival analysis, regression modeling, machine learning, model validation, and interpretability techniques.
I am particularly interested in learning more about the OMOP Common Data Model and contributing to multicenter and distributed research through OHDSI. I hope to become actively involved in workgroups such as Methods Research, Patient-Level Prediction, Evidence Network, and Health Equity, and I would be very interested in collaborating on ongoing studies where I can contribute to study design, statistical analysis, interpretation, and manuscript development.
I look forward to learning from the OHDSI community and collaborating with investigators across institutions.
Muni Rubens, MD, MPH, PhD