My name is Phung Q. Mai. I’m an RN, and I have been working as an RN in various settings as my part-time. At the same time, I work for a local health system as a clinical systems analyst. This website is interesting, and I think what you are doing really help the health care IT community in huge scheme of things in health IT.
Besides, I also had 10+ experience in engineering which I think is a huge for me in my KB bank.
Thanks for the welcome.
My name is David Carnahan. I am an Internal Medicine physician who served in the US Air Force for 20 years. I have a masters in epidemiology from UPenn and have over 10 years experience using health IT for quality and safety measures, ad hoc analytics, research, and software development life cycle management of a platform that was used by the military health system (known as Carepoint). I am a proficient coder in R, python, SQL, Stata (from my UPenn days), have two certs in AWS (devops associate, and solutions architect associate), and dabble in static website generation. I am currently taking Andrew Ng machine learning courses in Coursera because of my interest in AI. I got involved with OHDSI while working with IQVIA and the FDA on the BEST initiative: where we are performing data curation of a network of OMOP/OHDSI data partners to support the work in biologics (allergenics, transfusions, blood derived products, etc) surveillance. I look forward to joining the cause and getting active in the data quality side of the house.
My name is Katy Sadowski and I’m a Data Analyst at TrialSpark, an NYC health+technology startup where we’re working to make clinical trials faster and more efficient. We’ve got a network of clinics across NYC, DC, and Chicago where we’ve implemented a vertically-integrated and technology-driven trial model.
My team and I are in the process of implementing the OMOP CDM in order to facilitate scalable, meaningful, and accurate analyses on the structured data we export from our clinics’ EHRs. We’re working specifically with CCD exports right now, and in the future are planning to incorporate unstructured doctors’ notes and claims data as well. I’m looking very much forward to leveraging the power of the full CDM and to contributing back to the community once we’re up to speed. As a lot of my work will involve defining “phenotypes” and cohorts, I could see myself pitching in to the Phenotype WG in the future. And of course sharing learnings in the EHR data realm. Our clinics are mostly small, community practices - makes for quite an interesting mix of data compared to what you’d find at a large research institution.
I’m delighted to have discovered this community and look forward to collaborating with you all.
My name is Beth Percha and I’m an Assistant Professor at the Icahn School of Medicine at Mount Sinai. I also help lead a small product development/data science team at the Mount Sinai Health System called the Precision Health Enterprise. Our goal is to enable the health system to adapt long-term to changing patterns in health care delivery and payment, and to better use the data we collect every day.
My PhD focused on natural language processing of biomedical text, and I am particularly interested in how we can apply observational data (much of which is recorded in the unstructured text of scientific articles and clinical documents) in a systematic way to create a healthcare system that can learn and evolve over time.
Long term, I would like to see Mount Sinai adopt the OMOP CDM for our own data warehouse so we can contribute to the larger OHDSI effort. Our team also does a lot of work with billing and cost accounting data, and I would love to contribute to the development of a more complete structured data model for financial data. Short term, I’m looking forward to hearing more about what you all are up to and helping with projects/partnerships in any way that makes sense.
Glad to be here, and please feel free to reach out to me at firstname.lastname@example.org if you’d like to talk more.
I’m Mark Shervey and am a data engineer in the Icahn School of Medicine, and colleagues with Beth Percha above. Along with my work with Beth in the Precision Health Enterprise, I’ve been leading data projects in another institute, The Institute for Next Generation Healthcare (INGH).
At INGH, we work in many different areas of health and medicine. We work closely with clinicians that would like to augment studies with digital health products, such as wearables; assist researchers in data engineering tasks regarding our EHR data; and help with outside collaborators wanting to work with our data, either from scratch, or to replicate studies (this is a lot of why I’m here).
I have two main hopes joining this working group. The first is to learn enough through particpation to be able to bring OHDSI into the Mount Sinai system. Once I’m more familiar with the working group and the OMOP CDM, and I’mn echoing Beth here, would be to collaborate in development of a financial data module that could be integrated into the common data model.
Excited to begin here! I can be reached at email@example.com if you have any questions.
Please feel free to join us for tomorrow’s OHDSI Community Call from 12-1pm ET. An agenda, along with details on how to join is available here:
My name is Sophie Williams and I am a Research Scientist working at Barts Health NHS Trust. I am developing a tool for predicting diabetes disease progression in our very diverse East London population. I am interested in using ML using factors from demographics, previous medical history and (particularly) social and lifestyle factors associated with Health inequalities.
I have a PhD in Neuroscience and have been working in data scientist for the past couple of years, using Python and SQL, although I am keen to improve my skillls in R. I have experience using knowledge graphs and am currently very interested in using NLP of free text to compliment the clinical data coded in SNOMED-CT / ICD10 etc., so would be very happy to chat to others in the OHDSI community working in this areas.
I have been building data products in various roles for about 10 years (ETL pipelines, dashboards, predictive models, visualizations, etc). I am an enthusiastic R programmer, with a little background in Python and (very recently) Julia as well. I love to write code.
In my current role, I am developing an OMOP ETL process using Epic Caboodle as the source data. R is being used to orchestrate the process, while SQL does the heavy lifting. I know that sounds weird, but R can act as a robust ETL tool if used properly. I am hoping that an ‘ETL for R’ package will be one of the results of this work.
Glad to be part of such an engaged community.
A great place to get started is by joining a working group. All OHDSI working groups are listed here: https://www.ohdsi.org/web/wiki/doku.php?id=projects:overview
And details about how to join each workgroup meetings are available here: https://docs.google.com/document/d/1X0oa9R-V8cwpF1WQZDJOqcXZguPKRiCZ6XrQ2zXMiuQ/edit
A very quick into. I’ve only just heard of OHDSI from having attended the 2019 Epidemiology Oxford Summer School. I’m impressed!
I am a senior scientist at Oxford University working on drug repurposing using clinical datasets (CPRD), transcriptomic datasets (LINCS1000 via CMAP) and pretty much any mathematical technique from Life Sciences all the way into Chemistry.
I’m a mathematical chemist (quantum chemistry and molecular dynamic simulations) via my PhD, interested in diseased protein folding; an epidemiologist when at Oxford; and finally a professional software developer having learned the trade in industry. My original higher education was in Artificial Intelligence and Natural Computing, with a very strong focus on the mathematical theory behind Artificial Neural Networks and Evolutionary Computing.
My day job at Oxford entails a tremendous amount of R/R-shiny & MySQL development (including API development to encourage general purpose use) to help us better understand the long term behaviour of drug prescription and clinical diagnosis of migraine sufferers. I’m combining this with informatics from CMAP and PubChem where possible.
I feel most at home when combining techniques from across the sciences and developing in Java, R, C/C++, Fortran and SQL (and pretty much any other language under the sun). I like the idea of becoming involve in any OHSDI group involved in science software development. In particular, I have a personal interest on work with a focus on restless leg syndrome.
Hi everyone, I’m Liu from Oxford University. I attended the summer course held in Oxford organised by prof Daniel Prieto-Alhambra last week, through which I knew Patrick Ryan and OHDSI. It is a fantastic platform and I’m amazed by the whole idea. Hopefully we could work together in the future.
This is Osaid Alser from NDORMS, University of Oxford. I’m a medic from Palestine with interest in surgical epi using large databases from NHS England (HES, ONS … etc)
I got to know OHDSI from the Oxford Real World Epidemiology Summer School here in Oxford
Lovely to e-meet all of you
My name is John Franz and I am a Senior Director-Research Data on the Scientific Computing team at the Icahn School of Medicine at Mount Sinai. I lead teams of Data Analysts, Data Engineers, and Developers to accelerate scientific discovery at Mount Sinai by providing researchers with high performance computational and data services along with the human expertise for efficient and effective use of these resources. As part of these teams, we provide the Mount Sinai Data Warehouse and associated Data Marts, Research Application Portals, and other custom developed research applications.
The Mount Sinai Data Warehouse (MSDW) portion of my team has an ecosystem of data products and services which now includes not just our internal MSDW but also i2b2, TriNetX, and many related data marts. To add to that ecosystem, we have an OMOP CDM and OHDSI tools migration well underway and expect to complete this soon (in Q3 2019).
I am particularly interested in the OHDSI suite of tools and also vocabulary mappings from our custom data model to OMOP CDM and would love to discuss this with others and help out in this area. We’ve also been working on NLP initiatives and would love to collaborate in this area as well.
Welcome to the community @franzj! Sounds like a great effort going on at Mount Sinai. I work for @Christian_Reich helping to enable folks in the US, Canada and Latin America in their journey to implement the OMOP CDM and OHDSI tools.
If there’s anything I can do to support Mount Sinai, let me know. As @Rijnbeek says, you’ll never walk alone in your OHDSI journey.
NLP wise, you may want to check out @HuaXu and @noemie’s NLP work group (NLP Workgroup Discussion Thread + Wiki Page: https://www.ohdsi.org/web/wiki/doku.php?id=projects:workgroups:nlp-wg).
Hi My name is Yi Zhang. I’m a senior researcher at a nonprofit outcomes research institutie mtppi.org. At MTPPI, my main role is designng and conducting studies using large electronic health databases and advanced statistical methods. In the past 12 years, I have been working with causal inference methods for the appropriate design and analysis of observational data. Most of my work has involved the use of Medicare claims databases as platforms for CER on safety of treatment exposure among dialysis patients and others with chronic medical conditions.
I look forward to collaborating with OHDSI researchers!
Hey folks! My name is Chris Ryan, I am a data scientist at TrialSpark working with EHR data. I’ve been interested in working with medical data for a long time. I have a PhD from UC Berkeley where I used computer simulations to study how things in cells self-organize, and have been a data scientist for the past 5.5 years. I’m just getting to know the OHDSI community and joined on recommendation from a colleague, so I’m looking forward to learning more about all the work that has been done and all the open problems left to work on. The first meeting I expect to join will be the NLP meeting.
Joking aside, welcome to @chrisjryan and @yzhang! You’ve completed step 1 of joining the OHDSI journey by introducing yourself. Next up: join a Tuesday community call (more info here: https://www.ohdsi.org/web/wiki/doku.php?id=projects:ohdsi_community).
Good day, my name is Mark Seal. I work at Cherokee Health System where currently I wear many hats as an interface specialist, SQL admin and software developer. Currently I am automating the ETL process from the NextGen EHR into the OMOP format and loading it to the All of US program using C# and TSQL.
In my former life I was a back end developer and data architect for USSI, a Meter Data Management enterprise software company, leveraging Java, Scala, Python and PostgreSQL.
When I am not transforming coffee into code, I am out on a Disc Golf course, hiking or gardening.
Hello everyone! I’m a long time lurker but am hoping to get more involved in my new position. I’m a Senior Health Information Systems Specialist (contractor) with the U.S. Agency for International Development. I’m working specifically on HIV and will be assisting our country teams with design and deployment of health management and reporting systems–possibly including but not limited to EHR systems, community health outreach systems, and more general district and provincial level reporting systems. I look forward to contributing to the OHDSI journey and seeing how the incredible work OHDSI has been doing can translate to improving the health of some of the world’s most vulnerable inhabitants.