At Truveta, we’re proud of our Truvetans and our growing intern program. In honor of National Intern Day (the last Thursday of July every year), we spoke to a few of our interns. They shared a bit about the projects they’ve been working on, and what Truveta’s vision means to them.
I’ve been working on methods for machine learning, model training, and development that will allow for a better understanding of the terms and concepts in different ontologies. This will help us recognize these concepts and their organizational structure in clinical settings, which will improve our understanding of clinical notes, which will enable us to empower researchers with knowledge more quickly.
I work on medication normalization. My work is to evaluate medication normalization model, error analysis, and try to improve the models. Medication is important for patient care. These medications are in medical notes, past patient history, and prescriptions. They are written as free text or in a standardized form. However, they have different patterns in different health systems. I try to build a new mapping method to systematically map medication terms to RxNorm terminology using ingredients, drug strength, dose form, and brand name. I believe that standardized data in healthcare is essential for patient care and necessary for closing the gap of healthcare inequality.
I’m working on a very interesting project, optimizing data pipelines. Daily notebook execution requires many manual steps, and our team has a conceptual idea to automate the Databricks data pipeline. My role is to prototype and implement this concept into reality, and the prototype and testing stages have been completed, which will lead to significant time savings for our team. There are many reasons why I enjoy working here, and my favorite parts are the daily standup meetings, a great manager, mentor, and team members who are all very patient and helpful. I really love learning how to work collaboratively with team members regardless of your own plans. Teamwork and team goals, and a healthy work environment, allow me to just focus on getting my work completed successfully.
Sarah Stewart, MD
I am a pediatrician and clinical informatician. I grew up in Seattle and then spent over a decade in the Bay Area completing my undergraduate degree in Materials Science engineering, medical school, pediatric residency and then working as an attending pediatrician at Stanford University. I am currently completing my Clinical Informatics fellowship at University of Washington and Seattle Children’s Hospital, and as part of this fellowship, participating as the first clinical informatics visiting fellow at Truveta. I am working with the other Clinical Informaticists to define and build our clinical quality metrics. I am excited to be here to learn how Truveta is leveraging data and technology to save lives.
This summer, I am a Graduate Engineering Intern working to productionize and scale machine learning models. My team works to create sophisticated ML models and scale them across different services. My goal is to enable the creation of infrastructure and pipelines that allow models to reach the user faster and more effectively. What saving lives with data means to me, is bringing quality affordable healthcare insights to millions of people with technology.
I take “saving lives with data” quite literally. We have information (data) that can help save someone’s life through an innovative therapy, a well-timed drug, or procedure. I get to be a part of it. This summer I’ve been working with Truveta leadership to define what ethical responsibilities we have as we save lives with data.
I’m a PhD student at UMass Amherst. I’m working on note normalization and concept mapping. I’m working on the pretraining part of the model to extract healthcare entities from clinical texts.
My task is to develop technology that would automate ways to mask or hide personal identifiable information (PII) or personal health information (PHI) on medical images such as MRI scans, CT, and X-rays that follow the DICOM standard. This work would enable researchers to view these images in Truveta as part of their clinical research while protecting patient privacy.
Working with state-of-the-art deep learning models towards generating time-series synthetic data. This helps to reproduce the statistical properties of the real data while preserving the privacy of patients. Synthetic data can help to accelerate the research development and questions involving the real patient data.
I’m an Undergraduate Engineering Intern working with the Clinical Informatics team to improve search functionality that helps researchers by addressing various medical expressions used to represent clinical diagnoses. As I near the end of my second summer with Truveta, I’ve loved the sense of community and shared purpose within the office and the inclusion of everyone within the company in our mission to save lives with data.
Most of my work has been related to improving functionality for data modelers. For these features, I’ve done work on both the backend and the UX, and I value being able to work on both of these sides. At Truveta, I appreciate how everyone is willing to teach and answer questions and I value the environment of learning and growth that has been provided for me.
I’m a rising senior at the University of Michigan and a returning intern, so the chance to apply the skills that I’ve learned in the last few years to my work this summer has been really exciting. I have been working on developing APIs that enable an end user to access different types of analytics computed from graph query data. Being able to work under the vision of “saving lives with data” has been an extremely rewarding experience, as I have the opportunity to contribute to work that has the potential to impact the most fundamental aspect of human life, our health, at such a large scale.
Interested in joining Truveta? We’re hiring! Check out our Careers page for more info about our values and to view open roles and opportunities.