UVA Health strengthens AI and real-time analytics
The use of AI tools in healthcare has accelerated, with growing confidence in the results produced and delivered by such tools.
RAMP, one such tool already in use at UVA Health, focuses on delivering actionable, verifiable, and explainable machine learning, integrating it as a decision support tool into the clinical workflow to improve understanding of patient health trends and to facilitate faster delivery of necessary care, allowing the patient to function better. outcomes.
AI-powered predictive analytics models use complex real-time and historical patient data to provide healthcare professionals with actionable insights and alert healthcare teams when the patient needs immediate attention.
Valentina Baljak is a senior data scientist at UVA Health. She has a PhD in Information Science and Technology, Applied Machine Learning. UVA Health created and used RAMP today.
Baljak and two of her colleagues will discuss AI, RAMP and more at HIMSS25 in March in Las Vegas in their session titled “Realtime Analytics Monitoring Platform: Actionable AI in Action.” We spoke with Baljak to get insight into what she and her colleagues will talk about during the session and what HIMSS25 participants can learn from their talk.
Q. What is the key topic you will cover in your session and why is it relevant to healthcare and healthcare IT today?
A. With the recent emergence of generative AI models, this topic is gaining increasing attention in healthcare. In this work, we focus on real-time clinical decision support tools. Artificial intelligence is not a new term.
At UVA Health, we’ve been developing real-time predictive systems for several years, and one of the biggest lessons we’ve learned is that the form AI should take is the one that best suits your needs. Doctors will not find out about tools that they cannot explain. Building trust in our models and tools meant close collaboration every step of the way, from day one.
We want to provide a blueprint for building a system that works in your environment, and raise awareness of the importance of transparency, accountability, and explainability of your models. This is especially important in the medical environment, with real-time predictions that can have a significant impact on patient outcomes.
Q. You will focus sharply on AI. How is it used in healthcare in the context of your session focus?
A. The most important aspect of RAMP is the real-time collection of data from the EHR and other data sources. The ability to write results back to patient records in an EHR and alert care teams in real time makes RAMP a critical tool in the clinical setting.
The technologies used here are fairly well established and all open source. Python provides a solid foundation for our ML development, back-end connectivity and data processing. Connections to various data sources are built with FiHR, REST API and custom HL7. The website is built with Angular.
As our latest major expansion, we are building a new predictive model on top of our largest real-time data stream, built with Kafka to collect all vital data and EKG waveforms from bedside monitors.
Q. Participants come to your session to take home knowledge. What’s a takeaway they can expect?
A. AI is a fundamental part of modern healthcare and takes different forms depending on the need. Selecting the right AI approach is crucial, given the high stakes.
If you have the expertise and resources in-house, developing a custom AI system is a powerful alternative to vendor-provided black-box systems.
Valentina Baljak’s session, “Real-Time Analytics Monitoring Platform: Actionable AI in Action,” is scheduled for Tuesday, March 4 at 12:45 p.m. HIMSS25 in Las Vegas.