Using AI to Spot
Disease Faster for Our Beloved Furry Friends
Digital Product Development
Cloud Modernization
AI/ML
Zomedica is a veterinary service provider on a mission to support veterinary practitioners by delivering cutting-edge technology, products, and services to improve animal health and well-being. As a leader in diagnostic technology for veterinary care, Zomedica sought to harness the potential of AI to improve the speed and accuracy of their flagship diagnostic tool, TRUVIEW.
Known for their solutions that turn days of traditional veterinary workflows into a few short hours, Zomedica was looking to once again lead through innovation; this time powered by AI.
Zomedica needed the expertise to lay the technical groundwork for this upgraded solution and the skills to deliver the new AI-enabled diagnostic tool as well as the end-to-end MLOps workflow. Vervint answered the house call.
Primary Goals
Provide faster diagnostics through cloud modernization
Upgrade the cloud environment to significantly improve processing time, allowing for faster diagnosis capabilities.
Improve efficiency with AI & MLOps
Zomedica sought to pair an AI assistant with human clinicians to create a more streamlined process where initial blood reviews were completed by AI, flagging potential issues.
Improve accuracy through human + AI redundancy
Increase the volume of indicators identified at early stages through the combination of AI + human intelligence, allowing for improved treatment options sooner, saving lives.
We never get the same kind of feedback from other consultants that we get with Vervint. That is the differentiator and why we stay with them.
Understanding the why before AI
We started with gaining a deep understanding of Zomedica’s business objectives and AI/ML goals helping us uncover precisely what types of problems would be useful to solve, which data sources had to be readied to test and then scale, and the expected outcomes the ML models could deliver if successful.
Designing a world-class MLOps workflow
With clear objectives and alignment, we worked with the Zomedica team to create an end-to-end MLOps pipeline canvassing the entire machine learning workflow. From data preparation to model development, and into training, validation, deployment and monitoring, we used this new workflow to help make key decisions tied to tooling, technologies, and cloud services required to build this solution out at scale.
Deploying into a complex DevOps environment
Partnering with Zomedica’s technical leads, we integrated the newly formed MLOps pipeline into their existing DevOps processes, culminating in a smooth and automated deployment. In parallel, we optimized Zomedica’s cloud environment, readying it for increased demands the image-based AI solution would introduce to the system.
Results Delivered: Upgrades to Zomedica’s TRUVIEW platform
Vervint delivered upgrades in two unique phases.
Phase 1: A system upgrade decreasing cloud processing time while increasing the volume of data it can capture and utilize for decision making. Results have surpassed Zomedica’s performance targets, processing images up to 20 gigapixels in the new optimized cloud.
Phase 2: Integration of AI analytics into TRUVIEW, accomplishing the goals of increasing speed and accuracy with two levels of review. This solution is in production and testing and will soon be available to all TRUVIEW customers.
By helping Zomedica leadership make their digital vision a reality, Vervint is helping ensure that our beloved furry friends receive the best healthcare outcomes possible, sooner than ever before. It is in these bespoke cases of utilizing AI for discreet problem solving and integration that we often find tremendous value for all parties involved.
