We have reduced bandwidth and processing power requirements, introduced several new user features and continue to make Ouva the best healthcare enterprise AI solution for virtual care.
2x less bandwidth
We decreased the minimum recommended resolution across all sensors by half. This reduces network bandwidth and processing power loads needed.
Dynamic dashboard sorting
You can filter and sort the dashboard dynamically. For example, you can sort rooms by priority, first showing the rooms with the most critical alerts.
Search inside tables
You can filter patient and configuration tables. Click on the 🔍 icon found next to column titles to search.
Inbox indicator with color
The inbox indicator dot now shows the most critical alert color. You can find it on the side menu when the inbox is closed.
Fixes and Improvements
- We fixed a major problem that caused our platform to build a large memory footprint and crash over multiple days of continuous use.
- You can collapse/expand all sensors and details on the rooms configuration page.
- We updated the visual theme of the sidebar.
- We refined the app's aesthetic consistency by harmonizing font sizes and other stylistic elements across sections.
- We standardized loading animations and their behaviors throughout all pages and widgets.
- We added the missing "sitting on the chair" icon on the dashboard.
- We fixed an issue that showed more than 60 minutes in hourly mobility charts and more than 24 hours in the daily charts.
- Resolved an issue that displayed ">1" mobility amount for newly admitted patients, ensuring it shows 0 as expected.
- We resolved an issue in the "Rooms with sensors" form that occurred after the username field was populated and cleared.
- We resolved an issue in the patient admit dialog, making search fields resilient to inadvertent space characters.
Technical Improvements
- We now have better logging to identify issues with video streams.
- Before enabling video streams, we added a secondary check for the sensor URL format.
- Fixed a bug that prevented persisting wander risk while starting a new patient session.
NVIDIA Optimized
We have highly optimized our AI models for NVIDIA processors. This new upgrade now allows for lower latency and higher throughput on the Ouva cloud and your data centers that NVIDIA powers.
API
- Improved API endpoints to include sensor, room, department, and patient reference keys so that consuming clients no longer need to send another GET request to fetch related reference keys.
- Implemented a new GET endpoint to fetch all active patient sessions with all related records in one go (patient, room, sensor, department).
- Improved room-related GET endpoints to include related sensor and department records as well.
- Fixed a bug that allowed the patient session start endpoint to return a different patient reference key than the one provided in the first start request.
- Fixed a bug that prevented handling a valid patient session start request with a deleted sensor.
- Removed unique constraints of room and department records.
