
Ahead of a visit to the hospital for a surgical procedure, patients often have plenty of questions about what to expect - and can be plenty nervous.
To help minimize presurgery jitters, NVIDIA and Deloitte are developing AI agents using NVIDIA AI to bring the next generation of digital, frontline teammates to patients before they even step foot inside the hospital.
These virtual teammates can have natural, human-like conversations with patients, answer a wide range of questions and provide supporting guidance prior to preadmission appointments at hospitals.
Working with NVIDIA, Deloitte has developed Frontline AI Teammate for use in settings like hospitals, where the digital avatar can have practical conversations - in any language - that give the end user, such as a patient, instant answers to pressing questions.
Powered by the NVIDIA AI Enterprise software platform, Frontline AI Teammate includes avatars, generative AI and large language models.
Avatar-based conversational AI agents offer an incredible opportunity to reduce the productivity paradox that our healthcare system faces with digitization, said Niraj Dalmia, partner at Deloitte Canada. It could possibly be the complementary innovation that reduces administrative burden, complements our healthcare human resources to free up capacity and helps solve for patient experience challenges.
Next-Gen Technologies Powering Digital Humans Digital humans can provide lifelike interactions that can enhance experiences for doctors and patients.
Developers can tap into NVIDIA NIM microservices, which streamline the path for developing AI-powered applications and moving AI models into production, to craft digital humans for healthcare industry applications. NIM includes an easily adaptable NIM Agent Blueprint developers can use to create interactive, AI-driven avatars that are ideal for telehealth - as well as NVIDIA NeMo Retriever, an industry-leading embedding, retrieval and re-ranking model that allows for fast responses based on up-to-date healthcare data.
Customizable digital humans - like James, an interactive demo developed by NVIDIA - can handle tasks such as scheduling appointments, filling out intake forms and answering questions about upcoming health services. This can make healthcare services more efficient and more accessible to patients.
In addition to NIM microservices, James uses NVIDIA ACE and ElevenLabs digital human technologies to provide natural, low-latency responses.
NVIDIA ACE is a suite of AI, graphics and simulation technologies for bringing digital humans to life. It can integrate every aspect of a digital human into healthcare applications - from speech and translation abilities capable of understanding diverse accents and languages, to realistic animations of facial and body movements.
Deloitte's Frontline AI Teammate, powered by the NVIDIA AI Enterprise platform and built on Deloitte's Conversational AI Framework, is designed to deliver human-to-machine experiences in healthcare settings. Developed within the NVIDIA Omniverse platform, Deloitte's lifelike avatar can respond to complex, domain-specific questions that are pivotal in healthcare delivery.
The avatar uses NVIDIA Riva for fluid, multilingual communication, helping ensure no patient is left behind due to language barriers. It's also equipped with the NeMo Megatron-Turing 530B large language model for accurate understanding and processing of patient data. These advanced capabilities can make clinical visits less intimidating, especially for patients who may feel uneasy about medical environments.
Personalized Experiences for Hospital Patients
Patients can get overwhelmed with the amount of pre-operative information. Typically, they have only one preadmission appointment, many weeks before the surgery, which can leave them with lingering questions and escalating concerns. The stress of a serious diagnosis may prevent them from asking all the necessary questions during these brief interactions.
This can result in patients arriving unprepared for their preadmission appointments, lacking knowledge about the appointment's purpose, duration, location and necessary documents, and potentially leading to delays or even rescheduling of their surgeries.
To enhance patient preparation and reduce pre-procedure anxiety, The Ottawa Hospital is using AI agents, powered by NVIDIA and Deloitte technologies, to provide more consistent, accurate and continuous access to information.
With the digital teammate, patients can experience benefits including:
24/7 access to the digital teammate using a smartphone, tablet or home computer.
Reliable, preapproved answers to detailed questions, including information around anesthesia or the procedure itself.
Post-surgery consultation to resolve any questions about the recovery process, potentially improving treatment adherence and health outcomes.
In user acceptance testing of the digital teammate conducted this summer, a majority of the testers noted that responses provided were clear, relevant and met the needs of the given interaction.
The Frontline AI Teammate offers a novel and innovative solution to help combat our health human resource crisis - it has the potential to reduce the administrative burden, giving back time to healthcare providers to provide the quality care our population deserves and expects from The Ottawa Hospital, said Mathieu LeBreton, digital experience lead at The Ottawa Hospital. The opportunity to explore these technologies is well-timed, given the planning of the New Campus Development, a new hospital project in Ottawa. Proper identification of the problems we are trying to solve is imperative to ensure this is done responsibly and transparently.
Deloitte is working with other hospitals and healthcare institutions to deploy digital agents. A patient-facing p
More from Nvidia
26/10/2025
This year's ROSCon conference heads to Singapore, bringing together the global robotics developer community behind Robot Operating System (ROS) - the world&...
24/10/2025
Monday, Oct. 27, 12:30 p.m.
How Medium-Sized Cities Are Tackling AI Readiness
L to R: Mark Muro, senior fellow at Brookings Metro; Micah Runner, city manag...
23/10/2025
The nights grow longer and the shadows get bolder with Vampire The Masquerade: B...
21/10/2025
Coastal communities in the U.S. have a 26% chance of flooding within a 30-year period. This percentage is expected to increase due to climate-change-driven sea-...
20/10/2025
NVIDIA and Google Cloud are expanding access to accelerated computing to transform the full spectrum of enterprise workloads, from visual computing to agentic a...
17/10/2025
As Open Source AI Week comes to a close, we're celebrating the innovation, c...
17/10/2025
AI has ignited a new industrial revolution.
NVIDIA and TSMC are working togethe...
16/10/2025
GeForce NOW is more than just a platform to stream fresh games every week - it offers celebrations for the gamers who make it epic, with member rewards to sweet...
14/10/2025
AI is transforming the way enterprises build, deploy and scale intelligent applications. As demand surges for enterprise-grade AI applications that offer speed,...
14/10/2025
At Oracle AI World, NVIDIA and Oracle announced they are deepening their collabo...
13/10/2025
The future of AI took flight at Starbase, Texas - where NVIDIA CEO Jensen Huang ...
13/10/2025
At the OCP Global Summit, NVIDIA is offering a glimpse into the future of gigawa...
09/10/2025
NVIDIA Blackwell swept the new SemiAnalysis InferenceMAX v1 benchmarks, deliveri...
09/10/2025
Microsoft Azure today announced the new NDv6 GB300 VM series, delivering the ind...
09/10/2025
Lock, load and stream - the battle is just beginning. EA's highly anticipated Battlefield 6 is set to storm the cloud when it launches tomorrow with GeForce...
08/10/2025
Telecommunication networks are critical infrastructure for every nation, underpi...
02/10/2025
Editor's note: This blog has been updated to include an additional game for October, The Outer Worlds 2.
October is creeping in with plenty of gaming treat...
01/10/2025
Many users want to run large language models (LLMs) locally for more privacy and control, and without subscriptions, but until recently, this meant a trade-off ...
30/09/2025
Quantum computing promises to reshape industries - but progress hinges on solvin...
30/09/2025
Editor's note: This blog is a part of Into the Omniverse, a series focused o...
25/09/2025
Suit up and head for the cloud. Mecha BREAK, the popular third-person shooter, is now available to stream on GeForce NOW with NVIDIA DLSS 4 technology.
Catch i...
24/09/2025
Canada's role as a leader in artificial intelligence was on full display at ...
24/09/2025
Open technologies - made available to developers and businesses to adopt, modify...
23/09/2025
Energy efficiency in large language model inference has improved 100,000x in the...
22/09/2025
OpenAI and NVIDIA just announced a landmark AI infrastructure partnership - an initiative that will scale OpenAI's compute with multi-gigawatt data centers ...
19/09/2025
AI is no longer solely a back-office tool. It's a strategic partner that can...
18/09/2025
The U.K. was the center of the AI world this week as NVIDIA, U.K. and U.S. leade...
18/09/2025
GeForce NOW is packing a monstrous punch this week. Dying Light: The Beast, the latest adrenaline fueled chapter in Techland's parkour meets survival horror...
17/09/2025
Today's creators are equal parts entertainer, producer and gamer, juggling game commentary, scene changes, replay clips, chat moderation and technical troub...
16/09/2025
The U.K. is driving investments in sovereign AI, using the technology to advance...
13/09/2025
Celtic languages - including Cornish, Irish, Scottish Gaelic and Welsh - are the U.K.'s oldest living languages. To empower their speakers, the UK-LLM sover...
10/09/2025
GeForce NOW Blackwell RTX 5080-class SuperPODs are now rolling out, unlocking a new level of ultra high-performance, cinematic cloud gaming.
GeForce NOW Ultima...
09/09/2025
Inference has emerged as the new frontier of complexity in AI. Modern models are...
09/09/2025
As large language models (LLMs) grow larger, they get smarter, with open models from leading developers now featuring hundreds of billions of parameters. At the...
09/09/2025
At this week's AI Infrastructure Summit in Silicon Valley, NVIDIA's VP o...
09/09/2025
Inference performance is critical, as it directly influences the economics of an AI factory. The higher the throughput of AI factory infrastructure, the more to...
09/09/2025
At this week's IAA Mobility conference in Munich, NVIDIA Vice President of A...
09/09/2025
ComfyUI - an open-source, node-based graphical interface for running and buildin...
04/09/2025
NVIDIA today announced new AI education support for K-12 programs at a White House event to celebrate public-private partnerships that advance artificial intell...
04/09/2025
Editor's note: This post is part of the AI On blog series, which explores the latest techniques and real-world applications of agentic AI, chatbots and copi...
04/09/2025
NVIDIA Blackwell RTX is coming to the cloud on Wednesday, Sept. 10 - an upgrade ...
03/09/2025
3D artists are constantly prototyping.
In traditional workflows, modelers must build placeholder, low-fidelity assets to populate 3D scenes, tinkering and adju...
02/09/2025
For more than a century, meteorologists have chased storms with chalkboards, equ...
28/08/2025
Brace yourself, COGs - the Locusts aren't the only thing rising up. The Coal...
28/08/2025
Last week at Gamescom, NVIDIA announced the winners of the NVIDIA and ModDB RTX ...
27/08/2025
AI models are advancing at a rapid rate and scale.
But what might they lack that (most) humans don't? Common sense: an understanding, developed through rea...
25/08/2025
Robots around the world are about to get a lot smarter as physical AI developers...
25/08/2025
As autonomous vehicle systems rapidly grow in complexity, equipped with reasonin...
22/08/2025
As the latest member of the NVIDIA Blackwell architecture family, the NVIDIA Blackwell Ultra GPU builds on core innovations to accelerate training and AI reason...
22/08/2025
AI reasoning, inference and networking will be top of mind for attendees of next...