Jewish General Hospital brings AI into Hospital@Home

Montreal’s Jewish General Hospital (JGH) – part of CIUSSS West-Central Montreal, the region’s Integrated Health and Social Services network – continues to advance its Hospital@Home program. As a key element of the CIUSSS’s Care Everywhere vision, the JGH now operates a 20-bed “virtual hospital,” delivering inpatient-level treatment to users in their own homes with the same high standard of care as on site.

It’s all made possible through a combination of remote monitoring technology and in-person visits by clinicians and support staff.

The program has treated roughly 3,400 patients at home since 2022, achieving a 93 percent satisfaction rate. In turn, this has freed up thousands of bed days, allowing other patients to access beds for surgeries and helping to reduce congestion in the Emergency Department.

Patients and staff have shown a deep appreciation for the program, resulting in rapid growth.

“What’s more, the range of conditions the program can support has expanded. From a handful of medical conditions, such as COVID-19, heart failure and straightforward infections, our Hospital@Home program is now caring for patients with about 30 different medical conditions,” said Dr. Lawrence Rudski, chief of cardiology at the JGH and medical director, strategy and development of virtual care for the CIUSSS.

“This includes a growing focus on oncology patients and palliative care as a bridge to the CIUSSS’s existing home palliation program. In some cases, even stabilized ICU patients have been able to return home sooner and receive follow-up care there.”

In fact, as part of its broader commitment to helping patients remain safely at home with the care they need, the JGH also introduced limited point-of-care testing through a partnership with a diagnostics company. This on-the-spot testing allows clinicians to confirm or rule out common respiratory viruses in minutes rather than hours, supporting faster treatment decisions without requiring a hospital visit.

Leveraging AI for better care: With rapid growth inevitably come new challenges.

“There’s a heavy burden on clinicians for screening patients for admission to the program, which is one of the reasons why Hospital@Home hasn’t scaled faster across jurisdictions,” added Erin Cook, associate CEO of CIUSSS West-Central Montreal. “Screening is a time-consuming process and there’s a formidable cognitive load on physicians and nurses.”

“Currently, the way to identify patients is to manually review paper lists, done by doctors, nurses and multidisciplinary teams – sometimes together and sometimes asynchronously,” added Dr. Rudski.

When the CIUSSS’s Virtual Care team attended a global Hospital at Home conference back in 2023, it became clear that partners from around the world were facing the same challenge.

Interestingly, a few participants at the conference said they were experimenting with AI as a screening tool. That made sense to the CIUSSS team, and they decided to investigate artificial intelligence solutions.

This is where OROT – the CIUSSS’s Connected Health Innovation Hub – steps in to support the organization’s AI-first approach, providing intelligent monitoring, real-time data integration, and predictive insights into everyday clinical decision-making.

“Digital tools enable predictions and earlier detection of deterioration, faster therapeutic adjustments, and more proactive care management. In this way, we improve outcomes for patients while reducing avoidable hospital-level care,” said Kathy Malas, director of OROT, and the CIUSSS’s chief of quality, innovation, artificial intelligence and value officer.

The JGH has also been working with Signal 1, a Toronto-based AI company, operating at the frontier of responsible healthcare AI. Its solutions are currently used at seven health systems across Canada and the United States. Together, Signal 1 and the JGH have created a first-of-its-kind AI-enabled solution for screening H@H patients in Canada.

Mara Lederman, chief operating officer of Signal 1, outlined some of the steps the AI solution considers when screening.

“There are practical factors, like are patients in the right geography and do they have an appropriate caregiver? There are inclusion criteria, exclusion criteria, and there are always a bunch of edge cases where patients look like they may be suitable, but sometimes you have to rule them out.”

She added that AI is great for this, because it can assess a great amount of data about a patient and match it to the data of patients who have successfully gone through the H@H program – all very quickly.

What’s more, it can do it on its own, pulling the data from electronic patient records.

“When the day begins, the AI can say, here are all the people we think may be suitable [for transfer to H@H]. And it can rank them on how suitable they are for a member of a clinical team to make the final decision,” said Lederman.

By leveraging OROT’s user-centric design expertise, the AI system is now being tested as team members review its outputs and compare them with their own clinical assessments. Multiple evaluation sessions have already taken place, with Signal 1 collaborating closely with hospital staff and clinicians to refine the tool. As expected, this process has led to adjustments to the algorithm to better align it with clinicians’ real-world decision-making.

“I think it’s very important to make sure we’re deploying a model that’s safe and responsible,” said Charina Alducente, clinical deployment manager at Signal 1. “We’re taking those steps together to do that. I think we’ve gotten really good feedback from each of the sessions.”
That iterative process is nearing completion, at least for version 1.0. “It’s mostly a case of tweaking the rules in order to better define and improve the accuracy,” said Dr. Rudski. “We’re hoping to launch quite soon.”

Although the AI screening algorithm is still in the testing phase at the Jewish General Hospital, the organization has already been sharing its Hospital@Home expertise across Quebec. In 2023, the Government of Quebec invested $120 million to expand H@H programs, and the JGH supported eight other organizations in launching their own initiatives.

The JGH has also applied its remote care expertise to help another Quebec hospital facing a critical nursing shortage. Over a three month period, JGH nurses cared for 150 patients remotely using augmented reality glasses. This technology enabled them to assess patients, monitor their condition in real-time, and supervise on-site care teams from a distance.

The C4 Command Centre: Not only is the Jewish General Hospital a leader in technological innovation, but it’s also re-thinking the organizational structure of the healthcare system. On this front, it created an innovative Command Centre called C4 – short for care, collaboration, creation, and communication.

C4 was originally established during the COVID-19 pandemic to predict when the hospital would have to transform units into special wards. Since then, it has been used to help reduce the numbers of Alternate Level of Care (ALC) patients in the hospital by electronically monitoring all the factors that might influence discharge and quickly marshalling the resources to overcome the roadblocks.

At the same time, the effort also encouraged more teamwork and communication throughout the organization.

Of note, the C4 reduced the number of ALC patients occupying an acute care bed from 11.4 percent in 2020 to 7.3 percent in 2022.

The success of the centre in reducing ALC numbers encouraged the organization to expand the Command Centre to better monitor four other key areas more closely, and to promote communication and creativity between these groups. The areas added in 2021 were ED overcrowding, mental health services access, virtual care integration and overall hospital flow optimization.

The JGH calls this a Team of Teams approach, an idea borrowed from the U.S. military, where members of each team are in communication with each other through a series of huddles every day. That constant communication has built a culture of collaboration and group problem-solving.

A recent incident illustrates the effectiveness of this approach. On a recent exceptionally busy day, the hospital’s Emergency Department faced a surge of 63 patients awaiting admission as inpatients – a number that compares with a typical average of between 20 and 35.

The connected teams worked together on the surge: the community team quickly arranged services for patients ready for discharge to home care; the virtual team enrolled eligible patients into remote monitoring programs; the home care group deployed extra nursing and rehab resources; and long-term care sites accelerated their intake process.

These actions enabled the safe discharge of 81 patients in 24 hours, maintaining system flow without transfers to external facilities.

It was a case of teamwork in action, with extensive digital systems enabling and enhancing the work of the people who manage the hospital, resulting in better patient care.