Can virtual nursing combined with computer vision AI boost care quality?

Nurses are the lifeblood of the healthcare system. But unprecedented levels of burnout and staff shortages have left many exhausted.

But the population is aging rapidly and the acuity of patients is increasing. This translates into a higher patient load per nurse, which can lead to an increase in medical errors, infections, pressure sores and even mortality rates.

Virtual nursing has shown tremendous potential to help address these gaps, but a critical consideration for its effectiveness is often overlooked: Ultimately, the success of a virtual nursing program depends on the technologies in place at a given provider.

Narinder Singh is co-founder and CEO of LookDeep Health, a provider of AI-powered video monitoring tools designed for patient care.

We interviewed Singh to discuss why virtual nursing is getting so much attention, wwhat computer vision AI is and why he thinks it should be integrated with virtual nursing technologies, what effective collaboration between virtual nurses and AI technology could look like, and how AI can improve care and improve outcomes for hospitals and healthcare systems.

Q. Virtual nursing is getting more attention these days. Why is this?

A. Nursing workforce challenges have increased over the past decade, with few measures taken to address them. COVID created massive demand and burnout, exacerbating the problem of nurses leaving the industry.

This culminated in huge explosions in the costs of travel nursing bringing all these issues to the forefront of the executive suite. Workforce challenges became the top issue cited by hospital CEOs.

Most actions aimed at improving offerings and reducing burnout are neither easy nor quick. Virtual nursing, while narrowly defined, is one of the few concrete solutions available. Healthcare IT vendors stood out, creating and running their solutions.

Yet most solutions are very narrowly defined or deployed. For example, organizations often drive a camera and monitor into the patient room and have a virtual nurse do the admission or discharge of a patient. This is a concrete, positive action. However, it is difficult for a bedside nurse to focus on one patient while caring for other patients during these processes.

At the same time, it saves a nurse at the bedside approximately one hour per patient over an average stay of five days. Assuming that a nurse cares for four to seven patients during a normal shift, this is a real benefit for the nurse at the bedside: it gives them more time for other patients and has a positive impact on burnout.

Initially, this time savings allowed hospitals to expand their bedside teams (reducing the burnout benefit) and partially reduce the use of expensive travel nurses. But as travel nursing is reduced, its financial benefits quickly diminish; Ultimately, the same amount of work is still done by a nurse – whether it’s a bedside nurse or a virtual nurse.

There is an important and clear advantage to virtual nursing. However, if it can only shift where the work is done, it is a tactic – not a strategy.

Q. What is computer vision AI, and why do you think it should be integrated with virtual nursing technologies?

A. Computer vision is a branch of artificial intelligence that focuses on understanding what is happening in an image or series of images (video). Examples of common uses include identifying objects (people, beds, equipment); defining how people move (pose estimation); and identifying when certain actions occur (getting out of bed, eating, lying down, walking).

One of the key workforce challenges is that nurses cannot be everywhere at once. When a nurse is with one patient, he or she is by definition not focused on the other five to seven patients. This is usually fine, because patients are often limited in their ability to move or rest.

At other points, however, it means that the nurse misses important details of the patient’s journey. Walking into a patient’s room and seeing him or her lying on the floor or writhing in pain creates urgency without any context – for example, what happened, how long has it been happening?

If the computer can simply keep an eye on you – ignoring the unimportant but important details – it is actually helping the nurse with their work. In addition to specific activity at a specific time, this type of ‘watching AI’ can track patterns over longer periods of time.

How much time does the patient spend in bed today compared to yesterday; how much and when they exercise most; how much time clinical staff spend on this; and much more. These can provide new insights into a patient’s journey.

With this addition, virtual nursing technologies can become dramatically more relevant to virtually every aspect of bedside team support.

Q. What does effective collaboration between virtual nurses and AI technology look like?

A. Early AI solutions for hospitals presented themselves as magical, but they routinely disappointed or failed to understand how long it would take to be reliable. Today’s most advanced computer vision applications – self-driving cars – have been close to completion for almost a decade.

The stakes are just as high for acute care, but a decade of development is not practical. A better pattern is human plus AI, where the AI ​​draws a virtual nurse’s attention to a specific situation, and that nurse can then supplement the data (what medications the patient is taking, lab values, procedures, etc.) and take broader action. within the context of their human expertise. It is driving assistance for hospitals.

An important caveat is that attempts to force that assistance directly to bedside nurses will burden an already burned-out population. Instead, have the AI ​​assist a virtual nurse and have the virtual nurse make a final assessment and communicate it to the bedside team.

In this way, it protects the nurse’s time at the bedside and gives them a familiar interface (another nurse) to communicate and interact with.

Even within these concepts, there is a tremendous amount of work to be done to transform tactical virtual nursing solutions into a strategic factor to improve hospital care. For example, it is critical to identify which tasks, processes, or assessments should be AI-powered and completed by a virtual nurse.

Examples of this include nudging when patients have had a poor night’s sleep, are at increased risk for pressure ulcers due to a lack of exercise, or helping with certain best practices that the hospital has defined (for example, a delirium prevention checklist, such as ensuring that the blinds are open/closed).

Virtual nurses become the core user of AI nudges and a guardian angel for the bedside team.

Q. How can this AI technology improve outcomes for hospitals and healthcare systems?

A. Investments to support nursing workflows are generally not reimbursable. Therefore, hospitals and healthcare systems must justify themselves by demonstrating labor efficiency or better outcomes with clear financial ties (reduction in falls or pressure ulcers, length of stay, readmissions, etc.).

While this feels like a higher bar, it’s also clearer and more lasting. Exceeding this will result in widespread adoption in every hospital in the US and around the world.

At a macro level, staff salaries represent 50-60% of costs in a hospital (nursing is one of the largest components). Time with the patient is between 10-50% of what doctors and nurses do in the hospital.

Over the next decade, computer vision AI will be able to do 5 to 20% of the work that takes place in a hospital. Much of this will be done with the help of a virtual nurse. AI allows the virtual nurse to continuously do more: see the right patients quickly, perform visual assessments of the patient, and complete documentation automatically.

Still, it’s critical that we don’t try to translate what a virtual nurse can do with AI from the bedside to the bottom line. Much of these productivity improvements must be reinvested in the healthcare model of the future.

Those investments will be different, but important: more mentorship for new nurses, more investments in nursing assistants and certain high-quality nursing skills, for example. By using these revolutionary tools to modernize healthcare models, we can generate substantial financial returns and improve patient care.

To do this, physicians will need to take the lead in this change. Just as revenue optimization alone cannot create a profitable business, relying on overly simplistic ratios will undermine this revolution. A system powered by computer vision can provide new insights into how much care is applied to which patients and under what circumstances. But it’s just an instrument; our nurses and doctors are the magicians who can use this to orchestrate care.

We can use more data about what the patient does when he or she is alone and combine this with insight into where care is provided, so that we can provide the right care to the right patient more often. AI to expand the scope of patient and care observation, combined with virtual nursing and healthcare design improvements, can revolutionize hospital patient care and create a more sustainable financial model for hospitals in any region.

Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email him: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.