Deepak Gaddipati is founder and chief technology officer at VirtuSense, an artificial intelligence company that aims to transform healthcare from reactive to proactive by alerting care teams to adverse events such as falls, sepsis and heart attacks before they occur.

Gaddipati invented the first commercial full-body, automated, AI-powered scanning system, which is widely deployed across most U.S. airports.

He is steeped in the power of AI. Healthcare IT News sat down with Gaddipati to discuss some of his work in healthcare with AI and where he sees the technology headed.

Q. You invented the full-body scanning system. You suggest you can take this AI technology from airports to healthcare and improve efficiencies and drive better outcomes. How?

A. AI already is around us. It's in our cars, TVs, phones, favorite streaming services and much more. AI enables these devices to interpret data and make informed, unbiased decisions.

Just as airport security systems use this data interpretation to automate security processes, AI can do the same in healthcare. With AI, you can proactively and efficiently identify any threats before they become detrimental. It's a matter of training AI to find the data you care about.

Airport scanners are trained to find "never events," such as weapons, illegal substances, etc., making their way onto the plane. The same vision can be applied to AI in healthcare. With millions of data points captured for a single patient, healthcare providers can proactively and efficiently protect patients from medical threats and adverse events such as falls, sepsis, heart attacks and pressure ulcers by training AI to identify the data pattern that indicates that malady.

Today's healthcare system is built on sick care. With AI, we can help transition care to healthcare through early detection of these and many other medical conditions.

Q. You have a mission to prevent falls because, sadly, your grandmother fell and within 10 days passed away. How does AI technology help prevent falls?

A. Yes, my mission to prevent falls is very personal. In 2009, my grandmother, who was healthy and had no severe medical issues, fell while walking to the bank and broke her hip. She died within ten days of the injury.

Even though there were several physicians in our family, she had never been offered existing interventions because she was never identified as a fall risk in the first place. Generally speaking, to be identified as a fall risk, you must first fall, and for many people, that is too late. So many people across the country have similar stories.

So, I wanted to develop AI solutions that prevent falls both in the long term and short term. For the long term, it was about being able to identify and take care of deficits before they become severe, and making that detection accurate, efficient and seamless, so it would be used.

Medicine has standardized tests and assessments for balance and function, but they take time to set up and conduct, and there's always room for human error. So, combining those evidence-based assessments for gait, balance and function with a highly specific AI trained for the smallest variants meant patients' mobility deficits could be proactively identified before they fall. From there, doctors can develop a care plan to help regain strength and mobility.

Short-term fall prevention – stopping falls just before they happen – is trickier. Proactive detection of an individual trying to get up from a bed or chair is essential as that is the vital moment. By collecting millions of hours of data on what people do before they get up from a bed or chair, AI tools can be trained to proactively detect if a person is going to get up from the bed or chair.

From there, tools need to interface with other tech capabilities, immediate alerting, communication with patients and nurse coordination. It takes many different pieces to create an AI tool that really works in practice.

It is important to understand that not all AI is the same. Many of the solutions on the market are reactive, detecting and analyzing an event upon its completion. The next level is an AI solution that detects the moment before the event happens to really make care preventative and proactive.

Q. How can AI solve challenges plaguing healthcare today, such as staffing shortages and skyrocketing costs?

A. Healthcare organizations are feeling a squeeze on all sides right now from staffing challenges to rising costs, so it is vital that the tools they adopt actively address both concerns. AI, as a tool, is particularly good at tackling routine problems.

Preventable events, such as hospital-acquired infections and patient falls, are perfect examples of problems that get worse with staffing and resource shortages and are perfectly suited for AI intervention.

For instance, many hospital fall-prevention strategies currently rely on employing bedside sitters and tele-sitters to monitor patients who are at risk of falling. Both approaches rely on staff to stay vigilant while performing mundane work, while also taking those employees out of an active care role.

AI specializes in 24/7 vigilance and pattern recognition, making it a perfect tool to maintain safety and get employees back to performing care instead of waiting to perform care. AI can transform hours of watching, waiting and record-keeping into a direct notification when action is needed, saving time and relieving task overload from nursing teams.

From a cost perspective, reducing adverse health events directly eases financial strain. To use falls as an example, patients over the age of 65 are 33% more likely to fall. On average, 20% of those who fall will get a major injury. The cost of treating these major falls averages around $34,000 per instance.

On top of this, an elderly person that falls has a 70% likelihood of dying as a result of complications from their fall. Statistically, falls will happen and 20% of those falls will cost the organization financially through direct care costs, staff hours, quality penalties and insurance claims.

Today, the cost of monitoring high-risk patients with sitters or tele-sitters can become astronomical and certainly unfeasible for patients who are classified as lower risk. But when you introduce AI, unit-wide monitoring – even hospital-wide monitoring – becomes financially feasible, doesn't require increasing staffing and prevents falls. The same can be said for solutions that use AI to prevent pressure ulcers, sepsis and other standard hospital risks.

Leveraging AI to transform healthcare is the future. There are numerous studies showing an uptick in AI being used across the industry.

I most recently came across the 3rd Annual Optum Survey on AI in Health Care report that stated 83% of healthcare executives already have an AI strategy, and another 15% plan to implement one. Fifty-nine percent of the respondents stated they expect to see tangible cost savings from AI – which is a 90% jump compared to those surveyed in 2018.

Twitter: @SiwickiHealthIT
Email the writer: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.