Deepak Gaddipati is the founder and chief technology officer at VirtuSense, an artificial intelligence company that aims to transform healthcare from reactive to proactive, alerting care teams of adverse events , such as falls, sepsis, and heart attacks, before they happen.
Gaddipati invented the first commercial AI-powered, automated, full-body scanning system, widely deployed at most US airports.
He is filled with 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 heading.
Q. You invented the full body scanning system. You suggest you can use this AI technology from the airport for healthcare and improve efficiency and deliver better results. How?
ONE. AI is already all around us – it’s in our cars, TVs, phones, our favorite streaming services and more. AI enables these devices to interpret data and make informed, unbiased decisions.
Just as airport security systems use this interpretation of data to automate security processes, AI can do the same in healthcare. With AI, you can proactively and effectively identify any threats before they become a disadvantage. The point is to train the AI to find the data you’re interested in.
Airport scanners are trained to find “events that never happen”, such as weapons, illegal substances, etc., on the way to the plane. The same vision can be applied to AI in healthcare. With millions of data points collected for a single patient, healthcare providers can proactively and effectively protect patients from medical threats and adverse events such as falls. , sepsis, heart attack, and pressure ulcers by training the AI to identify data patterns that indicate that illness.
Today’s healthcare system is built on disease care. With AI, we can help transform healthcare to healthcare through early detection of these and many other medical conditions.
Q. Do you have a mission to prevent falls because sadly your grandmother fell and died within 10 days. How does AI technology help prevent falls?
ONE. Yes, my mission to prevent falls is very personal. In 2009, my grandmother, who is healthy and has no serious medical problems, fell while walking to the bank and broke her hip. She died within ten days of the wound.
Despite several doctors in our family, she was never offered current interventions because she was never identified in the first place as being at risk for falls. In general, to be identified as at risk of a fall, you must first fall, and for many people, it is too late. So many people around the country have similar stories.
So I want to develop AI solutions to prevent falls both in the long term and in the short term. In the long run, it’s about being able to identify and address shortfalls before they become serious, and make that detection accurate, efficient and seamless, so it will be used use.
Medicine has standard tests and assessments of balance and function, but they take time to set up and run, and there is always room for human error. So combining those evidence-based assessments of gait, balance, and function with a highly specific AI trained for the smallest variations means reduced mobility. of patients can be proactively identified before they fall. From there, doctors can develop a plan of care to help regain strength and mobility.
Short-term fall prevention – stopping falls right before they happen – is harder. Proactively detecting a person trying to get up from a bed or chair is essential because that’s the crucial moment. By collecting millions of hours of data about what people do before getting up from a bed or chair, AI tools can be trained to proactively detect whether a person is about to get up from a bed or chair. are not.
From there, the tools need to communicate with other tech capabilities, instant alerts, communicate with patients, and coordinate nurses. It takes many different parts to create an AI tool that actually works in practice.
It’s important to understand that not all AI is the same. Many solutions on the market are reactive, detecting and analyzing an event upon completion. The next level is an AI solution that detects the moment before an event happens to be truly proactive and preventive for care.
Q. How can AI solve the current challenges facing healthcare, such as staff shortages and skyrocketing costs?
ONE. Healthcare organizations are now feeling squeezed on all sides, from staffing challenges to rising costs, so it’s important that the tools they adopt actively address address both concerns. AI, as a tool, is particularly good at solving everyday problems.
Preventable events, such as hospital-acquired infections and patient falls, are perfect examples of problems worsening with shortages of personnel and resources and complete perfectly suitable for AI intervention.
For example, many hospital fall prevention strategies currently rely on the use of bed attendants and telephone operators to monitor patients at risk of falls. Both approaches rely on employees staying alert while performing their normal duties, while removing those employees from the critical care role.
The AI specializes in 24/7 vigilance and pattern recognition, making it a perfect tool to stay safe and get staff back into care, instead of waiting to get care done. AI can turn hours of monitoring, waiting, and record keeping into live notifications when action is needed, saving time and reducing task overload from nursing teams.
From a cost perspective, reducing adverse health events directly reduces financial stress. To use falls as an example, patients over the age of 65 have a 33% higher risk of falling. On average, 20% of people who fall will have a serious injury. The average cost of treating these diseases is about $34,000 per case.
On top of that, an elderly person who falls has a 70% chance of dying from complications from a fall. Statistically, falls will happen and 20% of those falls will cost the organization financially through direct care costs, employee hours, quality penalties and insurance claim.
Today, the cost of monitoring high-risk patients with a custodial or telecaregiver can be extraordinary and certainly not feasible for patients classified as low-risk. than. But when you introduce AI, unit-wide monitoring — even hospital-wide monitoring — becomes financially viable, requiring no staffing and preventing 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 is a lot of research showing the rise of AI being used across the industry.
Most recently, I came across the 3rd Annual Choice Survey Report on AI in Healthcare stating that 83% of healthcare executives already have an AI strategy in place and another 15% have a plan in place. implement this strategy. Fifty-nine percent of respondents said they expect to see tangible cost savings from AI – this is a 90% jump over those surveyed in 2018.
Twitter: @SiwickiHealthIT
Email the writer: [email protected]
Healthcare IT News is a publication of HIMSS Media.
