Building a robust architecture
Tim Llewellynn is the CEO and co-founder of nViso, one of the world’s leading specialists in AI-driven facial analytics. When ePAT reached out to his team, the initial discussions led both organizations to realize that they had a huge opportunity to change pain management for the better.
“Our scientists talked to their scientists, and there was a real meeting of minds,” says Llewellynn. “We quickly decided to kick-start an innovation process and design a prototype to prove the concept.”
Daffas adds: “When you are trying something new in healthcare, you need to do it in stages. You start by working with healthcare organizations and helping them see that a new technology is genuinely beneficial. Next, you need to gain regulatory approval. Finally, you can start thinking about making a consumer-grade product.
“So our first goal was to build a tool that would help pain management specialists, physicians and other professional caregivers conduct assessments more easily and reliably.”
ePAT began working with nViso to develop a medical device in the form of a smartphone app. The app uses the smartphone camera to record a ten-second video of the patient’s face, and analyzes the images using nViso’s sophisticated facial analysis algorithms. If it recognizes any muscle movements that indicate pain, it takes note of them.
Next, the caregiver uses the app to answer questions regarding a total of 42 pain indicators, such as how the patient is moving and how they are vocalizing their pain. Finally, the app calculates an overall pain score for the patient, and syncs the results with a central database in the cloud. This allows caregivers to keep track of patients’ pain scores over time, and monitor whether medication and other pain management strategies are working effectively.
Daffas comments: “From a technical perspective, the project was challenging. Although the solution is delivered like a regular smartphone app, it needs to be engineered to medical device standards in order to pass regulatory scrutiny. We’re aiming to achieve Australian and European approvals later this year, and then start the complex process of gaining FDA approval in the United States.”
Llewellynn adds: “At nViso, we’ve had success in the past using IBM technologies to build solutions for other heavily regulated industries, such as finance. We also know that IBM has a lot of expertise in medical device development. So, we were confident that IBM was the right partner for this project.”
The design of the device needed to embrace “offline first” principles: it must be able to work without a data connection in case a user is temporarily unable to connect to the internet. At the same time, it needs the ability to send data to the cloud when a connection is re-established, so that the patient’s data is stored and protected in the event that the device is lost or broken.
Llewellynn says: “IBM® Cloudant® offers seamless replication capabilities, making it the perfect choice for us—it’s very easy to store data locally on the device and then sync it seamlessly with the central cloud data store when you’re next connected.
“We also liked the fact that Cloudant is a fully managed service, so we don’t need to worry about database management—we can focus on developing our application and leave the underlying infrastructure to the experts from IBM. And finally, unlike a traditional relational database, Cloudant doesn’t have a rigid schema, which makes it much easier to rethink our data structures as the project’s requirements evolve.”
Daffas agrees: “Flexibility is vital for any innovative project, and particularly for one that involves a multi-stage process, with different groups of stakeholders providing input at each stage. We have to be able to listen to the healthcare professionals, the regulators and—where possible—the patients themselves, and adapt our app to their needs. Technologies such as Cloudant can give us the ability to do just that.”
Moving from prototype to production
The ePAT device is now being trialed by a number of major healthcare organizations in Australia, and has completed its initial validation and implementation studies.
“Validation studies aim to show that our device provides good results compared to other tools that are currently in use; implementation studies explore how compatible it is with caregivers’ current workflows,” explains Daffas. “The feedback from both types of study has been very positive—our users are confident that the ePAT app is accurate compared to traditional paper-based assessment forms, and we are now exploring its clinical utility in daily caregiver practice.”
Llewellynn comments: “The current version of the app is just a first step on the journey—it gives caregivers a computer-assisted data collection tool that harnesses AI for one aspect of the assessment process. In the future, we aim to expand the use of AI to other areas too, and we’re excited by the prospect of harnessing IBM Watson® cognitive services to augment our capabilities.
“For example, one of the most common problems in healthcare—and one of the biggest barriers to unsupervised in-home care—is the risk of a patient accidentally taking the wrong medication. We could use Watson Visual Recognition to scan the barcodes on medication bottles, helping patients and caregivers double-check that they’re doing the right thing before they administer the meds.”
Daffas agrees: “It’s all about making pain management as easy and user-friendly as possible—using technology to make life simpler for healthcare professionals, patients and their families. Collaborative partnerships between companies such as ePAT, nViso and IBM are essential to make this happen.
“As we move ahead with the regulatory approval process, we’re confident that we have the right skills and technology in place to deliver a solution that helps healthcare organizations around the world transform the way they deliver pain management services. Ultimately, the outcome should be a model that helps patients live fuller, happier lives—relieving their pain more successfully, allowing them to spend more time at home and less in the hospital, and reducing the cost of care.”