'

How sensors enabled Eli Lilly to improve the patient experience

Combining the use of sensors and automation, the pharmaceutical giant looked into an approach that enabled independence for the patient and alleviated burden on the caregiver.

Global pharmaceutical company Eli Lilly set itself a "big, hairy audacious" goal to engage more people in clinical trials, but after visiting caregivers and their patients, the company soon realised more was needed than just developing medication and having it trialled.

Dave Crumbacher, Technology Architect at Eli Lilly and Company, told the AWS re:Invent conference in Las Vegas on Monday that his company tweaked its initial goal to one that makes clinical trials an option for all.

To do that, Crumbacher said the focus of Eli Lilly needed to be one alleviating the burden of participating in a clinical trial.

"Before we jumped to a technical solution, we wanted to see what we could learn," he explained. "We needed to gain empathy by going to an adult care centre for patients with dementia."

The team interviewed a number of caregivers to help them understand their burdens and what they were going through, Crumbacher said.

"It would be very difficult for them to take on the extra burden of participating in clinical trials," he said.

As technology can come with unintended consequences -- and it can also become the burden -- Crumbacher said the company needed to apply technology in a way that the users aren't even aware is there.

"An app in someone's hand might not be the right solution ... for someone with dementia, using an app doesn't make sense," he added. "We needed to come up with different ways to address that that aren't burdensome."

Eli Lilly turned to the use of ambient intelligence: Technology-enabled environments that are sensitive and responsive to the presence of people.

"Ambient technology is automatic, it just works, has natural interfaces, very simple to deploy -- set and forget -- and fades into the background," Crumbacher explained. "Lastly, it has low maintenance."

As sensor technology can help Eli Lilly gain a sense of the patient and caregivers' environments, Crumbacher said a whole new awareness was exposed.

"Our goal is not to just become aware of the environment, but create assistance," he explained.

Looking into the use of machine learning and artificial intelligence, enabled through the Internet of Things (IoT), Eli Lilly identified yet another need: The caregiver needs to know if their patient with Alzheimers took his medication.

Eli Lilly needed to deploy sensors to alert the patient to where the pill bottle was at the time he needed to take it and the caregiver then needed to be notified when the pill was taken.

"If we know the patient is close to the pill bottle, and it moves, it's a pretty good approximation that he has taken it -- so we then notify the caregiver," Crumbacher said.

Eli Lilly developed a 3D-printed pill bottle prototype, complete with its own IoT sensor; the company also built-out a software prototype for the caregiver, an app that allowed caregivers to communicate with others and be notified when their patient took the medication.

The smart pill bottle sends out an alert that notifies the patient it is time to take the medication. It also contains a beacon that communicates back to base stations deployed in the patient's environment. As a beacon is also present on the patient, when the two beacons are next to one another, the base station sends an alert to the caregiver via their smartphone app.

AWS allowed Eli Lilly to coordinate these activities.

"This is very much an IoT-centric architecture -- the pill bottle has an IoT shadow associated with it and with that, the shadow can be updated to say, 'It's time to turn on the alarm for the pill bottle' and the patient app is aware of that and is getting the notification," Crumbacher said.

The IoT solution uses DynamoDB to manage the messages on the caregiver app, which also allows them to communicate.

Eli Lilly then took the IoT data and moved it into a Kinesis stream associated with an analytics tool to gain an understanding of the base station data that's being reported to figure out where the patient is located. That data is then sent to a Lambda function to isolate the patient's exact location.

"We then built an Alexa skill that allows an Echo to then ask a question: 'Alexa, where is the patient?'," Crumbacher added.

From here, Eli Lilly has added further sensors and equipment to test out further capabilities of the IoT solution it has developed, with the overarching goal of making clinical trials more accessible for patients and their caregivers.

PREVIOUS AND RELATED COVERAGE

What is cloud computing? Everything you need to know about the cloud, explained

Updated: An introduction to cloud computing right from the basics up to IaaS and PaaS, hybrid, public, and private cloud.

Intuit to use AWS as its standard artificial intelligence platform

Intuit is planning to weave artificial intelligence and machine learning throughout its products. The company will use AWS' AI platform as a standard.

Amazon media services make it easier for companies to create, manage video in the cloud (TechRepublic)

With AWS Elemental Media Services, companies can build end-to-end video workflows in the cloud at a lower cost.

AWS Lambda: The smart person's guide (TechRepublic)

This comprehensive guide covers AWS Lambda, an on-demand serverless computing service. Learn how Lambda complements other AWS services, and how your business can use it.

Disclaimer: Asha McLean travelled to AWS re:Invent as a guest of AWS.