Artificial intelligence, algorithms lead the way for health care’s ‘bold’ new future’

Data used well via artificial intelligence and transparent algorithms offers health care a glimpse into democratization and equitable, efficient and efficacious care, according to an expert speaking at The Liver Meeting Digital Experience.

“Over the next six quarters, ... we are going to see technology advancements, we are going to see policy and regulatory change and cultural expectations that will ask us to deliver cures in novel settings using novel methods and processes that will require us as providers to rethink how health care works in this country and internationally,” John D. Halamka, MD, MS, president of the Mayo Clinic Platform, said during his President’s Choice Lecture.

Prerequisites to streamlined care

Halamka challenged meeting attendees to adjust their views of what a platform is and what it offers to both physicians and patients.

“Whether you’re a provider or just a care navigator for a family ... in 2020 and 2021, care is often challenging to coordinate. It’s not clear where you go next, what disease state you have, ... bringing the right patient to the right facility ... to get the right care ... is guesswork,” he said. “We want something different. By 2030, we want continuous care that’s easy to access and navigate based on evidence and [we want to] make this care equitable and highly available to all. And if we are going to achieve that, there are several prerequisites.”

Halamka said that initiatives such as the Mayo Clinic Platform need to build on four main areas: gathering novel sources of data, discovering what the data means, validating the function of the data and subsequent algorithms, and then delivering them into the workflow.

“We need to unify the data across an entire patient experience and not just a single episode of care,” Halamka said. But he stressed “turning that data into wisdom is hard.”

The Mayo Clinic Platform deidentified more than 60,000 patients and imported their data into Google Cloud, controlling what is imported and exported to develop working algorithms.

“This corpus of data ... is used to create an [artificial intelligence (AI)] factory and that AI factory turns out algorithms in a variety of specialties including liver disease,” Halamka said.

Those algorithms must then be tested, ensuring transparency to anyone who may wish to use them in the future and enabling an action after implementing them. Already in its 5 years of implementation, the Mayo Clinic Platform generated more than 60 algorithms.

“The notion of this Mayo Clinic Platform is to build these Lego blocks ... so we can empower a whole variety of new investigations, new cures and reach more people than ever before using these algorithms,” he said.

COVID-19 turning point

Though the COVID-19 pandemic challenged many aspects of health care, Halamka said it also taught us that so much more is possible.

“I would argue these last 2 years of COVID have taught us that bricks and mortar in some circumstances can be replaced with clicks and orders,” he said. “If one has remote patient monitoring, the right telemetry to understand a disease state and its progression, the right command center, where you have the right experts, the right dashboards, the right care plans, the right supply chain and workflow processes, the right staffing, you’re able to deliver a variety of novel therapies in nontraditional places.”

Specifically, Halamka said a patient’s home is often the best place for them to stay while receiving treatment. It lessens the risk of infection, lowers cost of care and is a game changer for older patients who may experience “sundowning” when moved into a new environment.

In treating one disease, he said Mayo Clinic implemented its method of starting small, thinking big and moving fast.

“We moved from one patient to 10 patients. Ten patients to 100, 100 to 1,000. Today, we have treated 3,000 patients with serious and complex illness at a distance. We have achieved the same outcomes, the same quality, the same safety, markedly reduced cost, markedly reduced readmission rates, markedly reduced nosocomial infections and other complications,” he said.

‘Imagine the future’

In looking ahead, Halamka said it is on the people of health care to meet the demands of the patients.

“Imagine the future as we’ve talked about it: more algorithms, more data and more nontraditional settings,” he said. But success with those pieces requires the right people — health care providers who can come to the home, set up for the patient, handle the supply chain and recognize the role the home plays in patient care.

“There’s a cultural change that has occurred as well. Patients are expecting care to be virtual in many circumstances because of its convenience and what it does for remarkable patient satisfaction,” he said. “As we deploy algorithms, we need to take into account all the variety of patients we are seeing, including factors like socioeconomic status. ... If you pick up an algorithm that’s been developed for hepatology, do you know how it’s been developed? If it will work for the patient in front of you?”

Physicians must meet their patients at a level of comfort — with technology, with automation, with personalized care.

“Let’s meet the patients at their level of technological comfort and sophistication. Let’s take into account social determinants of health and socioeconomic status. In doing so, we are going to achieve a very high quality of unbiased care and we are going to ensure that patients get the right care at the right time in the right setting,” Halamka said. “I believe this future we are, in the next 6 quarters, going to explore together will be increasingly digital first. It will not in any way diminish the importance of humans or human contact but it will give our families the tools they need to get that care they want and need in a much easier fashion than in the past.”

Data is democracy in health care and should be utilized in a way to make health care more effective, efficient and equitable, he said.

“Taking the world class specialists in hepatology and making their knowledge available to all who need it in a democratized fashion through increasing use of data and personalized care is truly a bold future and I think we would all agree we’re all in this to make health care better globally and these tools I described to you today will help us achieve this better future,” Halamka said.