At HIMSS20, two experts from Optum will offer tips and best practices for clinical and operational machine learning deployments.
Given all the relentless hype about its artificial intelligence and its transformative potential for healthcare, it would be understandable if some health systems might be casting about in search of AI or machine learning projects they could try.
But that sort of rushed, ad hoc approach is precisely the wrong one to take, says Tushar Mehrotra, senior vice president of analytics at Optum.
“The only way you are going to get value out of AI is to link the clinical or business problem to the organization’s overall strategy and make sure you have a rich enough data set to train the model so it generates actionable insights,” said Mehrotra.
Want to publish your own articles on DistilNFO Publications?
Send us an email, we will get in touch with you.
“Making sure you are building and designing your AI effort the right way means putting in the work up front to create a clear understanding of what you are trying to solve so it can be embedded in the decision-making workflow,” he said. “Too often, AI projects start with a quest for academic insight.”
At HIMSS20, Mehrotra and his colleague, Optum SVP of Artificial Intelligence and Analytics Platforms Sanji Fernando will offer their perspectives on how AI can be applied to promote growth and speed strategies for digital transformation.
“The providers that have seen the most success in AI initiatives are organizations that begin planning around what they are trying to solve, rather than open-ended academic experimentation,” said Fernando.
“From there, consider the data you are using to train your AI models,” he suggested. “How rich are the data, how much do you have, and how well do you understand the decisions that will be made off the data?”
Another key question: “With the automation you are creating, what are the outcomes of these decisions aided by the data?” said Fernando. “If the decisions directly impact outcomes in healthcare for patients, there should be a higher hurdle than for decisions around reimbursement, though those are important too.”
If those are some of foundational questions health systems should be asking themselves as they ponder potential AI deployments, there are also some common pitfalls to avoid.
“Depending on where they are in the country and in their AI maturity level, some providers need to put more consideration into how they will access certain kinds of talent to accomplish their goals,” Mehrotra explained. “While there has been considerable progress in recent years in the distribution of talent beyond the Northeast and West Coast, it can still be tricky. Organizations need to figure out what kind of talent to hire so they don’t, say, bring on 15 data scientists and have them all writing reports.”
In addition, “some organizations overlook the level of access they have to the data that will feed the models,” said Fernando. “AI models are only as powerful as that data you train them on. You need to know your business and the data your business runs on. If you do not have access to the data or the richness of it, you are missing an important piece, which will also limit your ability to link the model to the business problem.”
With proper planning, staffing and access protocols in place, AI and machine learning can help unlock some huge advances, particularly when it comes to driving cost efficiencies.
“We’ve seen the biggest material, quantified impact in operational and financial implementations – call them administrative operational use cases,” said Fernando.
“These include chart review, utilization and management and claims processing,” he explained. “So far, it has been more for making or approving reimbursement decisions and not necessarily automating clinical care. The maturity of technology may limit us from doing that successfully for the immediate term but the work continues to sharpen the technology enough for those clinical uses.”
If financial and operational projects offer a relatively easier initial launchpad for AI deployments – something another Optum exec recently described as a “walk before you run” approach – significant clinical gains are also on the horizon for those providers who do machine learning right.
“Very soon clinical decision supported – or augmented, as the AMA notes – with AI will happen,” said Fernando.
“So much innovation is happening. Traditional health care firms and new entrants alike are bringing new approaches to AI and ML that may lead us to a breakthrough that allows for true interpretive models and explainability. I am hopeful because we have seen so much investment, both public and private, that some breakthroughs may be happening today already in a class or a lab at Stanford or MIT that will change the way we think about CDS.”
“Innovation is happening, bringing together even more disparate and unique data sets, including clinical claims data, and transforming the art of the possible,” added Mehrotra.
At HIMSS20, his and Fernando’s session – which is targeted at CEOs, COOs, Chief Quality Officers, Chief Clinical Transformation Officers and other healthcare leaders – will offer some practical and actionable advice for health systems hoping to pave the way toward these advancements.
“Every provider executive I talk with is hungry for real-world experience with AI,” said Fernando. “Once you have a real-world problem framed, whether it’s better operating with customers or using AI internally, you can tackle the strategic questions of how does the model perform, how do we put it into a business setting that makes sense, and then consider how the models re-learn with new data.”
“At HIMSS20, we’re looking forward to a new conversation about how to drive practical value from an AI program or initiative,” said Mehrotra. “We will explain how to think about exploring a pilot for value and how to think about getting the skill set and data and everything else you need to create value from AI at scale.”
Source: Healthcare IT News