How Artificial Intelligence, Machine Learning Impact Care Coordination
Insurers can use artificial intelligence and machine learning tools to give their provider partners an edge on care coordination and quality of care.
Source: Getty Images
- When doctors have 2,000 to 3,000 patients on their patient panels, prioritization in care coordination efforts can be challenging. To Stephen Friedhoff, MD, senior vice president of health care services at Blue Cross and Blue Shield of North Carolina (Blue Cross NC), this creates the perfect environment for artificial intelligence (AI) and machine learning (ML) solutions.
Listen to the full podcast to hear more details. And don’t forget to subscribe on iTunes, Spotify, or Google Podcasts.
These tools excel at helping providers and payers allocate resources to streamline care coordination.
“If you're a physician and you have limited resources in your office to do outreach to patients, or if you're a health plan and you have limited resources to do outreach to the insured who are at risk, how do you decide where to deploy those resources? How do you decide where you can be the most proactive and have the greatest impact?” Freidhoff said on Healthcare Strategies.
“It turns out that most clinicians are really, really good when the patient is sitting right in front of them, but we're less good from a population health perspective on figuring out where best to deploy those resources. And that's where artificial intelligence and machine learning can really help us do more with less, or at least with existing resources.”
Health plans accrue copious amounts of healthcare data. Rather than sort through this wealth of information manually, AI and ML tools can compile an amalgamation of the relevant materials.
Using artificial intelligence and machine learning tools for the purposes of streamlining care coordination aligned well with Blue Cross NC’s value-based care approach, Friedhoff indicated. Both the payer’s value-based care model, Blue Premier, and its AI and ML strategies center on improving care coordination and clinical quality.
“As we get better at developing the artificial intelligence and machine learning models, start getting that to be something that we can actually put in the hands of providers to work more effectively with their own patient populations, the potential for that is just extraordinary. But I think taking that kind of a tool and delivering it to right at the point of care, that's really the next step in the evolution from my perspective,” Friedhoff said.
