How Can Predictive Analytics Help ACOs Boost Value-Based Care Delivery?

September 25, 2023 - Accountable care organizations (ACOs) play a critical role in shifting the healthcare system toward value-based care, but population health management and care coordination initiatives require ACOs to invest in new technologies to achieve success.

Predictive analytics is one of these technologies, allowing providers to better leverage their patient data for risk stratification.

On Xtelligent Healthcare Media’s Healthcare Strategies podcast, Sheila Magoon, MD, executive director of Buena Vida y Salud ACO and the South Texas Physician Alliance, and David Clain, chief product officer at the Health Data Analytics Institute (HDAI), detailed how their predictive analytics partnership is helping the ACO boost its value-based care delivery.

USING PREDICTIVE ANALYTICS TO KEEP PATIENTS “HEALTHY AT HOME”

When Buena Vida y Salud and HDAI launched their partnership in April, Magoon knew that the collaboration would help the ACO see its patient population from a different perspective and help meet the goal of “keeping patients healthy at home.”

Upon initially exploring HDAI’s predictive analytics platform, Magoon and her colleagues were presented with multiple options for data analysis, including assessing the risk of unplanned admissions, pneumonia development, and worsening heart failure.

HDAI helped Buena Vida y Salud pull reports for these populations, which the ACO used to develop cohorts of patients in the organization’s advanced care group, chronic care group, and rising risk group. From these cohorts, providers received lists to help guide their care management efforts.

However, this presented a challenge for Magoon.

“I had one [doctor] say, ‘This information is really great, you've done a lot of hard work. But you know what? There's only one thing I think I do out of all of this,’ because he expressed he was feeling overwhelmed,” she explained.

“So, then we negotiated it down to, ‘Okay, let's just look at those patients that are high risk of unplanned admissions, and if we could just look at that patient list and be able to see those patients,’” Magoon continued.

This approach was more successful, as the provider already had a workflow to make that unplanned admission data actionable. The ACO decided to leverage this approach with its other providers as well, allowing them to choose the patient cohorts or use cases that HDAI’s platform could help them better focus on.

Magoon emphasized that this helps engage providers instead of relying solely on internal care coordinators to guide the ACO’s value-based care work.

“Even though [providers] might be excited, they're really not sure where to start,” she said.

One of the ACO’s ongoing campaigns is focused on getting vaccinations for its patients at high risk of pneumonia as flu season approaches.

Magoon noted that pneumonia is in the ACO’s top ten drivers of hospital admissions, making preventing those admissions a top priority. Using HDAI’s platform, Buena Vida y Salud is working to encourage high-risk patients to get their pneumococcal vaccines.

While this may not eliminate pneumonia-related hospitalizations, it’s key to achieving the ACO’s goal.

“That's the whole thing,” Magoon stated. “How can we keep patients healthy at home? Let's look at [HDAI’s insights] with that end goal in mind.”

DATA QUALITY AND DIGITAL TWINS

To help ACOs reach their value-based care goals, HDAI utilizes a combination of predictive modeling and digital twins.

“When we think about digital twins and how we do these analyses, we're thinking about the kinds of conversations that Dr. Magoon is having, where she's going to individual physicians and saying, ‘Let's look at specific patients who might require some support or some specific intervention, but also broadly speaking, how are you doing managing this population?’” Clain explained.

In response to the introduction of tools like HDAI’s, many providers may hesitate, noting that they have a unique patient population and raising concerns that such tools may not be able to capture that nuance.

Gaining provider trust is not easy. Overcoming their hesitancy is even more difficult if predictive analytics vendors cannot display data to back up their claims. Addressing providers’ concerns is crucial, Clain noted.

“Having the ability to walk into the room saying, ‘Actually, we have thought about that. We've looked at the extent to which your patients are different. And we still see that there's an opportunity,’ or, conversely, ‘You've got a challenging population, and the numbers look bad in absolute terms. But given the population, you're doing really well.’ It's important to be able to do that, and digital twinning is how we do that,” he said.

In the past, ACOs have relied on Medicare data and risk adjustment factor (RAF) scores to gain insights into their patient populations, but these are limited in that they cannot capture all the complexities associated with a patient and her health.

Digital twins—digital or virtual representations of people, objects, processes, or systems designed to help simulate a potential outcome—represent a “third wave” of analysis, Clain posited, tying de-identified data from these and other sources to an ACO population. By benchmarking against precisely-matched comparison populations, HDAI can help ACOs measure their populations’ outcomes across various metrics relative to a very similar group of patients. This tactic can help identify areas for improvement.

“If we can go in and say [to providers], ‘You do have a very challenging population with a very high diabetes disease burden. We expect that you're going to have more diabetes-related hospitalizations than the average provider, but let's see how you're doing relative to that population,’ I think that makes for a lot more productive conversations when you can start with that baseline,” Clain said.

EARLY SUCCESSES AND LOOKING AHEAD

Buena Vida y Salud’s partnership with HDAI is still in its early stages, but the ACO has seen some nascent successes and is making plans for future initiatives.

Currently, the ACO’s admission rates are stable, which Magoon explained is positive because the end of the public health emergency led to an uptick in hospital admissions and emergency room (ER) utilization across the United States.

Despite these successes, Magoon noted that it may take a year of working with HDAI before the true impact of the partnership and the associated patient outcome trends are apparent.

In the meantime, the ACO’s next project involves improving care for patients with stage 3 chronic kidney disease (CKD3).

“We also recognize from looking at the data that our patients who have CKD3, whether it's A or B, are at a little higher risk of having ER visits and those kinds of things,” Magoon explained. “We've identified a nephrologist who's willing to work on it, so that's our next new project. What we're going to do is start looking at this [cohort] and then breaking it down into bite-sized pieces where we think we can actually have an impact.”

She expressed that she and her colleagues are excited because there are so many opportunities provided to the ACO by leveraging advanced analytics and so many potential applications that could significantly improve Buena Vida y Salud’s value-based care delivery.

“We're really hopeful to see here over the next year where this is going to take us,” Magoon said.