Quantifying the Benefits of AI-Powered Patient Adherence Programs

In this Pharmaceutical Executive video interview, Bill Grambley, CEO of AllazoHealth, delves into the potential of AI to revolutionize patient engagement and adherence. By utilizing patient-level data and predictive modeling, AI can identify individual needs and preferences, tailoring interventions to optimize treatment outcomes. This personalized approach addresses the common challenges of medication non-adherence and improves patient outcomes. The discussion highlights the importance of ethical considerations and data privacy when leveraging AI in healthcare. By focusing on patient well-being and using AI responsibly, healthcare providers can significantly enhance patient experiences and improve overall health outcomes.

What metrics and KPIs can be used to measure the effectiveness of AI-powered patient engagement and adherence programs? How can companies demonstrate the value of these interventions to payers and healthcare providers?

So, to us that the metrics that matter most are around first fills and then refills. And when we think about that patient medication journey, those are kind of the critical points that we that we focus on, and we look at all those touch points across the journey and how it's impacting those two outcomes. Now, the only downside to that is that those metrics can take time to measure. You know, adherence, by definition, is a period of time that you're on a medicine, and so that can take a while. So, we often look at interim KPIs that could. Include something like email, open rate, click through, rate, unsubscribe rate, how likely or how often do people answer the phone attempts? So, there's a lot of these interim measures.

Now, while those can be good directional views of how things are going, they can be misleading, and this is where, as you think about how to use AI, it becomes a different question, because if you're using this appropriately, there will be some patients who need more support than other patients. And if you need more support, and you do, let's say, more outreach, you can influence some of those KPIs potentially in a negative way. Similarly, if you have a patient who, like my parents, will always do what their doctor says, maybe you actually don't want to reach out to them, because you'll annoy them. They'll actually opt out, or they'll have a negative experience compared to somebody else, those things can affect those interim KPIs. And so, when we think about our technology, it's always predicting. How does the action I take today impact that that future outcome I desire either starting the therapy or staying on therapy.

When you think about value, though, and you take a program that has treated people kind of like widgets you you've treated them as you are on this therapy, and I have a whole series of things I'm doing to support you, but it's an it's a very consistent across all your patients program, and then we use AI to now do this personalization, and we've done this across a number of different organizations, a number of different types of programs, digital heavy programs, phone call heavy programs, we continue to see a dramatic increase the effectiveness of those programs, Increasing initiation rates by 10% 10.4% in another program, we saw a 16% increase in the initiation rate. When you think of adherence. We've got programs that that decrease therapy discontinuation, which is one measure of adherence, by over 7% we have another one that we increase the days on therapy. So again, another way to measure adherence, by almost 19% and if you think about what that means to patients, that means more patients are starting the therapy that their doctor ordered, and they're staying on the therapy longer to therefore get the best clinical benefit from that medication.

So, we think this should become the standard, using these kinds of tools to actually improve these programs and really personalize the engagements. And I'll just kind of end that question with if you think about going back to Netflix, if every single one of us had the same Netflix queue, we would get bored very quickly, because it doesn't respond to us. And yet, many of these programs treat everybody the same. And so, if we can actually make that program more relevant to us as individuals, more patients will get the benefit of those programs, and more patients therefore will start and stay on therapy.