Personalized AI-Powered Solutions for Better Patient Adherence

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.

How can AI be used to identify patients at risk of medication non-adherence and intervene early to prevent negative outcomes? What data sources and predictive modeling techniques can be employed to develop effective early intervention strategies?

At the most foundational level, we want to use this identified patient data. When we do so, we can actually then make these predictions about nonadherence. If you think about us as people, if you think about who we are and how we engage in healthcare, you know, there are people who will be completely on top of what their doctor says. You know, my parents actually fall into this category. The doctor says, ‘Take this medicine.’ They take that medicine. On the other hand, there are people who maybe they have transportation challenges. It could be financial, maybe they actually have issues that they don't believe the doctor. There's all sorts of information out there that can impact somebody's likelihood to start therapy.

So, we start with using identified patient data, then we use these predictive models that we've built to now understand what is the risk of somebody not starting therapy or not staying on therapy. Again, we can use that now to create actually an optimal engagement plan for each patient, adjusting over time based on their actual behaviors. So, think of things like, what is the optimal content to use? Do you email? Do you text? Do you make phone calls? Does somebody need an intensive level of support over the first couple of weeks? Peaks, or is somebody actually they need more constant reminders over time? Do they know what actions to take? You know, our healthcare system now is pretty complex. There's therapies that we support that require vaccinations to be done, obviously prior authorizations or step therapies. These all come out as things that kind of confuse patients and need often help to get through when you think about data and sources of data, fundamentally, it starts with a patient opting into a program, but then when, once that happens, you can now have access to a larger set of data than just on that opt in. You can look at demographic information. You can look at social determinants of health information. You look at their prior engagement data. You can also look at things like consumer behavior data and the fill data that is available on these patients when we start thinking about those patients, and again, using these wider variety of sources of data, we now have a much more holistic view of who that patient is and what's going on in their lives. You had mentioned pharmacy deserts, that's a very real issue. If you have to schedule time to go pick up your medicine, that is going to be a barrier for certain people.

So, when we think of all this data, we actually have a data set now that maps all of these characteristics. We've got over 500 predictors about a person with what engagements occur and what behavior results from those engagements, and that's the foundation for us to use this AI to make these predictions, you can really actually move beyond kind of looking at a patient as a widget, almost even beyond looking at them as a persona defined, usually by demographic characteristics. And now you can actually bring that down to a persona of one. You look at the patient as an individual across all of these different touch points across all the different parts of your program to then deliver to them what is going to help that person stay on their medication journey, get the therapy or stay on the therapy over a long period of time.