While clinician burnout is well known, “patient burnout” within the chronic disease population is an equally critical but silent issue. Managing chronic conditions, especially diabetes, is complex and overwhelming. Nonadherence affects 12% of the U.S. population with Type 2 diabetes; 42% of patients with chronic conditions manage at least two or more.
Dr. Tejaswi Kompala, head of cardiometabolic clinical strategy at Teladoc Health, says artificial intelligence is rethinking healthcare’s approach to chronic conditions like diabetes. She believes artificial intelligence can help by:
Personalizing interventions to improve patient engagement and reduce A1c levels in diabetes management.
Predicting and identifying patients at risk of uncontrolled outcomes a year in advance.
Working synergistically with healthcare providers and coaches to enhance patient experiences.
We interviewed Kompala to get her insights on these topics and examples from her own practice as an endocrinologist of how AI helps treat patients holistically, focusing on the main pillars of cardiometabolic health for sustainable outcomes – nutrition, activity, sleep and stress.
Q. Please describe what you call patient burnout within the chronic disease population. And how it is, as you say, a “silent issue.”
A. Clinician burnout is a serious and well-documented issue, but patient burnout is often overlooked. Though it’s rarely spoken about, patient burnout has serious health consequences – and from my own practice, I can see it’s on the rise.
One contributing factor is the growing prevalence of chronic disease. About 42% of Americans are living with at least two chronic conditions, which only adds to the complexities each patient is already dealing with as they navigate their care journey.
Managing these conditions is an ongoing challenge, requiring significant commitment, engagement, resources and time to adhere to their medication and treatment plan fully. Juggling the demands of managing a chronic condition is stressful, and it often impacts one’s mental health. In fact, patients with diabetes are two to three times more likely to struggle with mental health than those without.
These conditions can make it even harder to successfully stick to a treatment plan. Nonadherence – when patients don’t take their medications or follow guidelines as prescribed – is a major issue and can stem from life’s daily stressors, exacerbated by complex dosing or treatment schedules.
It’s a lot to keep track of: remembering to take medications, making lifestyle and behavior changes, and staying on top of medical appointments. And remember, patients are often managing these conditions over the course of a lifetime, which can also contribute to feelings of being overwhelmed and burnout.
In my practice, we’re seeing chronic conditions on the rise in younger populations, which can magnify these challenges. We’re asking patients to be engaged in their health for decades – not just for a few weeks or months.
Q. In general terms, how can artificial intelligence step in here and help with patient burnout?
A. Managing chronic conditions is a burden, and it’s normal for patients to have periods of low motivation and burnout. Artificial intelligence can play a powerful role keeping people engaged through those ebbs and flows.
In the last couple years, we’ve started leveraging new applications of AI to proactively identify patients at risk of uncontrolled diabetes. Our predictive models use data such as blood glucose levels, medication fills, food logging and other health signals to identify those at risk and drive increased engagement in the program. Engagement is a key factor in boosting health outcomes and can help address patient burnout.
In addition, AI models like this help identify patterns in patient behavior that indicate potential signs of burnout or nonadherence when patients have missed multiple doses or skipped logging their activities.
These insights help patients stay on track and avoid falling through the cracks in the healthcare system. Ultimately, it helps clinicians allocate their resources and time more effectively to provide additional support to and where patients need it the most.
Q. How can AI predict and identify patients at risk of uncontrolled outcomes a year in advance?
A. Predictive modeling has the potential to transform diabetes care by proactively identifying a patient or population at risk of uncontrolled outcomes up to a year in advance. This is particularly important because uncontrolled diabetes over the long term can lead to severe and devastating complications, such as nerve damage.
With predictive modeling, we’re able to analyze more than 100 ongoing personal health data points to identify those at risk and zero-in on attributes that may impact their at-risk status, based on their personalized health journey.
The data is analyzed regularly, taking into account a range of inputs, from frequency of glucose readings to medication dosing and even a person’s engagement with educational material in the app. Historically, medicine has taken a reactive approach – responding after a complication. But new applications of technology give us the opportunity to potentially respond and intervene before a complication.
Once you identify who’s at risk, clinicians can respond to help patients get back on track. Shifting from a reactive to proactive approach allows for more effective, tailored care. These tools allow for more timely, personalized interventions to avoid complications, improve outcomes, and better control costs for employers and health plans.
Q. How can AI work synergistically with healthcare providers and coaches to enhance patient experiences?
A. I like to think of it as collaborative intelligence versus “artificial” intelligence. As clinicians, these tools help us harness data and insights in ways that make us smarter, more effective and more efficient. By using data in, on and around each person, AI can help enable more personalized care.
Emerging technologies will continue to play a bigger role in the future when it comes to surfacing relevant insights from data, but it’s ultimately up to the humans – coaches and clinicians – to leverage the trusted relationships they’ve built with patients to help put those insights into action, and drive better outcomes.
Throughout the care journey, these insights identify what engagement methods are effective for certain populations and where additional interventions are needed to target and engage patients.
Targeted interventions with access to healthcare providers or human coaches can make the difference in driving sustainable behavior changes like helping patients adhere to medications, exercise regularly and eat healthy. Ultimately, these tools actually help us be more human and provide more compassionate and empathetic care.
Q. Please provide some insights and examples from your own practice as an endocrinologist into how AI helps treat patients holistically.
A. Where I’m seeing the most potential from AI in my own practice is delivering insights that allow myself and colleagues to provide much more personalized care that supports individual behavior change day in, day out.
For example, I spend a lot of time working with patients on implementing behavior change, but often I’ll only have a handful of touchpoints with them throughout the year. Digital tools help implement our care plans and can help us intervene at the right time if a patient is going off track.
Managing diabetes is a marathon, not a sprint. It requires a lot of lifestyle and behavior changes that must be sustainable over time in order to achieve better outcomes. AI plays a role in connecting and engaging with my patients beyond our regular appointments to ensure they’re adhering to medications, exercising regularly and eating healthy to achieve A1c reduction, weight loss and mental health improvements.
Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email him: [email protected]
Healthcare IT News is a HIMSS Media publication.
Source : Healthcare IT News
—-
Author : News7
Publish date : 2024-09-17 15:59:00
Copyright for syndicated content belongs to the linked Source.