Three ways to improve patient retention in recovery programs

Deaths from drug overdoses have increased from ~1 per 100,000 in 1999 to ~4 per 100,000 in 2020.1 The introduction of fentanyl has only exacerbated and accelerated this crisis, driving a 282% overdose death increase between 2016 and 2021.2 Despite expansion of evidence-based treatments (e.g., buprenorphine), only about half of patients stay in treatment, limiting their chance at recovery.3,4

Healthcare organizations need better avenues for identifying why patients are dropping out and implementing meaningful retention strategies.

Using thousands of real-world data points, advanced artificial intelligence (AI), and machine learning capabilities, we identified three key trends and corresponding strategies for improving patient health and recovery.

(Note: Large-scale, real-world data is most effective, as it offers insights and recommendations that payers and providers can apply in a day-to-day setting—not just in a highly controlled clinical trial.)

  • Patients are more likely to stay in care if they (a) see the same provider, (b) attend more in-person visits, and (c) have health insurance.
  • Patients are more likely to use fentanyl if they (a) use multiple substances, (b) are younger than 40, (c) cancel their appointments within 24 hours, and (d) fail to take their medication.
  • Patients who adhere to Sublocade treatment protocols are more likely to stay in treatment and less likely to use substances relative to patients who fail to adhere to treatment protocol.

Three strategies to improve patient health and recovery

1: Work to enhance the patient-provider relationship

A strong, trusting relationship between a patient and their clinician is important for long-term adherence and wellbeing. Whenever possible, assign patients to the same clinician(s) for each visit to foster continuity and build rapport. Proactively scheduling regular in-person visits can help maintain patient engagement and monitor progress. Make sure you have a robust reminder system set up to keep patients accountable for their appointments and treatments.

2: Target efforts to enhance prevention and early intervention

Catching patients early for prevention and intervention is ideal. Clinicians who have a strong working relationship with patients are most equipped to extract and flag risky behaviors—including past substance use, appointment cancellations, and medication non-compliance. With a robust protocol in place for quick response and support, providers can identify patients who might benefit from prevention efforts, including health education, as well as early intervention.

3: Innovate to improve program adherence

As technology advances, your communication approaches to at-risk patients can also improve to fit current trends and needs. For example, consider using digital tools such as mobile apps or SMS reminders to encourage medication compliance and consistent appointment attendance. You can also use digital platforms (e.g., websites, portals) to deliver important education to patients about substance misuse and abuse, as well as the benefits they could achieve by following treatment protocols.

Start comprehensively addressing substance misuse and abuse

To do this well, organizations need to bring all their data together in one place with maximum interoperability. Using powerful augmented analytics to surface actionable insights, organizations are equipped to enable proactive care interventions, efficient risk stratification, and streamlined care coordination to name a few. Optimize resource allocation and add focus where it’s needed most to enable better patient outcomes and achieve population health management goals.

Want to learn more about our data science pursuits supporting healthcare? Let’s talk!

  1. 2022 National Healthcare Quality and Disparities Report [Internet]. Rockville (MD): Agency for Healthcare Research and Quality (US); 2022 Oct. SUBSTANCE USE DISORDERS. Available from: https://www.ncbi.nlm.nih.gov/books/NBK587176/
  2. Jeffery, M. M., Stevens, M., D’Onofrio, G., & Melnick, E. R. (2023). Fentanyl-Associated Overdose Deaths Outside the Hospital. New England Journal of Medicine.
  3. Chan, B., Gean, E., Arkhipova-Jenkins, I., Gilbert, J., Hilgart, J., Fiordalisi, C., … & Guise, J. M. (2021). Retention strategies for medications for opioid use disorder in adults: a rapid evidence review. Journal of addiction medicine, 15(1), 74.
  4. Kennedy, A. J., Wessel, C. B., Levine, R., Downer, K., Raymond, M., Osakue, D., … & Liebschutz, J. M. (2022). Factors associated with long-term retention in buprenorphine-based addiction treatment programs: A systematic review. Journal of general internal medicine, 1-9.

Matthew Hanauer, Ph.D.

Dr. Matthew Hanauer has over 10 years of experience in statistics and data science. He worked for several large healthcare companies, helping to lead and transform their data science programs using ML, AI, NLP, and integrating GenAI. He has published in top-tier journals and traveled the country, presenting at conferences on the interaction of healthcare and data science. Dr. Hanauer has a PhD in Research Methods and an MPA in Public Affairs both from Indiana University – Bloomington.

Get our take on industry trends

Why managed Medicaid/Medicare health plans need analytics to improve outcomes

Why managed Medicaid/Medicare health plans need analytics to improve outcomes

September 21, 2021

Managed care organizations that provide healthcare services to Medicare/Medicaid members are dedicated to improving the health and wellness of these underserved populations, especially those living in rural areas.   

Read on...

Using consumer analytics to steer health-related decisions

September 7, 2021

Companies tap into what people like to eat and drink, how we purchase consumables, where we like to shop, what shows we might like to stream, whether we vote, and so on. If you have ever created a profile on a streaming application (think Netflix or Amazon), you will receive recommended books, movies and other items just as soon as you start surfing.

Read on...
Data Science into your Organization

Run: Bringing Data Science into your Organization

August 30, 2021

In this three-part series, we’ve been detailing a tiered approach to introducing and incorporating data science into your organization. In Part One: Crawl and Part Two: Walk, we discussed how to get started from scratch and start building out a dedicated data science program. Today, we’ll dive into the third and final phase to see how to grow quality, centralize governance, incorporate user feedback, and more.

Read on...
Data Science into your Organization part 2

Walk: Bringing Data Science into your Organization

August 23, 2021

In this three-part series, we’re exploring a tiered approach to introducing and incorporating data science into your organization. In Part One: Crawl, we discussed how to get started from scratch. Today in Part Two: Walk, we’ll address issues that may emerge and how to overcome them, how to build out a dedicated data science team, and more.

Read on...