Personalized Text Messaging for Type 2 Diabetes

(REINFORCE2 Trial)

Overseen By Julie Lauffenburger, PharmD, PhD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Brigham and Women's Hospital

Must be taking: Oral diabetes medications

Disqualifiers: Pillbox use, Daily medication help

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

Duration: 6 months

60 Participants Needed

Trial Summary

Do I need to stop my current medications for this trial?

The trial does not specify that you need to stop taking your current medications. It focuses on supporting medication adherence for those already prescribed 1-3 daily oral medications for type 2 diabetes.

What data supports the effectiveness of the treatment Reinforcement Learning for Personalized Text Messaging in Type 2 Diabetes?

Research shows that reinforcement learning, a type of machine learning, can help tailor text messages to improve medication adherence in diabetes patients by learning individual response patterns. Additionally, similar methods have been effective in optimizing insulin regimens and controlling blood glucose levels in diabetes, suggesting potential benefits for personalized text messaging interventions. ^{1 2 3 4 5}

Is personalized text messaging for type 2 diabetes safe for humans?

In a small trial with 16 patients using a similar approach called reinforcement learning for insulin management in type 2 diabetes, no severe episodes of low blood sugar (hypoglycemia) or high blood sugar with ketosis were reported, suggesting it is generally safe. ^{2 3 4 6 7}

How does the personalized text messaging treatment for type 2 diabetes differ from other treatments?

This treatment uses reinforcement learning, a type of machine learning, to tailor text messages based on individual responses, making it more personalized compared to generic messaging approaches. This method aims to improve medication adherence by optimizing communication to each patient's unique patterns. ^{1 3 5 8 9}

What is the purpose of this trial?

Reinforcement learning is an advanced analytic method that discovers each individual's pattern of responsiveness by observing their actions and then implements a personalized strategy to optimize individuals' behaviors using trial and error. The goal of the proposed research is to refine, adapt and perform efficacy testing of a novel reinforcement learning-based text messaging intervention to support medication adherence for patients with type 2 diabetes within a community health center setting. This study will be a parallel randomized pragmatic trial comparing medication adherence and clinical outcomes for adults in a community setting aged 18-84 with type 2 diabetes who are prescribed 1-3 daily oral medications for this disease. Participants will be randomized to one of two arms for the duration of the study period: (1) a reinforcement learning intervention arm with up to daily, tailored text messages based on time-varying treatment-response patterns; or (2) a control arm with up to daily, un-tailored text messages. Outcomes of interest will be medication adherence, as measured by electronic pill bottles, and HbA1c levels over 6 months.

Eligibility Criteria

This trial is for adults aged 18-84 with type 2 diabetes who have a recent HbA1c level of at least 7.5%, use a smartphone, understand English or Spanish, take 1-3 daily oral diabetes meds, and have been less than ideally consistent with their medication (PDC <0.80). It's not for those getting daily help with meds or unwilling to switch to electronic pill bottles.

Inclusion Criteria

Must have a basic working knowledge of English or Spanish

I have been diagnosed with Type 2 Diabetes.

I take 1 to 3 pills daily for my diabetes.

Exclusion Criteria

Receive help at home on a daily basis with taking medications

Currently using a pillbox and/or not willing to use electronic pill bottles for 6 months

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants receive up to daily text messages, tailored or untailored, to support medication adherence

6 months

Follow-up

Participants are monitored for medication adherence and glycemic control after the intervention

6 months

Treatment Details

Interventions

• Reinforcement Learning

Trial Overview The study tests if personalized text messages based on reinforcement learning can improve medication adherence in type 2 diabetes patients compared to standard texts. Participants will be randomly assigned to receive either tailored messages that adapt over time or generic ones, both potentially up to daily.

Participant Groups

Group I: Reinforcement Learning Intervention Arm Experimental Treatment 1 Intervention

Up to daily, tailored text messages.

Group II: Control Arm Active Control 1 Intervention

Up to daily, untailored text messages.

Who Is Running the Clinical Trial?

Brigham and Women's Hospital

Lead Sponsor

Trials

1,694

Recruited

14,790,000+

National Institute on Aging (NIA)

Collaborator

Trials

1,841

Recruited

28,150,000+

Boston Medical Center

Collaborator

Trials

410

Recruited

890,000+

References

1. England pubmed.ncbi.nlm.nih.gov

REinforcement learning to improve non-adherence for diabetes treatments by Optimising Response and Customising Engagement (REINFORCE): study protocol of a pragmatic randomised trial. [2022]

2. United States pubmed.ncbi.nlm.nih.gov

Estimating Dynamic Treatment Regimes in Mobile Health Using V-learning. [2022]

3. United States pubmed.ncbi.nlm.nih.gov

Optimized glycemic control of type 2 diabetes with reinforcement learning: a proof-of-concept trial. [2023]

4. Netherlands pubmed.ncbi.nlm.nih.gov

Near-optimal insulin treatment for diabetes patients: A machine learning approach. [2021]

5. United States pubmed.ncbi.nlm.nih.gov

An Adaptive, Algorithm-based Text Message Intervention to Promote Health Behavior Adherence in Type 2 Diabetes: Treatment Development and Proof-of-Concept Trial. [2023]

6. United States pubmed.ncbi.nlm.nih.gov

Clinical evaluation of decision support system for insulin-dose adjustment in IDDM. [2019]

7. United States pubmed.ncbi.nlm.nih.gov

Development and Validation of Binary Classifiers to Predict Nocturnal Hypoglycemia in Adults With Type 1 Diabetes. [2023]

8. Netherlands pubmed.ncbi.nlm.nih.gov

Model driven mobile care for patients with type 1 diabetes. [2017]

9. United States pubmed.ncbi.nlm.nih.gov

[mSalUV: a new mobile messaging system for diabetes control in Mexico]. [2019]