Trial Outcomes & Findings for Reinforcement Learning in Diabetes Mellitus Trial (NCT NCT04473326)
NCT ID: NCT04473326
Last Updated: 2023-02-08
Results Overview
Medication adherence to type 2 diabetes oral medications (averaged) as measured by the number of dates and times of pillbottle openings in the electronic pill bottles
Recruitment status
COMPLETED
Study phase
NA
Target enrollment
60 participants
Primary outcome timeframe
6 months
Results posted on
2023-02-08
Participant Flow
Participant milestones
| Measure |
Reinforcement Learning Intervention Arm
Up to daily, tailored text messages.
Reinforcement Learning: Participants in the intervention arm will receive up to daily, tailored text messages based on their electronic pill bottle-measured adherence. Given the participants' baseline characteristics and time-varying responses to the messages, a reinforcement learning algorithm will deliver different text messages and adapt over time to determine which type of messaging works best for each individual participant.
|
Control Arm
Up to daily, untailored text messages.
|
|---|---|---|
|
Overall Study
STARTED
|
29
|
31
|
|
Overall Study
COMPLETED
|
28
|
28
|
|
Overall Study
NOT COMPLETED
|
1
|
3
|
Reasons for withdrawal
| Measure |
Reinforcement Learning Intervention Arm
Up to daily, tailored text messages.
Reinforcement Learning: Participants in the intervention arm will receive up to daily, tailored text messages based on their electronic pill bottle-measured adherence. Given the participants' baseline characteristics and time-varying responses to the messages, a reinforcement learning algorithm will deliver different text messages and adapt over time to determine which type of messaging works best for each individual participant.
|
Control Arm
Up to daily, untailored text messages.
|
|---|---|---|
|
Overall Study
Death
|
0
|
1
|
|
Overall Study
Withdrawal by Subject
|
1
|
2
|
Baseline Characteristics
Reinforcement Learning in Diabetes Mellitus Trial
Baseline characteristics by cohort
| Measure |
Reinforcement Learning Intervention Arm
n=29 Participants
Up to daily, tailored text messages.
Reinforcement Learning: Participants in the intervention arm will receive up to daily, tailored text messages based on their electronic pill bottle-measured adherence. Given the participants' baseline characteristics and time-varying responses to the messages, a reinforcement learning algorithm will deliver different text messages and adapt over time to determine which type of messaging works best for each individual participant.
|
Control Arm
n=31 Participants
Up to daily, untailored text messages.
|
Total
n=60 Participants
Total of all reporting groups
|
|---|---|---|---|
|
Age, Continuous
|
60.31 years
STANDARD_DEVIATION 11.35 • n=99 Participants
|
56.68 years
STANDARD_DEVIATION 12.89 • n=107 Participants
|
58.43 years
STANDARD_DEVIATION 12.20 • n=206 Participants
|
|
Sex: Female, Male
Female
|
12 Participants
n=99 Participants
|
14 Participants
n=107 Participants
|
26 Participants
n=206 Participants
|
|
Sex: Female, Male
Male
|
17 Participants
n=99 Participants
|
17 Participants
n=107 Participants
|
34 Participants
n=206 Participants
|
|
Race (NIH/OMB)
American Indian or Alaska Native
|
0 Participants
n=99 Participants
|
0 Participants
n=107 Participants
|
0 Participants
n=206 Participants
|
|
Race (NIH/OMB)
Asian
|
2 Participants
n=99 Participants
|
1 Participants
n=107 Participants
|
3 Participants
n=206 Participants
|
|
Race (NIH/OMB)
Native Hawaiian or Other Pacific Islander
|
0 Participants
n=99 Participants
|
0 Participants
n=107 Participants
|
0 Participants
n=206 Participants
|
|
Race (NIH/OMB)
Black or African American
|
6 Participants
n=99 Participants
|
7 Participants
n=107 Participants
|
13 Participants
n=206 Participants
|
|
Race (NIH/OMB)
White
|
17 Participants
n=99 Participants
|
17 Participants
n=107 Participants
|
34 Participants
n=206 Participants
|
|
Race (NIH/OMB)
More than one race
|
1 Participants
n=99 Participants
|
2 Participants
n=107 Participants
|
3 Participants
n=206 Participants
|
|
Race (NIH/OMB)
Unknown or Not Reported
|
3 Participants
n=99 Participants
|
4 Participants
n=107 Participants
|
7 Participants
n=206 Participants
|
|
Region of Enrollment
United States
|
29 participants
n=99 Participants
|
31 participants
n=107 Participants
|
60 participants
n=206 Participants
|
|
Self-reported automaticity of medication-taking, n(%)
0-1 (no or low automaticity)
|
7 Participants
n=99 Participants
|
12 Participants
n=107 Participants
|
19 Participants
n=206 Participants
|
|
Self-reported automaticity of medication-taking, n(%)
2+ (high automaticity)
|
22 Participants
n=99 Participants
|
19 Participants
n=107 Participants
|
41 Participants
n=206 Participants
|
|
Baseline HbA1c, mean (sd)
|
8.99 percentage of glycated hemoglobin
STANDARD_DEVIATION 1.39 • n=99 Participants
|
9.10 percentage of glycated hemoglobin
STANDARD_DEVIATION 1.47 • n=107 Participants
|
9.05 percentage of glycated hemoglobin
STANDARD_DEVIATION 1.42 • n=206 Participants
|
|
Education level, n(%)
High school graduate or below
|
7 Participants
n=99 Participants
|
5 Participants
n=107 Participants
|
12 Participants
n=206 Participants
|
|
Education level, n(%)
Some college/college graduate
|
15 Participants
n=99 Participants
|
19 Participants
n=107 Participants
|
34 Participants
n=206 Participants
|
|
Education level, n(%)
Post-graduate
|
7 Participants
n=99 Participants
|
7 Participants
n=107 Participants
|
14 Participants
n=206 Participants
|
|
Number of self-reported physicians, n(%)
1-3
|
10 Participants
n=99 Participants
|
15 Participants
n=107 Participants
|
25 Participants
n=206 Participants
|
|
Number of self-reported physicians, n(%)
4+
|
19 Participants
n=99 Participants
|
16 Participants
n=107 Participants
|
35 Participants
n=206 Participants
|
|
Number of self-reported medications, n(%)
1
|
2 Participants
n=99 Participants
|
2 Participants
n=107 Participants
|
4 Participants
n=206 Participants
|
|
Number of self-reported medications, n(%)
2-4
|
6 Participants
n=99 Participants
|
4 Participants
n=107 Participants
|
10 Participants
n=206 Participants
|
|
Number of self-reported medications, n(%)
5+
|
21 Participants
n=99 Participants
|
25 Participants
n=107 Participants
|
46 Participants
n=206 Participants
|
|
Number of Pillsy bottles, n(%)
1
|
20 Participants
n=99 Participants
|
25 Participants
n=107 Participants
|
45 Participants
n=206 Participants
|
|
Number of Pillsy bottles, n(%)
2+
|
9 Participants
n=99 Participants
|
6 Participants
n=107 Participants
|
15 Participants
n=206 Participants
|
|
Level of non-adherence, self-reported number of doses missed in past month, n(%)
0
|
12 Participants
n=99 Participants
|
14 Participants
n=107 Participants
|
26 Participants
n=206 Participants
|
|
Level of non-adherence, self-reported number of doses missed in past month, n(%)
1+
|
17 Participants
n=99 Participants
|
17 Participants
n=107 Participants
|
34 Participants
n=206 Participants
|
PRIMARY outcome
Timeframe: 6 monthsPopulation: Participants were included in the analysis until they no longer participated in the study.
Medication adherence to type 2 diabetes oral medications (averaged) as measured by the number of dates and times of pillbottle openings in the electronic pill bottles
Outcome measures
| Measure |
Reinforcement Learning Intervention Arm
n=29 Participants
Up to daily, tailored text messages.
Reinforcement Learning: Participants in the intervention arm will receive up to daily, tailored text messages based on their electronic pill bottle-measured adherence. Given the participants' baseline characteristics and time-varying responses to the messages, a reinforcement learning algorithm will deliver different text messages and adapt over time to determine which type of messaging works best for each individual participant.
|
Control Arm
n=31 Participants
Up to daily, untailored text messages.
|
|---|---|---|
|
Medication Adherence
|
74 pill bottle openings
Standard Deviation 31
|
68 pill bottle openings
Standard Deviation 29
|
SECONDARY outcome
Timeframe: 6 monthsPopulation: Participants were included in the analysis until they no longer participated in the study. Differences were calculated among those who had follow-up HbA1c values recorded.
Change in glycated hemoglobin A1c from baseline to end of the 6-month follow-up
Outcome measures
| Measure |
Reinforcement Learning Intervention Arm
n=29 Participants
Up to daily, tailored text messages.
Reinforcement Learning: Participants in the intervention arm will receive up to daily, tailored text messages based on their electronic pill bottle-measured adherence. Given the participants' baseline characteristics and time-varying responses to the messages, a reinforcement learning algorithm will deliver different text messages and adapt over time to determine which type of messaging works best for each individual participant.
|
Control Arm
n=31 Participants
Up to daily, untailored text messages.
|
|---|---|---|
|
Glycemic Control
|
-0.82 percentage glycated hemoglobin
Standard Deviation 1.19
|
-1.20 percentage glycated hemoglobin
Standard Deviation 2.28
|
Adverse Events
Reinforcement Learning Intervention Arm
Serious events: 0 serious events
Other events: 0 other events
Deaths: 0 deaths
Control Arm
Serious events: 0 serious events
Other events: 0 other events
Deaths: 1 deaths
Serious adverse events
Adverse event data not reported
Other adverse events
Adverse event data not reported
Additional Information
Julie Lauffenburger, PharmD, PhD
Brigham and Women's Hospital
Phone: 617-525-8865
Email: [email protected]
Results disclosure agreements
- Principal investigator is a sponsor employee
- Publication restrictions are in place