Medication Adherence
Conditions
Keywords
Voice Assistant, Medication Management, Insulin Management, Smart Speaker, AI, Artificial Intelligence, Autonomous Prescriptions
Brief summary
This study randomizes participants to have their basal insulin titrated either through standard of care or by receiving prompts through interactions with an AI-enabled smart speaker device. The primary objective of this study is to investigate the feasibility of an AI-enabled smart speaker device and whether such a device facilitates insulin titration management, increases insulin adherence and decreases time to optimal insulin dose. The secondary objective of the study is to explore whether the device improves glycemic control as defined by improvements in fasting blood sugar.
Interventions
DEVICEVoice Assistant Device
Voice AI-enabled smart speaker device delivers daily custom insulin titration instructions.
Sponsors
Stanford University
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
TREATMENT
Masking
NONE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
* Patients with Type 2 Diabetes * Patients clinically indicated to be taking daily long-acting insulin * Patients currently taking long-acting insulin but necessitating active dose adjustments
Exclusion criteria
* Patients who do not speak English * Patients who do not own a smart phone * Patients who do not have stable wireless internet connection at home
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Insulin Medication Adherence | 8 weeks | Percentage of adherence to taking insulin based on logs over 8 weeks |
| Attitudes Toward Health Technology | Baseline and 8 weeks | Change in Composite Score of Attitudes Toward Health Technology. A 2-item self-report questionnaire on a 5 point Likert scale, scored 0 to 4. The scores are summed to create an overall score (Minimum value = 0, Maximum value = 8). Higher scores indicated more favorable attitudes toward health technology. |
| Attitudes Toward Medication Adherence | Baseline and 8 weeks | Change in Composite Score of Attitudes Toward Medication Adherence. A 5-item self-report questionnaire on a 5-point Likert scale (0 to 4). The scores are summed to create an overall score (Minimum value = 0, Maximum value = 20). Higher scores indicate more favorable attitudes toward medication adherence. |
| Time to Optimal Insulin Dose | 8 weeks | Number of days between study start date and goal fasting sugar |
| Attitudes Toward Diabetes | Baseline and 8 weeks | Change in Composite Score of Attitudes Toward Diabetes (PAID-5). A 5-item psychometrically validated self-report questionnaire on a 5 point Likert scale (0= not problem; 4= a serious problem). The scores of each item are summed to create an overall score (Minimum value = 0; Maximum value = 20). Higher scores denote higher levels of diabetes related distress. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Glycemic Improvement | Day 3 and 8 weeks (assessed at the end of each 3 day period) | Change in 3-day average fasting sugars between first 3 days and last 3 days of study |
| Percentage of Participants Who Achieved Glycemic Control | 8 weeks | Proportion (percentage) of participants with fasting sugar within goal at end of trial. |
Countries
United States
Participant flow
Participants by arm
| Arm | Count |
|---|---|
| Control Subjects have their insulin titrated via standard of care for 8 weeks. The Voice Assistant Device is limited to providing a daily reminder to take medication. | 16 |
| Voice Assistant Device Subjects have their insulin titrated by a voice assistant device for 8 weeks. The Voice Assistant Device software algorithm is used to provide daily insulin dose and titration instructions. | 16 |
| Total | 32 |
Baseline characteristics
| Characteristic | Control | Total | Voice Assistant Device |
|---|---|---|---|
| Age, Continuous | 56.2 years STANDARD_DEVIATION 13.5 | 55.1 years STANDARD_DEVIATION 12.7 | 54.1 years STANDARD_DEVIATION 12.3 |
| Ethnicity (NIH/OMB) Hispanic or Latino | 5 Participants | 8 Participants | 3 Participants |
| Ethnicity (NIH/OMB) Not Hispanic or Latino | 11 Participants | 24 Participants | 13 Participants |
| Ethnicity (NIH/OMB) Unknown or Not Reported | 0 Participants | 0 Participants | 0 Participants |
| Race (NIH/OMB) American Indian or Alaska Native | 0 Participants | 1 Participants | 1 Participants |
| Race (NIH/OMB) Asian | 5 Participants | 8 Participants | 3 Participants |
| Race (NIH/OMB) Black or African American | 1 Participants | 2 Participants | 1 Participants |
| Race (NIH/OMB) More than one race | 1 Participants | 3 Participants | 2 Participants |
| Race (NIH/OMB) Native Hawaiian or Other Pacific Islander | 0 Participants | 0 Participants | 0 Participants |
| Race (NIH/OMB) Unknown or Not Reported | 1 Participants | 2 Participants | 1 Participants |
| Race (NIH/OMB) White | 8 Participants | 16 Participants | 8 Participants |
| Region of Enrollment United States | 16 Participants | 32 Participants | 16 Participants |
| Sex: Female, Male Female | 10 Participants | 19 Participants | 9 Participants |
| Sex: Female, Male Male | 6 Participants | 13 Participants | 7 Participants |
Adverse events
| Event type | EG000 affected / at risk | EG001 affected / at risk |
|---|---|---|
| deaths Total, all-cause mortality | 0 / 16 | 0 / 16 |
| other Total, other adverse events | 0 / 16 | 0 / 16 |
| serious Total, serious adverse events | 0 / 16 | 0 / 16 |
Outcome results
Primary
Attitudes Toward Diabetes
Change in Composite Score of Attitudes Toward Diabetes (PAID-5). A 5-item psychometrically validated self-report questionnaire on a 5 point Likert scale (0= not problem; 4= a serious problem). The scores of each item are summed to create an overall score (Minimum value = 0; Maximum value = 20). Higher scores denote higher levels of diabetes related distress.
Time frame: Baseline and 8 weeks
Population: Participants who received intervention as randomized
| Arm | Measure | Group | Value (MEAN) | Dispersion |
|---|---|---|---|---|
| Control | Attitudes Toward Diabetes | Baseline | 6.5 score on a scale | Standard Deviation 4.9 |
| Control | Attitudes Toward Diabetes | Change at Week 8 | 1.7 score on a scale | Standard Deviation 4.4 |
| Voice Assistant Device | Attitudes Toward Diabetes | Baseline | 8.4 score on a scale | Standard Deviation 3.4 |
| Voice Assistant Device | Attitudes Toward Diabetes | Change at Week 8 | -1.9 score on a scale | Standard Deviation 4.2 |
p-value: 0.0395% CI: [-6.8, -0.4]Welch 2-sample method
Primary
Attitudes Toward Health Technology
Change in Composite Score of Attitudes Toward Health Technology. A 2-item self-report questionnaire on a 5 point Likert scale, scored 0 to 4. The scores are summed to create an overall score (Minimum value = 0, Maximum value = 8). Higher scores indicated more favorable attitudes toward health technology.
Time frame: Baseline and 8 weeks
Population: Participants who received intervention as randomized
| Arm | Measure | Group | Value (MEAN) | Dispersion |
|---|---|---|---|---|
| Control | Attitudes Toward Health Technology | Baseline | 6.6 score on a scale | Standard Deviation 1.9 |
| Control | Attitudes Toward Health Technology | Change at Week 8 | -1.1 score on a scale | Standard Deviation 2.3 |
| Voice Assistant Device | Attitudes Toward Health Technology | Baseline | 7.1 score on a scale | Standard Deviation 1.5 |
| Voice Assistant Device | Attitudes Toward Health Technology | Change at Week 8 | 0.3 score on a scale | Standard Deviation 1.4 |
p-value: 0.0695% CI: [-0.03, 2.8]Welch 2-sample method
Primary
Attitudes Toward Medication Adherence
Change in Composite Score of Attitudes Toward Medication Adherence. A 5-item self-report questionnaire on a 5-point Likert scale (0 to 4). The scores are summed to create an overall score (Minimum value = 0, Maximum value = 20). Higher scores indicate more favorable attitudes toward medication adherence.
Time frame: Baseline and 8 weeks
Population: Participants who received intervention as randomized
| Arm | Measure | Group | Value (MEAN) | Dispersion |
|---|---|---|---|---|
| Control | Attitudes Toward Medication Adherence | Baseline | 13.6 score on a scale | Standard Deviation 3.8 |
| Control | Attitudes Toward Medication Adherence | Change at Week 8 | -0.1 score on a scale | Standard Deviation 2.6 |
| Voice Assistant Device | Attitudes Toward Medication Adherence | Baseline | 14.0 score on a scale | Standard Deviation 4.4 |
| Voice Assistant Device | Attitudes Toward Medication Adherence | Change at Week 8 | 0.8 score on a scale | Standard Deviation 4.3 |
p-value: 0.4695% CI: [-1.6, 3.5]Welch 2-sample method
Primary
Insulin Medication Adherence
Percentage of adherence to taking insulin based on logs over 8 weeks
Time frame: 8 weeks
Population: Participants who received intervention as randomized
| Arm | Measure | Value (MEAN) | Dispersion |
|---|---|---|---|
| Control | Insulin Medication Adherence | 50.2 percentage of adherance | Standard Deviation 43 |
| Voice Assistant Device | Insulin Medication Adherence | 82.9 percentage of adherance | Standard Deviation 20.6 |
p-value: 0.0195% CI: [8, 57.4]Welch 2-sample method
Primary
Time to Optimal Insulin Dose
Number of days between study start date and goal fasting sugar
Time frame: 8 weeks
Population: Participants who received intervention as randomized
| Arm | Measure | Value (MEDIAN) |
|---|---|---|
| Control | Time to Optimal Insulin Dose | 56 days |
| Voice Assistant Device | Time to Optimal Insulin Dose | 15 days |
p-value: 0.006Log Rank
Secondary
Glycemic Improvement
Change in 3-day average fasting sugars between first 3 days and last 3 days of study
Time frame: Day 3 and 8 weeks (assessed at the end of each 3 day period)
Population: Participants who received intervention as randomized
| Arm | Measure | Group | Value (MEAN) | Dispersion |
|---|---|---|---|---|
| Control | Glycemic Improvement | Baseline | 145.9 mg/dL | Standard Deviation 41.5 |
| Control | Glycemic Improvement | Change at Week 8 | 23.0 mg/dL | Standard Deviation 54.7 |
| Voice Assistant Device | Glycemic Improvement | Baseline | 167.5 mg/dL | Standard Deviation 53.9 |
| Voice Assistant Device | Glycemic Improvement | Change at Week 8 | -45.9 mg/dL | Standard Deviation 45.9 |
p-value: 0.00195% CI: [-107.1, -30.1]Welch 2-sample method
Secondary
Percentage of Participants Who Achieved Glycemic Control
Proportion (percentage) of participants with fasting sugar within goal at end of trial.
Time frame: 8 weeks
Population: Participants who received intervention as randomized
| Arm | Measure | Value (NUMBER) |
|---|---|---|
| Control | Percentage of Participants Who Achieved Glycemic Control | 25.0 percentage of participants |
| Voice Assistant Device | Percentage of Participants Who Achieved Glycemic Control | 81.3 percentage of participants |
Comparison: Comparison of percentage (proportion) of participants achieving glycemic control.p-value: 0.00595% CI: [0.21, 0.91]2-sample test