Trial Outcomes & Findings for Can Mental Health Chatbots Help Chronic Disease Populations? (NCT NCT04620668)
NCT ID: NCT04620668
Last Updated: 2024-08-26
Results Overview
The Patient Health Questionnaire (PHQ-9) contains nine items, each of which is rated on a scale of 0 to 3. Ratings are summed for a composite score; the minimum score is 0 and the maximum score is 27. Higher scores indicate higher levels of depression.
Recruitment status
COMPLETED
Study phase
NA
Target enrollment
79 participants
Primary outcome timeframe
Participants are assessed at baseline, two weeks into the study, and four weeks into the study.
Results posted on
2024-08-26
Participant Flow
Recruitment occurred from October 2021 to October 2022.
98 individuals were assessed for eligibility. 19 did not meet inclusion criteria. 79 were assigned to groups.
Participant milestones
| Measure |
Treatment Group (Wysa)
Wysa: Wysa is an AI-based mental health chatbot. It uses evidence-based techniques to help users build mental resilience skills and improve their mental health.
|
Control Group
No treatment control group.
|
|---|---|---|
|
Overall Study
STARTED
|
41
|
38
|
|
Overall Study
COMPLETED
|
34
|
34
|
|
Overall Study
NOT COMPLETED
|
7
|
4
|
Reasons for withdrawal
| Measure |
Treatment Group (Wysa)
Wysa: Wysa is an AI-based mental health chatbot. It uses evidence-based techniques to help users build mental resilience skills and improve their mental health.
|
Control Group
No treatment control group.
|
|---|---|---|
|
Overall Study
Withdrawal by Subject
|
2
|
0
|
|
Overall Study
Ineligible despite claims at outset of the study
|
1
|
0
|
|
Overall Study
Removed before analysis: missing data
|
2
|
0
|
|
Overall Study
Removed before analysis: failed multiple quality check questions
|
1
|
2
|
|
Overall Study
Removed before analysis: statistical outlier
|
1
|
2
|
Baseline Characteristics
Can Mental Health Chatbots Help Chronic Disease Populations?
Baseline characteristics by cohort
| Measure |
Treatment Group (Wysa)
n=34 Participants
Wysa: Wysa is an AI-based mental health chatbot. It uses evidence-based techniques to help users build mental resilience skills and improve their mental health.
|
Control Group
n=34 Participants
No treatment control group.
|
Total
n=68 Participants
Total of all reporting groups
|
|---|---|---|---|
|
Age, Continuous
|
43.50 years
STANDARD_DEVIATION 11.00 • n=5 Participants
|
42.24 years
STANDARD_DEVIATION 11.66 • n=7 Participants
|
42.87 years
STANDARD_DEVIATION 11.27 • n=5 Participants
|
|
Sex/Gender, Customized
Gender · Men
|
8 Participants
n=5 Participants
|
12 Participants
n=7 Participants
|
20 Participants
n=5 Participants
|
|
Sex/Gender, Customized
Gender · Women
|
26 Participants
n=5 Participants
|
21 Participants
n=7 Participants
|
47 Participants
n=5 Participants
|
|
Sex/Gender, Customized
Gender · Transgender Men
|
0 Participants
n=5 Participants
|
1 Participants
n=7 Participants
|
1 Participants
n=5 Participants
|
|
Race/Ethnicity, Customized
Race/Ethnicity · White
|
25 Participants
n=5 Participants
|
25 Participants
n=7 Participants
|
50 Participants
n=5 Participants
|
|
Race/Ethnicity, Customized
Race/Ethnicity · Black / African Canadian
|
0 Participants
n=5 Participants
|
1 Participants
n=7 Participants
|
1 Participants
n=5 Participants
|
|
Race/Ethnicity, Customized
Race/Ethnicity · Indigenous / First Nations
|
1 Participants
n=5 Participants
|
2 Participants
n=7 Participants
|
3 Participants
n=5 Participants
|
|
Race/Ethnicity, Customized
Race/Ethnicity · Hispanic / Latino
|
1 Participants
n=5 Participants
|
0 Participants
n=7 Participants
|
1 Participants
n=5 Participants
|
|
Race/Ethnicity, Customized
Race/Ethnicity · Asian / Pacific Islander
|
5 Participants
n=5 Participants
|
4 Participants
n=7 Participants
|
9 Participants
n=5 Participants
|
|
Race/Ethnicity, Customized
Race/Ethnicity · Middle Eastern
|
0 Participants
n=5 Participants
|
0 Participants
n=7 Participants
|
0 Participants
n=5 Participants
|
|
Race/Ethnicity, Customized
Race/Ethnicity · Other
|
0 Participants
n=5 Participants
|
1 Participants
n=7 Participants
|
1 Participants
n=5 Participants
|
|
Race/Ethnicity, Customized
Race/Ethnicity · Mixed Race or Ethnicity
|
2 Participants
n=5 Participants
|
1 Participants
n=7 Participants
|
3 Participants
n=5 Participants
|
|
Region of Enrollment
Canada
|
34 participants
n=5 Participants
|
34 participants
n=7 Participants
|
68 participants
n=5 Participants
|
|
Chronic Diseases
Diabetes
|
16 Participants
n=5 Participants
|
16 Participants
n=7 Participants
|
32 Participants
n=5 Participants
|
|
Chronic Diseases
Arthritis
|
18 Participants
n=5 Participants
|
18 Participants
n=7 Participants
|
36 Participants
n=5 Participants
|
PRIMARY outcome
Timeframe: Participants are assessed at baseline, two weeks into the study, and four weeks into the study.The Patient Health Questionnaire (PHQ-9) contains nine items, each of which is rated on a scale of 0 to 3. Ratings are summed for a composite score; the minimum score is 0 and the maximum score is 27. Higher scores indicate higher levels of depression.
Outcome measures
| Measure |
Treatment Group (Wysa)
n=34 Participants
Wysa: Wysa is an AI-based mental health chatbot. It uses evidence-based techniques to help users build mental resilience skills and improve their mental health.
|
Control Group
n=34 Participants
No treatment control group.
|
|---|---|---|
|
Changes in Depression as Measured by the Patient Health Questionnaire (PHQ-9)
Baseline
|
8.65 units on a scale
Standard Deviation 6.03
|
7.82 units on a scale
Standard Deviation 6.29
|
|
Changes in Depression as Measured by the Patient Health Questionnaire (PHQ-9)
Week 2
|
7.18 units on a scale
Standard Deviation 4.90
|
7.41 units on a scale
Standard Deviation 5.88
|
|
Changes in Depression as Measured by the Patient Health Questionnaire (PHQ-9)
Week 4
|
5.26 units on a scale
Standard Deviation 4.11
|
7.56 units on a scale
Standard Deviation 6.33
|
PRIMARY outcome
Timeframe: Participants are assessed at baseline, two weeks into the study, and four weeks into the study.The Generalized Anxiety Disorder Scale (GAD-7) contains seven items, each of which is rated on a scale of 0 to 3. Ratings are summed for a composite score; the minimum score is 0 and the maximum score is 21. Higher scores indicate higher levels of anxiety.
Outcome measures
| Measure |
Treatment Group (Wysa)
n=34 Participants
Wysa: Wysa is an AI-based mental health chatbot. It uses evidence-based techniques to help users build mental resilience skills and improve their mental health.
|
Control Group
n=34 Participants
No treatment control group.
|
|---|---|---|
|
Changes in Anxiety as Measured by the Generalized Anxiety Disorder Scale (GAD-7)
Baseline
|
7.44 units on a scale
Standard Deviation 5.37
|
6.09 units on a scale
Standard Deviation 6.27
|
|
Changes in Anxiety as Measured by the Generalized Anxiety Disorder Scale (GAD-7)
Week 2
|
5.85 units on a scale
Standard Deviation 4.02
|
6.32 units on a scale
Standard Deviation 6.66
|
|
Changes in Anxiety as Measured by the Generalized Anxiety Disorder Scale (GAD-7)
Week 4
|
4.74 units on a scale
Standard Deviation 3.30
|
6.56 units on a scale
Standard Deviation 6.45
|
PRIMARY outcome
Timeframe: Participants are assessed at baseline, two weeks into the study, and four weeks into the study.The Perceived Stress Scale (PSS-10) contains ten items, each of which is rated on a scale of 0 to 4. Ratings are summed for a composite score; the minimum score is 0 and the maximum score is 40. Higher scores indicate higher levels of stress.
Outcome measures
| Measure |
Treatment Group (Wysa)
n=34 Participants
Wysa: Wysa is an AI-based mental health chatbot. It uses evidence-based techniques to help users build mental resilience skills and improve their mental health.
|
Control Group
n=34 Participants
No treatment control group.
|
|---|---|---|
|
Changes in Stress as Measured by the Perceived Stress Scale (PSS-10)
Baseline
|
19.00 units on a scale
Standard Deviation 6.79
|
17.53 units on a scale
Standard Deviation 8.83
|
|
Changes in Stress as Measured by the Perceived Stress Scale (PSS-10)
Week 2
|
18.56 units on a scale
Standard Deviation 6.57
|
17.47 units on a scale
Standard Deviation 7.82
|
|
Changes in Stress as Measured by the Perceived Stress Scale (PSS-10)
Week 4
|
17.06 units on a scale
Standard Deviation 6.21
|
17.35 units on a scale
Standard Deviation 7.93
|
SECONDARY outcome
Timeframe: Participants are assessed at baseline, two weeks into the study, and four weeks into the study.The Satisfaction with Life Scale contains five items, each of which is rated on a scale of 1 to 7. Scores are summed for a composite score; the minimum score is 5 and the maximum score is 35. Higher scores indicate higher levels of life satisfaction.
Outcome measures
| Measure |
Treatment Group (Wysa)
n=34 Participants
Wysa: Wysa is an AI-based mental health chatbot. It uses evidence-based techniques to help users build mental resilience skills and improve their mental health.
|
Control Group
n=34 Participants
No treatment control group.
|
|---|---|---|
|
Changes in Life Satisfaction as Measured by the Satisfaction With Life Scale
Baseline
|
18.91 units on a scale
Standard Deviation 6.85
|
19.59 units on a scale
Standard Deviation 7.06
|
|
Changes in Life Satisfaction as Measured by the Satisfaction With Life Scale
Week 2
|
18.29 units on a scale
Standard Deviation 6.87
|
19.50 units on a scale
Standard Deviation 7.39
|
|
Changes in Life Satisfaction as Measured by the Satisfaction With Life Scale
Week 4
|
20.29 units on a scale
Standard Deviation 7.40
|
20.15 units on a scale
Standard Deviation 6.94
|
Adverse Events
Treatment Group (Wysa)
Serious events: 1 serious events
Other events: 1 other events
Deaths: 0 deaths
Control Group
Serious events: 1 serious events
Other events: 2 other events
Deaths: 0 deaths
Serious adverse events
| Measure |
Treatment Group (Wysa)
n=34 participants at risk
Wysa: Wysa is an AI-based mental health chatbot. It uses evidence-based techniques to help users build mental resilience skills and improve their mental health.
|
Control Group
n=34 participants at risk
No treatment control group.
|
|---|---|---|
|
Surgical and medical procedures
Brief hospitalization
|
2.9%
1/34 • 4 weeks (from baseline assessment to final assessment)
|
0.00%
0/34 • 4 weeks (from baseline assessment to final assessment)
|
|
General disorders
Brief hospitalization
|
0.00%
0/34 • 4 weeks (from baseline assessment to final assessment)
|
2.9%
1/34 • 4 weeks (from baseline assessment to final assessment)
|
Other adverse events
| Measure |
Treatment Group (Wysa)
n=34 participants at risk
Wysa: Wysa is an AI-based mental health chatbot. It uses evidence-based techniques to help users build mental resilience skills and improve their mental health.
|
Control Group
n=34 participants at risk
No treatment control group.
|
|---|---|---|
|
Infections and infestations
Infectious disease
|
2.9%
1/34 • 4 weeks (from baseline assessment to final assessment)
|
2.9%
1/34 • 4 weeks (from baseline assessment to final assessment)
|
|
Surgical and medical procedures
Dental procedure
|
0.00%
0/34 • 4 weeks (from baseline assessment to final assessment)
|
2.9%
1/34 • 4 weeks (from baseline assessment to final assessment)
|
Additional Information
Results disclosure agreements
- Principal investigator is a sponsor employee
- Publication restrictions are in place