Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
This is a feasibility trial of a personalized 8-week text messaging intervention aimed at young adults (ages 18-25) with depression and anxiety who are not interested in -- or experience barriers to -- receiving traditional face-to-face psychological treatments.
The trial will consist of a pilot test of (1) an 8-week adaptive (personalized) messaging intervention relative to (2) a non-personalized digital mental health intervention, or (3) an active control which will send weekly psychoeducation information by way of Uniform Resource Locators (URLs). The adaptive intervention will uses machine learning to tailor Short Message Service (SMS) messages to an individual's needs and preferences, and URL links to provide access to psychoeducational content to contextualize messages, when the length of that content exceeds the limitations of messages.
The primary goals of the project are to conduct a feasibility trial using a sequential multiple assignment randomized treatment (SMART) design, which will evaluate (a) the effectiveness of an adaptive, personalized messaging intervention in reducing engagement relative to a non-personalized version; and (b) whether human coaching results in greater symptom reduction and engagement, relative an unguided implementation.
The primary purpose of this trial is to test the feasibility of conducting a randomized controlled trial of digital mental health intervention (DMHI) for non-treatment seeking young adults with symptoms of depression or anxiety, comparing an 8-week adaptive (personalized) messaging intervention, an 8-week non-personalized digital mental health intervention, or an active control which will deliver psychoeducational content via clickable URLs. The adaptive intervention will be powered by reinforcement learning to deliver tailored SMS messages based on user profiles and the ways in which a user interacts with the intervention system, along with links to longer psychoeducational content. The non-personalized intervention arm will not personalize the messages, but will still be an active treatment. This study will examine the adaptive intervention's ability to engage users and effectiveness in decreasing psychological distress relative to a non-personalized intervention. Participants who become disengaged (5 continuous days of not clicking on content URL links, responding to messages, or message ratings) from the adaptive or static intervention arms at any point in the first two weeks of treatment will be randomized to receive low-intensity human coaching or continue without coaching for the remainder of the intervention period.
Recruitment will take place via Mental Health America's (MHA) website. MHA is a large mental health advocacy organization that hosts online screeners and has large number of visitors the majority of whom meet clinical cutoffs for depressive or anxiety disorder symptoms. This study will enroll individuals who have completed a depression or anxiety disorder screener on MHA's website, and meet clinical cut-offs on the Patient Health Questionnaire - 9 (PHQ-9) or Generalized Anxiety Disorder - 7 (GAD-7).
Initial randomization will be generated in permuted blocks of 5 using a computer program. To prevent allocation bias, randomization will be conducted by the biostatistician, who will not inform the study team of the treatment arms until the baseline assessment has been completed and the patient has been enrolled. Second randomization of disengaged participants will occur as disengagement is detected during the first two weeks. Half (50%) of disengaged individuals will be randomized to receive additional human coaching throughout the remainder of the study while remaining in either the adaptive or non-personalized treatment arms. The disengaged participants not randomized to receive additional human coaching will continue to receive either the non-personalized or adaptive automated treatment the participants were randomized to initially.
Coaching will consist of providing users with support and accountability via positive reinforcement, goal and expectation setting, and monitoring. Coaching outreach will focus on adherence to the treatment but will not provide treatment advice. Coaches will provide a brief (15-minute phone call or equivalent depending on the medium) engagement session over the phone, SMS, or email, depending user preference. Thereafter, coaches will check in with participants via messaging, phone call, or email, twice per week and respond to patient texts.
Participants will be assessed using self-report measures at baseline, weeks 4, 8, 12, and 16 weeks.
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Adaptive digital mental health intervention without coaching | Experimental | The adaptive intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Psychoeducational content will be delivered via a URL in an SMS message. Machine learning will be used to tailor messages and timing to meet participant preferences. |
|
| Non-personalized digital Mental Health intervention without coaching | Experimental | The non-personalized intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Messages and content will not be tailored based on participants profile or usage. |
|
| Adaptive digital mental health intervention with coaching | Experimental | The adaptive intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Psychoeducational content will be delivered via a URL in an SMS message. Machine learning will be used to tailor messages and timing to meet participant preferences. Coaching will be provided to support engagement and intervention use via medium of participants choice (texts, calls, or emails). |
|
| Non-personalized digital Mental Health intervention with coaching | Experimental |
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Adaptive messaging intervention | Behavioral | Psychological content and messages delivered regularly over an 8-week period via interactive SMS messages. Content and messages will be tailored using machine learning. |
| Measure | Description | Time Frame |
|---|---|---|
| Kessler Psychological Distress Scale | 10-item self-report measure of transdiagnostic distress, used as outcome measure across diagnostic categories. Higher scores mean greater distress. Minimum score: 10; maximum score: 50 | 16 weeks |
| Engagement Length | Last message/content rating or click on content URL link received from participant. This measure can include select individuals who exceed 56 days of interaction due to user's ability to temporarily pause receipt of messages, resulting in messages extending beyond 8 weeks (56 days). | 62 days |
| Measure | Description | Time Frame |
|---|---|---|
| Patient Health Questionnaire-9 | 10-item self-report measure assessing depression symptom severity. Higher scores mean greater symptom severity. Minimum score: 0; maximum score: 27 | 16 weeks |
| Generalized Anxiety Disorder-7 |
| Measure | Description | Time Frame |
|---|---|---|
| Depression Symptom Inventory - Suicidality Subscale | 4-item self-report questionnaire assessing the frequency and intensity of suicidal thoughts over previous two weeks. Higher scores signal greater frequency and severity of suicidal thoughts. Minimum score: 0; maximum score: 12 | 16 weeks |
| Cognitive Behavioral Response to Stress Scale |
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Affiliation | Role |
|---|---|---|
| David C Mohr, PhD | Northwestern University | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Northwestern University | Chicago | Illinois | 60611 | United States |
De-identified data will be shared through and managed by the National Institute of Mental Health (NIMH) Data Archive (NDA). De-identified human subjects data, harmonized to a common standard, are available to qualified researchers.
Data will be available after publication of the primary outcome papers.
The NIMH Data Archive is managed by the NIMH. Access criteria are determined by the NIMH.
Prior to random assignment, participants who provided affirmative informed consent were required to have completed baseline assessments, confirm their ability to receive text messages as part of the intervention, and complete required payment forms.
Participants were recruited from the Mental Health America (MHA) screening website. Website visitors who completed a depression or anxiety screening form and obtained a score of 10 or higher on either screener were eligible to see an advertisement for our study that contained a link to an informational page and eligibility screening form. Those meeting eligibility criteria were given an option of providing informed consent.
Not provided
| ID | Title | Description |
|---|---|---|
| FG000 | Adaptive Digital Mental Health Intervention | The adaptive intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Psychoeducational content will be delivered via a URL in an SMS message. Machine learning will be used to tailor messages and timing to meet participant preferences. |
| FG001 | Non-personalized Digital Mental Health Intervention | The non-personalized intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Messages and content will not be tailored based on participants profile or usage. |
| FG002 | Adaptive Digital Mental Health Intervention With Coaching | The adaptive intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Psychoeducational content will be delivered via a URL in an SMS message. Machine learning will be used to tailor messages and timing to meet participant preferences. Coaching will be provided to support engagement and intervention use via medium of participants choice (texts, calls, or emails). |
| FG003 | Non-personalized Digital Mental Health Intervention With Coaching | The non-personalized intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Messages and content will not be tailored based on participants profile or usage. Coaching will be provided to support engagement and intervention use via medium of participants choice (texts, calls, or emails). |
| FG004 | Active Control | The active control condition will provide brief text messages that include a URL link to psychoeducational content, but will not include the interactive messaging component described in experimental arms. |
| Title | Milestones | Reasons Not Completed | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| First Randomization |
| |||||||||||||
| Second Randomization |
|
Non-treatment seeking young adult Mental Health America website visitors
Not provided
| ID | Title | Description |
|---|---|---|
| BG000 | Adaptive Digital Mental Health Intervention Without Coaching | The adaptive intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Psychoeducational content will be delivered via a URL in an SMS message. Machine learning will be used to tailor messages and timing to meet participant preferences. |
| Units | Counts |
|---|---|
| Participants |
|
| Title | Description | Population Description | Parameter Type | Dispersion Type | Unit of Measure | Calculate Percentage | Denominator Units Selected | Denominators | Classes |
|---|---|---|---|---|---|---|---|---|---|
| Race (NIH/OMB) | Grouping by initial treatment arm assignment |
| Type | Title | Description | Population Description | Reporting Status | Anticipated Posting Date | Parameter Type | Dispersion Type | Unit of Measure | Calculate Percentage | Time Frame | Units Analyzed | Denominator Units Selected | Arm/Group Information | Denominators | Classes | Analyses | |||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Primary | Kessler Psychological Distress Scale | 10-item self-report measure of transdiagnostic distress, used as outcome measure across diagnostic categories. Higher scores mean greater distress. Minimum score: 10; maximum score: 50 | Numbers are lower than participants assigned to groups due to loss to follow-up or incomplete data. Results are grouped per-arm and includes data from all participants with available data. | Posted | Mean | Standard Deviation | Score | 16 weeks |
|
From enrollment until end of follow-up, up to 16 weeks
Results are grouped by initial treatment assignment (adaptive or non-personalized digital mental health intervention or control) as the primary focus of this feasibility trial was feasibility of primary treatment randomization and thus includes data from all participants.
Not provided
| ID | Title | Description | Deaths (Affected) | Deaths (At Risk) | Serious Events (Affected) | Serious Events (At Risk) | Other Events (Affected) | Other Events (At Risk) |
|---|---|---|---|---|---|---|---|---|
| EG000 | Adaptive Digital Mental Health Intervention Without Coaching | The adaptive intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Psychoeducational content will be delivered via a URL in an SMS message. Machine learning will be used to tailor messages and timing to meet participant preferences. |
Not provided
Not provided
Loss to follow-up and missing data affect the interpretability of data from this trial (as all trials). Additionally, this trial was powered for feasibility not for efficacy.
| Title | Organization | Phone | Extension | |
|---|---|---|---|---|
| Jonah Meyerhoff | Northwestern University | 3125031232 | jonah.meyerhoff@northwestern.edu |
Not provided
| Type | Includes Protocol | Includes SAP | Includes ICF | Document Label | Document Date | Document Uploaded Date | Document File Name |
|---|---|---|---|---|---|---|---|
| Prot | Yes | No | No | Study Protocol | Jun 7, 2023 | Dec 22, 2025 | Prot_000.pdf |
| SAP | No | Yes | No | Statistical Analysis Plan | Dec 5, 2025 | Dec 22, 2025 | SAP_001.pdf |
Not provided
| ID | Term |
|---|---|
| D003863 | Depression |
| D001008 | Anxiety Disorders |
| D059020 | Suicidal Ideation |
| ID | Term |
|---|---|
| D001526 | Behavioral Symptoms |
| D001519 | Behavior |
| D001523 | Mental Disorders |
| D013405 | Suicide |
Not provided
Not provided
This study uses a sequential multiple assignment randomized trial (SMART) design. The first level of randomization is to one of the three treatment conditions: self-guided non-personalized intervention, self-guided adaptive intervention, or active control. The second level of randomization occurs during the first two weeks of intervention. Participants who meet criteria for disengagement from either the non-personalized or adaptive intervention are then randomized to receive coaching or continue as self-guided. This will provide the investigators with preliminary information on the need for and value of coaching. Participants will receive the assigned intervention from baseline to week 8, followed by an 8 week follow-up period
Not provided
Not provided
Not provided
Not provided
The non-personalized intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Messages and content will not be tailored based on participants profile or usage. Coaching will be provided to support engagement and intervention use via medium of participants choice (texts, calls, or emails).
|
| Active control | Active Comparator | The active control condition will provide brief text messages that include a URL link to psychoeducational content, but will not include the interactive messaging component described in experimental arms. |
|
| Non-personalized messaging intervention | Behavioral | Psychological content and messages delivered regularly over an 8-week period via interactive SMS messages. Psychological content will center on a single psychological strategy each week. There will not be any tailoring of messaging and content based on group or individual level data. |
|
| Coaching | Behavioral | Human coaching to support intervention use and engagement via telephone calls, text or email |
|
| Psychoeducational links | Behavioral | SMS messages with URLs containing brief psychoeducational information. |
|
8-item self-report measure assessing generalized anxiety disorder symptom severity Higher scores mean greater symptom severity. Minimum score: 0; maximum score: 21
| 16 weeks |
9-item self-report measure of behavioral and cognitive coping related skills. Higher scores indicate greater adaptive cognitive and behavioral skills use. Two domains: Frequency of use and usefulness. For each domain, there is a subscale of cognitive (4 items) or behavioral (5 items) coping skills. Frequency rated 0-6 with higher scores being more frequent use. Usefulness is rated 0-6 with higher scores being more useful. Cognitive skill frequency range: 0-24 Cognitive skill usefulness range: 0-24 Behavioral skill frequency range: 0-35 Behavioral skill usefulness range: 0-35 |
| 16 weeks |
| Objective Engagement Markers: Percent of Messages Responded to | Number of messages responded to during the active messaging/intervention period. | 62 days |
| Objective Engagement Markers: Link Clicks | Number of URL clicks during the study. | 62 days |
| COMPLETED |
|
| NOT COMPLETED |
|
| BG001 | Non-personalized Digital Mental Health Intervention Without Coaching | The non-personalized intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Messages and content will not be tailored based on participants profile or usage. |
| BG002 | Active Control | The active control condition will provide brief text messages that include a URL link to psychoeducational content, but will not include the interactive messaging component described in experimental arms. |
| BG003 | Total | Total of all reporting groups |
| Count of Participants |
| Participants |
|
| Ethnicity (NIH/OMB) | Grouping by initial treatment arm assignment | Count of Participants | Participants |
|
| Age, Categorical | Grouping by initial treatment arm assignment | Count of Participants | Participants |
|
| Sex/Gender, Customized | Grouping by initial treatment arm assignment | Count of Participants | Participants |
|
| Psychological Distress (Kessler 10/K10 Score) | Grouping by initial treatment arm assignment | Mean | Standard Deviation | Score |
|
| OG001 | Non-personalized Digital Mental Health Intervention Without Coaching | The non-personalized intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Messages and content will not be tailored based on participants profile or usage. |
| OG002 | Adaptive Digital Mental Health Intervention With Coaching | The adaptive intervention consists of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Psychoeducational content is delivered via a URL in an SMS message. Machine learning is be used to tailor messages and timing to meet participant preferences. Coaching is be provided to support engagement and intervention use via medium of participants choice (texts, calls, or emails). |
| OG003 | Non-personalized Digital Mental Health Intervention With Coaching | The non-personalized intervention consists of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Messages and content are nottailored based on participants profile or usage. Coaching is provided to support engagement and intervention use via medium of participants choice (texts, calls, or emails). |
| OG004 | Active Control | The active control condition will provide brief text messages that include a URL link to psychoeducational content, but will not include the interactive messaging component described in experimental arms. |
|
|
| Primary | Engagement Length | Last message/content rating or click on content URL link received from participant. This measure can include select individuals who exceed 56 days of interaction due to user's ability to temporarily pause receipt of messages, resulting in messages extending beyond 8 weeks (56 days). | Numbers are lower than participants assigned to groups due to loss to follow-up or incomplete data. Results are grouped per-arm and includes data from all participants with available data. | Posted | Mean | Standard Deviation | Days | 62 days |
|
|
|
| Secondary | Patient Health Questionnaire-9 | 10-item self-report measure assessing depression symptom severity. Higher scores mean greater symptom severity. Minimum score: 0; maximum score: 27 | Differences in numbers from those assigned due to loss to follow-up or individuals with incomplete data. Results are grouped per arm and include data from all participants with available data. | Posted | Mean | Standard Deviation | Score | 16 weeks |
|
|
|
| Secondary | Generalized Anxiety Disorder-7 | 8-item self-report measure assessing generalized anxiety disorder symptom severity Higher scores mean greater symptom severity. Minimum score: 0; maximum score: 21 | Numbers are lower than participants assigned to groups due to loss to follow-up or incomplete data. Results are grouped per arm and include data from all participants with available data. | Posted | Mean | Standard Deviation | Score | 16 weeks |
|
|
|
| Other Pre-specified | Depression Symptom Inventory - Suicidality Subscale | 4-item self-report questionnaire assessing the frequency and intensity of suicidal thoughts over previous two weeks. Higher scores signal greater frequency and severity of suicidal thoughts. Minimum score: 0; maximum score: 12 | Numbers are lower than participants assigned to groups due to loss to follow-up or incomplete data. Results are grouped per arm and thus include data from all participants with available data. | Posted | Mean | Standard Deviation | Score | 16 weeks |
|
|
|
| Other Pre-specified | Cognitive Behavioral Response to Stress Scale | 9-item self-report measure of behavioral and cognitive coping related skills. Higher scores indicate greater adaptive cognitive and behavioral skills use. Two domains: Frequency of use and usefulness. For each domain, there is a subscale of cognitive (4 items) or behavioral (5 items) coping skills. Frequency rated 0-6 with higher scores being more frequent use. Usefulness is rated 0-6 with higher scores being more useful. Cognitive skill frequency range: 0-24 Cognitive skill usefulness range: 0-24 Behavioral skill frequency range: 0-35 Behavioral skill usefulness range: 0-35 | Numbers are lower than participants assigned to groups due to loss to follow-up or incomplete data. Results are grouped per arm and include data from all participants with available data. | Posted | Mean | Standard Deviation | Score | 16 weeks |
|
|
|
| Other Pre-specified | Objective Engagement Markers: Percent of Messages Responded to | Number of messages responded to during the active messaging/intervention period. | Results are per arm and thus includes data from all participants with available data. This measure can include select individuals who exceed 56 days of interaction due to user's ability to temporarily pause receipt of messages, resulting in messages extending beyond 8 weeks (56 days). Because Active Control is not an interactive medium that contained messages to which participants could respond, there are no participants listed in the active control group. | Posted | Mean | Standard Deviation | Percent of messages responded to | 62 days |
|
|
|
| Other Pre-specified | Objective Engagement Markers: Link Clicks | Number of URL clicks during the study. | Results are grouped per arm. Means and standard deviations include only individuals with >0 link clicks. This measure can include select individuals who clicked on links beyond 56 days of interaction due to user's ability to temporarily pause receipt of messages. | Posted | Mean | Standard Deviation | Number of link clicks per person | 62 days |
|
|
|
| 0 |
| 34 |
| 0 |
| 34 |
| 0 |
| 34 |
| EG001 | Non-personalized Digital Mental Health Intervention Without Coaching | The non-personalized intervention will consist of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Messages and content will not be tailored based on participants profile or usage. | 0 | 30 | 0 | 30 | 0 | 30 |
| EG002 | Adaptive Digital Mental Health Intervention With Coaching | The adaptive intervention consists of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Psychoeducational content is delivered via a URL in an SMS message. Machine learning is be used to tailor messages and timing to meet participant preferences. Coaching is be provided to support engagement and intervention use via medium of participants choice (texts, calls, or emails). | 0 | 6 | 0 | 6 | 0 | 6 |
| EG003 | Non-personalized Digital Mental Health Intervention With Coaching | The non-personalized intervention consists of SMS messages, symptom tracking, and psychological content that centers on evidence-based psychological strategies. Messages and content are nottailored based on participants profile or usage. Coaching is provided to support engagement and intervention use via medium of participants choice (texts, calls, or emails). | 0 | 10 | 0 | 10 | 0 | 10 |
| EG004 | Active Control | The active control condition will provide brief text messages that include a URL link to psychoeducational content, but will not include the interactive messaging component described in experimental arms. | 0 | 40 | 0 | 40 | 0 | 40 |
Not provided
Not provided
| D016728 |
| Self-Injurious Behavior |
|
| Cognitive Skill Usefulness |
|
|
| Behavioral Skill Frequency |
|
|
| Behavioral Skill Usefulness |
|
|