AI Wellness Chatbot for Depression and Anxiety

Overseen By Camellia Bui

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Pennsylvania

Disqualifiers: Severe depression, Suicidality

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

Compensation: Varies

Number of Visits: Unknown

Duration: 4 weeks

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial evaluates an AI mental health chatbot called Elomia to assess its effectiveness in helping college students manage stress, anxiety, and feelings of being overwhelmed. Elomia provides support and strategies using responses developed by real therapists. Participants will use Elomia for about 30 minutes each week, with the option to use it more if desired. The trial seeks undergraduate students at the University of Pennsylvania experiencing mild to moderate depression or anxiety. As an unphased trial, participants can contribute to innovative mental health solutions while receiving personalized support.

Do I need to stop my current medications to join the trial?

The trial information does not specify whether you need to stop taking your current medications.

What prior data suggests that this AI mental health chatbot is safe for college students?

Research shows that doctors created Elomia, an AI mental health chatbot, to help with stress, anxiety, and depression. However, studies have not fully assessed its safety for users. While Elomia aims to provide support and has benefited many, clear information about its safety remains insufficient. Participants in earlier studies reported improvements in mental health, but specific safety details are not well-documented. This uncertainty means the long-term use of the chatbot without issues is not guaranteed. As a digital tool, Elomia lacks the physical side effects of medications, but users should remain aware of the limited safety data. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about Elomia, a digital mental health chatbot, because it offers a novel approach to addressing depression and anxiety. Unlike traditional treatments, such as medication and face-to-face therapy, Elomia leverages artificial intelligence to provide personalized support through text-based interactions. Trained by real therapists, it can suggest evidence-based therapeutic strategies and help users tackle feelings like stress, anxiety, and procrastination. Its accessibility and convenience allow users to engage with it as needed, making mental health support more readily available and flexible.

What evidence suggests that the Elomia chatbot is effective for depression and anxiety?

Research has shown that AI chatbots like Elomia, which participants in this trial may use, can help reduce depression and anxiety. One study found that Elomia provided personalized support and strategies, helping users feel less overwhelmed and better able to manage stress. Another study indicated that Elomia could assist users in dealing with negative feelings and improving their emotional well-being. These findings suggest that Elomia might be a useful tool for college students seeking mental health support. Meanwhile, participants in another arm of this trial will use the Penn Wellness Modules, a curated collection of digital wellness resources. ^{3 4 6 7 8}

Who Is on the Research Team?

Melissa G Hunt, PhD

Principal Investigator

University of Pennsylvania

Are You a Good Fit for This Trial?

This trial is for University of Pennsylvania undergraduate students who are at least 18 years old. It's designed to help those experiencing depression, anxiety, or high levels of stress.

Inclusion Criteria

N/A

I am an undergraduate student at the University of Pennsylvania and am 18 or older.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants use either the Elomia chatbot or Penn Wellness Modules at least once per week for around 30 minutes

4 weeks

Follow-up

Participants are monitored for changes in depression, anxiety, and stress symptoms

4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• Elomia

Trial Overview The study is evaluating an AI-enabled mental health chatbot called Elomia and comparing it with Penn Digital Wellness Resources to see how well they support student wellness.

How Is the Trial Designed?

Group I: Elomia - Digital Mental Health Chatbot Experimental Treatment 1 Intervention

Participants randomized to Elomia will be expected to use the intervention at least once per week (for around 30 minutes) but are encouraged to use as needed/wanted. Elomia is a generative AI program that can respond to text the user types in with unique responses that are designed to address therapeutic targets like stress, anxiety, procrastination, feeling overwhelmed and so on. Elomia was "trained" by real therapists with expertise in cognitive-behavioral therapy who responded to many different real people typing about their concerns. Thus, Elomia can suggest a number of different evidence based therapeutic strategies and can help the user process negative feelings, think through problems, plan solutions, and trouble shoot things that might get in the way of implementing those strategies.

Group II: Penn Wellness Modules Active Control 1 Intervention

Participants randomized to the control condition will be expected to use the intervention at least once per week (for around 30 minutes) but are encouraged to use as needed/wanted. The control condition consists of a curated collection of digital wellness resources that are already available freely to Penn students, including tips on getting good sleep, learning center material on time management and procrastination, and so on. The resources will be accessed via a single website, but there is no interactive component.

Who Is Running the Clinical Trial?

University of Pennsylvania

Lead Sponsor

Trials

2,118

Recruited

45,270,000+

Published Research Related to This Trial

The study aims to test 'ChatV', an AI health bot designed to improve adherence to varenicline, a medication for smoking cessation, by providing reminders and support to users during a 12-week treatment period with 40 participants.

The feasibility study will assess how well participants use ChatV and its impact on medication adherence and smoking cessation, with results guiding the decision to proceed to a larger randomized controlled trial.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

AI Conversational Agent to Improve Varenicline Adherence: Protocol for a Mixed Methods Feasibility Study. Minian, N., Mehra, K., Earle, M., et al.[2023]

The 16-week Feel Program, a digital mental health support initiative, showed a 65% retention rate among 48 adult participants, with high user satisfaction (65% reported very high satisfaction) and significant engagement in activities designed to manage depressive and anxiety symptoms.

Results indicated that 93.5% of participants experienced a decrease in depressive or anxiety symptoms, with 51.6% showing clinically significant improvement, suggesting that higher engagement in the program correlates with better mental health outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Feasibility, engagement, and preliminary clinical outcomes of a digital biodata-driven intervention for anxiety and depression. Tsirmpas, C., Andrikopoulos, D., Fatouros, P., et al.[2022]

In a study involving 1,205 users of the Wysa app for mental health, users reported a strong therapeutic alliance with the AI conversational agent, with scores comparable to traditional therapy methods like CBT.

Over a brief period of 3 days, users' perceptions of their bond with Wysa improved, indicating that digital mental health services can effectively foster a therapeutic relationship similar to that found in face-to-face therapy.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Evaluating the Therapeutic Alliance With a Free-Text CBT Conversational Agent (Wysa): A Mixed-Methods Study. Beatty, C., Malik, T., Meheli, S., et al.[2022]

Chatbots can effectively support patients with anxiety and depression, serving as affordable and efficient virtual assistants, especially in areas with limited mental health resources.

Out of 42 studies reviewed, about 60% of chatbots targeted both anxiety and depression, indicating their versatility in addressing multiple mental health issues, while their role in mental health care is expected to grow.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Chatbot features for anxiety and depression: A scoping review. Ahmed, A., Hassan, A., Aziz, S., et al.[2023]

AI-based chatbots, like Happify Health's Anna, are emerging as promising tools in digital mental health interventions (DMHIs) for diagnostics, symptom management, and behavior change, highlighting their potential effectiveness and usability.

Future research should focus on understanding user perceptions of AI, individual differences in responses, and ethical considerations to enhance the integration and impact of AI in mental health services.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificially intelligent chatbots in digital mental health interventions: a review. Boucher, EM., Harake, NR., Ward, HE., et al.[2022]

Project AFFECT aims to create an AI-based software, LyssnCBT, to automatically assess the quality of cognitive behavioral therapy (CBT) sessions, which could enhance training and supervision for therapists and improve treatment outcomes for clients.

In a planned Phase II trial involving 1,875 clients, the effectiveness of LyssnCBT will be evaluated to see if it can improve therapist skills, client outcomes, and reduce client drop-out rates, marking a significant step towards scalable quality assurance in psychotherapy.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Enhancing the quality of cognitive behavioral therapy in community mental health through artificial intelligence generated fidelity feedback (Project AFFECT): a study protocol. Creed, TA., Salama, L., Slevin, R., et al.[2023]

Citations

1. pubmed.ncbi.nlm.nih.gov pubmed.ncbi.nlm.nih.gov/38631422/

The therapeutic effectiveness of artificial intelligence-based ... This meta-analysis highlights the promising role of AI-based chatbot interventions in alleviating depressive and anxiety symptoms among adults.

2. ceur-ws.org ceur-ws.org/Vol-2870/paper89.pdf

Elomia Chatbot: the Effectiveness of Artificial Intelligence in ... The article is presenting results of controlled study of effectiveness of Elomia chatbot in reducing tendency to depression, anxiety and negative emotional ...

3. elomia.com elomia.com/research/Elomia%20UPenn%20Research%20Paper.pdf

Acceptability and Efficacy of a Mental Health Chatbot Depression, desperation, and suicidal ideation in college students: results from the. American Foundation for Suicide Prevention College Screening Project at ...

4. sciencedirect.com sciencedirect.com/science/article/pii/S2214782922000021

Using AI chatbots to provide self-help depression ... The therapy chatbot reduced depression in the 16 weeks intervention period and reduced anxiety in the first 4 weeks. •. A significantly better therapeutic ...

5. withpower.com withpower.com/trial/phase-depression-2025-8d613

AI Wellness Chatbot for Depression and Anxiety The 16-week Feel Program, a digital mental health support initiative, showed a 65% retention rate among 48 adult participants, with high user satisfaction (65% ...

6. elomia.com elomia.com/

Elomia — AI Mental Health Chatbot Designed by Clinicians Elomia is an AI mental health chatbot designed by clinicians. It is anonymous, available 24/7, and covers people with all kinds of problems, from having a ...

7. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC11980345/

GymBuddy and Elomia, AI-integrated applications, effects ... Mental health outcomes such as anxiety, depression, and stress levels were assessed using standardized baseline, midpoint, and endpoint measures ...

8. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC10242473/

An Overview of Chatbot-Based Mobile Mental Health Apps According to recent studies, patient safety has rarely been evaluated, health outcomes have been inadequately quantified, and no ...