AI Support for Mental Health Conditions

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Eleos Health

Disqualifiers: Concurrent research study, others

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

Compensation: Varies

Number of Visits: Unknown

280 Participants Needed

Trial Summary

Will I have to stop taking my current medications?

The trial does not specify if you need to stop taking your current medications, but if your medications might interfere with the study outcomes, you may not be eligible to participate.

What data supports the effectiveness of the AI Platform treatment for mental health conditions?

Research suggests that AI-based decision support systems, like the AI Platform, can improve treatment outcomes by personalizing care and predicting better results than traditional methods. For example, a study showed that a similar AI tool, FORT, led to better social function and work readiness in patients with severe mental illness compared to traditional treatment planning. ^{1 2 3 4 5}

Is AI support for mental health conditions safe for humans?

Current research suggests that AI in mental health care can pose risks if used without proper oversight, as it may introduce errors and ethical issues. There is a need for more research and policy to ensure safety before AI is widely used in direct care. ^{3 6 7 8 9}

How is the AI Platform treatment different from other mental health treatments?

The AI Platform treatment is unique because it uses artificial intelligence to provide personalized, on-demand mental health support through chatbots, which can offer round-the-clock assistance and help reduce stigma associated with seeking traditional care. This approach allows for scalable, discreet, and user-friendly mental health support, which is not typically available with standard treatments. ^{10 11 12 13 14}

What is the purpose of this trial?

The goal of this clinical trial is to assess the effectiveness of an artificial intelligence (AI) platform for case managers in a nonprofit health system specializing in mental health and substance use disorder. The main questions it aims to answer are: 1. Is the AI platform acceptable and feasible for case managers? 2. Does the AI platform improve providers' productivity and reported interventions? Participants will be approximately 30 case managers and their 250 adult clients receiving case management services. Researchers will compare the provider productivity and work satisfaction prior to the implementation of the AI platform to following its implementation.

Eligibility Criteria

This trial is for case managers working in a nonprofit health system that deals with mental health and substance use disorders. They will be using an AI platform to manage around 250 adult clients. To participate, these case managers should be currently active and providing case management services.

Inclusion Criteria

I am 18 years old or older.

Participants must be receiving case management services from a Centerstone provider

Exclusion Criteria

Participants currently involved in any other concurrent research study will be excluded to avoid potential confounding factors

I don't have any health issues or take medications that could affect the study results.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Services-as-usual (SAU)

Providers deliver routine case management services and report these services in the usual way

3 months

AI Platform Implementation

Providers use the AI-based platform for documenting services, with access to the Eleos Health platform

3 months

Follow-up

Participants are monitored for productivity and satisfaction after AI platform implementation

4 months

Treatment Details

Interventions

• AI Platform

Trial Overview The study is testing the impact of an AI platform on the productivity and satisfaction of case managers dealing with traumatic stress, depression, anxiety, and substance use disorders. It compares their performance before and after implementing this technology.

Participant Groups

Group I: Artificial Intelligence (AI) Experimental Treatment 1 Intervention

Once randomized to start using the AI-based platform for documenting their services, providers will have access to the Eleos Health platform, a secure and HIPAA-compliant tool specifically designed for documenting behavioral health encounters. This AI-powered platform enables providers to complete progress notes more quickly. Providers will complete the progress notes on their phones, and these notes will be integrated into the client's electronic health records.

Group II: Services-as-usual (SAU) Active Control 1 Intervention

During the services-as-usual (SAU) phase of this study, providers will deliver the routine case management services offered by Centerstone and report these services in the usual way they do.

Who Is Running the Clinical Trial?

Eleos Health

Lead Sponsor

Trials

2

Recruited

330+

Centerstone Research Institute

Collaborator

Trials

4

Recruited

1,700+

Findings from Research

AI technologies in mental health can enhance patient access and care quality, but current studies mainly address challenges faced by policymakers rather than frontline clinicians.

The proposed framework for 'pragmatic AI-augmentation' categorizes AI technologies into automation, engagement, and clinical decision support, highlighting their potential benefits and the practical challenges clinicians may encounter when integrating them into daily practice.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Pragmatic AI-augmentation in mental healthcare: Key technologies, potential benefits, and real-world challenges and solutions for frontline clinicians. Kellogg, KC., Sadeh-Sharvit, S.[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]

In a study involving 301 participants with depression or anxiety, the IntelliCare platform demonstrated strong engagement, with 84% of users continuing to use the apps for a median of 92 days post-treatment.

Coaching improved anxiety outcomes significantly compared to self-guided treatment, while weekly app recommendations enhanced depression outcomes, indicating that both methods can effectively support mental health through app engagement.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Comparison of the Effects of Coaching and Receipt of App Recommendations on Depression, Anxiety, and Engagement in the IntelliCare Platform: Factorial Randomized Controlled Trial. Mohr, DC., Schueller, SM., Tomasino, KN., et al.[2020]

The use of artificial intelligence (AI) in psychiatry has increased significantly, especially during the COVID-19 pandemic, to address the shortage of mental health providers and improve access to mental health care.

AI applications, such as chatbots and therapy bots, are being developed to assist with psychiatric diagnoses, symptom tracking, and emotional coping mechanisms, showing promise in enhancing mental health support and treatment delivery.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial Intelligence and Chatbots in Psychiatry. Pham, KT., Nabizadeh, A., Selek, S.[2022]

References

1. United States pubmed.ncbi.nlm.nih.gov

Decisional Informatics for Psychosocial Rehabilitation: A Feasibility Pilot on Tailored and Fluid Treatment Algorithms for Serious Mental Illness. [2019]

2. United States pubmed.ncbi.nlm.nih.gov

Machine Learning for Precision Psychiatry: Opportunities and Challenges. [2019]

3. Switzerland pubmed.ncbi.nlm.nih.gov

Pragmatic AI-augmentation in mental healthcare: Key technologies, potential benefits, and real-world challenges and solutions for frontline clinicians. [2022]

4. Australia pubmed.ncbi.nlm.nih.gov

Artificial intelligence (AI) and machine learning (ML) based decision support systems in mental health: An integrative review. [2023]

5. United States pubmed.ncbi.nlm.nih.gov

Artificial intelligence and machine learning in mobile apps for mental health: A scoping review. [2023]

6. Switzerland pubmed.ncbi.nlm.nih.gov

Key Considerations for Incorporating Conversational AI in Psychotherapy. [2022]

7. England pubmed.ncbi.nlm.nih.gov

Could artificial intelligence write mental health nursing care plans? [2023]

8. Netherlands pubmed.ncbi.nlm.nih.gov

[Artificial intelligence in psychiatry: co-creation of human and ChatGPT]. [2023]

9. England 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. [2023]

10. Canada pubmed.ncbi.nlm.nih.gov

A Therapeutic Relational Agent for Reducing Problematic Substance Use (Woebot): Development and Usability Study. [2021]

11. United States pubmed.ncbi.nlm.nih.gov

Psychological Artificial Intelligence Service, Tess: Delivering On-demand Support to Patients and Their Caregivers: Technical Report. [2020]

12. Canada pubmed.ncbi.nlm.nih.gov

Providing Self-Led Mental Health Support Through an Artificial Intelligence-Powered Chat Bot (Leora) to Meet the Demand of Mental Health Care. [2023]

13. Canada pubmed.ncbi.nlm.nih.gov

Comparison of the Effects of Coaching and Receipt of App Recommendations on Depression, Anxiety, and Engagement in the IntelliCare Platform: Factorial Randomized Controlled Trial. [2020]

14. United States pubmed.ncbi.nlm.nih.gov

Artificial Intelligence and Chatbots in Psychiatry. [2022]