AI to Support Mental Health Case Management Providers

NCT06280170 | Enrolling By Invitation

• 1 other identifier: ST11480
• Study Type: interventional
• Target: 280
• Locations: 1 country
• Sites: 1

Brief Summary

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. 1.Is the AI platform acceptable and feasible for case managers?
2. 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.

Conditions

Depressive Disorder; Anxiety Disorders; Substance Use Disorders; Post Traumatic Stress Disorder

Keywords

Case management; Artificial Intelligence; Provider productivity; Mental health services; Provider satisfaction

Outcome Measures

Primary Outcomes (3)

• Case manager satisfaction

  Providers will complete a self-report assessment about their experience providing case management services. Providers will be asked to (a) report the number of of hours spent on documentation per week; (b) respond on a Likert Scale (1-5, 1="Not at all" and 5="highly stressed" regarding their stress level about documentation; and (c) respond on a Likert scale 1-5 (1="Not at all satisfied", 5="Highly satisfied"), indicating their satisfaction with their current role as a case manager.

  Baseline, and 4 months after the rollout of the Eleos Health tool.

• Case manager productivity

  We will collect the number of encounters (i.e., case management visits provided) per month in the three months preceding the start of the study, and months 3-6 after the AI platform rollout.

  3 months before and 3 month after study start date

• Case manager note completion time

  We will record progress note completion time by hours since the time of service delivery (average, standard deviation, and range).

  3 months before and 3 month after study start date

Secondary Outcomes (1)

• Clients' crisis services utilization

  6 months before and 6 month after study start date

Study Arms (2)

Services-as-usual (SAU)

NO 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.

Artificial Intelligence (AI)

EXPERIMENTAL

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.

Other: Artificial Intelligence platform for case managers

Interventions

Artificial Intelligence platform for case managers OTHER

Providers will have access to the Eleos Health mobile AI platform to document their case management encounters.

Artificial Intelligence (AI)

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Participants must be adults.
• Participants must be receiving case management services from a Centerstone provider

You may not qualify if:

• Participants currently involved in any other concurrent research study will be excluded to avoid potential confounding factors.
• Participants with any medical conditions or medications that may significantly interfere with the study outcomes will be excluded.

Sponsors & Collaborators

• Eleos Health: lead
• Centerstone Research Institute: collaborator

Study Sites (1)

Centerstone

Alton, Illinois, 62002, United States

Location

Related Publications (3)

• Kellogg KC, Sadeh-Sharvit S. Pragmatic AI-augmentation in mental healthcare: Key technologies, potential benefits, and real-world challenges and solutions for frontline clinicians. Front Psychiatry. 2022 Sep 6;13:990370. doi: 10.3389/fpsyt.2022.990370. eCollection 2022.

  PMID: 36147984 BACKGROUND

• Sadeh-Sharvit S, Hollon SD. Leveraging the Power of Nondisruptive Technologies to Optimize Mental Health Treatment: Case Study. JMIR Ment Health. 2020 Nov 26;7(11):e20646. doi: 10.2196/20646.

  PMID: 33242025 BACKGROUND

• Sadeh-Sharvit S, Camp TD, Horton SE, Hefner JD, Berry JM, Grossman E, Hollon SD. Effects of an Artificial Intelligence Platform for Behavioral Interventions on Depression and Anxiety Symptoms: Randomized Clinical Trial. J Med Internet Res. 2023 Jul 10;25:e46781. doi: 10.2196/46781.

  PMID: 37428547 BACKGROUND

Related Links

• Link to Eleos Health's science page
• Link to Centerstone Research Institute

MeSH Terms

Conditions

Depressive Disorder; Anxiety Disorders; Substance-Related Disorders; Stress Disorders, Post-Traumatic

Interventions

Case Managers

Condition Hierarchy (Ancestors)

Mood Disorders; Mental Disorders; Chemically-Induced Disorders; Stress Disorders, Traumatic; Trauma and Stressor Related Disorders

Intervention Hierarchy (Ancestors)

Health Personnel; Health Care Facilities Workforce and Services

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Masking Details: The masking in this study involves a differential approach between providers and clients. Providers will be aware of whether they are in the Services-As-Usual (SAU) or Artificial Intelligence (AI) phase. However, participating clients will not be informed about the platform their provider is using to document their therapy sessions.
• Purpose: OTHER
• Intervention Model: SEQUENTIAL
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Model Details: This study will follow a stepped-wedge, randomized controlled design, where each provider team will undergo two phases: SAU and the AI platform phase. All teams will initially start with SAU, and the AI platform will be sequentially introduced to teams over time. Teams will be randomly assigned to different time periods for the AI platform phase using simple randomization. The order of implementation will be determined by randomly selecting the number of the team from sealed envelopes every two months. In both phases, the study will enroll new and existing clients. At the end of the trial all teams would have used Eleos for a few months

Study Record Dates

• First Submitted: January 30, 2024
• First Posted: February 28, 2024
• Study Start: February 19, 2024
• Primary Completion: June 30, 2025
• Study Completion: December 31, 2025
• Last Updated: February 28, 2024

Record last verified: 2024-02

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)