Skip to main content
ABCT 2024 58th Annual Convention Main banner
Psychology Tools Ad
Final Program


Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
Recorded Session
Recorded Session
Ticketed Session
Ticketed Session
Back
Evaluation ViewAttendees 3

Technology/Digital Health
Symposia

Symposium 134 - The promise of technological advancements in innovating various aspects of healthcare delivery

Friday, November 15, 2024
8:30 AM – 10:00 AM EST
Location: Congress B, Fourth Floor, Loews Hotel
CE: 1.5

Keywords: Technology / Mobile Health, Implementation, CBT
Level of Familiarity: Basic to moderate
Recommended Readings: Imel, Z. E., Tanana, M. J., Soma, C. S., Hull, T. D., Pace, B. T., Stanco, S. C., ... & Atkins, D. C. (2024). Mental Health Counseling From Conversational Content With Transformer-Based Machine Learning. JAMA Network Open, 7(1), e2352590-e2352590.,   Creed, T. A., Salama, L., Slevin, R., Tanana, M., Imel, Z., Narayanan, S., & Atkins, D. C. (2022). Enhancing the quality of cognitive behavioral therapy in community mental health through artificial intelligence generated fidelity feedback (Project AFFECT): a study protocol. BMC health services research, 22(1), 1177.,   Stade, E., Stirman, S. W., Ungar, L. H., Boland, C. L., Schwartz, H. A., Yaden, D. B., ... & Willer, R. (2023). Large language models could change the future of behavioral healthcare: A proposal for responsible development and evaluation.,   ,  

Our field’s current most urgent and call for action is in addressing the ever-increasing need for mental health services globally with evidence-based interventions. Scaling the reach of evidence-based intervention like CBT is of utmost significance in addressing this access to care gap that we have in mental health. Technological advances provide us with the possibility of innovative solutions that were not available easily before. This symposium showcases five distinct examples of how technological advancements can be leveraged to address the challenges we face along the continuum of healthcare delivery. 
The first talk focuses on how Artificial Intelligence (AI) can aid in the identification of patients who would meaningfully engage with self-paced mindfulness interventions for generalized anxiety disorder and thus, inform personalized treatment recommendations. The subsequent talks exemplify how AI can be harnessed to evaluate the quality of delivery of evidence-based interventions. The second talk describes the user-centered design process engaged to adapt a AI-fidelity monitoring platform to be attuned to the needs of community mental health providers working in a public mental health system, serving patients who identify as historically racial and ethnically marginalized. The talk reports on providers’ acceptance of the adapted AI-fidelity monitoring platform, fidelity evaluation, and patient symptomatology improvement and dropout. The third talk details how large language models were trained and validated to assess fidelity assessment asynchronous messaging based CPT for PTSD, as well as how generative AI applications can also be used to support ongoing therapist fidelity. The fourth talk uses machine learning (ML) to evaluate intervention use in text-based counseling and how they relate to patient engagement, satisfaction, and symptom improvement. The last talk delineates the use of ML to identify distinct patient profiles using a multidimensional outcome measure, and how these relate to distinct treatment options (short-term therapy, long-term therapy, digital interventions) and clinical improvements. 
The discussant will summarize the implications of these talks in how technology can innovatively solution problems in clinical care. Aligning with the year’s conference theme, the public health impact of the results will be highlighted, especially in promoting health equity. 

Learning Objectives:

At the end of this session, the learner will be able to:
  1. State at least 2 different ways that technological advancements been applied in the delivery of mental healthcare
  2. Describe at least 2 patient and provider level impacts of leveraging technological innovations
  3. Delineate at least 1 benefit and 1 limitation of using AI and ML in the various aspects of care provision.
  4. Identify 1 method (AI or ML based) for identifying patients for digital mental health interventions
  5. Describe 1 way that AI can enhance fidelity monitoring of CBT

Presentations:

  • 8:30 AM – 10:00 AM EST
    (SYM 134) Identifying Predictors of Engagement to a Brief Mindfulness Ecological Momentary Intervention for Generalized Anxiety Disorder Using Explainable Artificial Intelligence (AI)

    Speaker: Nur Hani Zainal, M.S., Ph.D. (she/her/hers) – National University of Singapore

    Co-author: Michelle G. Newman, B.S., M.A., Ph.D. (she/her/hers) – The Pennsylvania State University

  • 8:30 AM – 10:00 AM EST
    (SYM 134) A Generative AI Application to Assess and Support Fidelity to Cognitive Processing Therapy

    Speaker: Shannon Wiltsey Stirman, Ph.D. – National Center for PTSD and Stanford University

    Co-author: Elizabeth Stade, PhD (she/her/hers) – Stanford University

    Co-author: Sohayla Elhusseini, B.A. – University of Kentucky

    Co-author: Stefanie T. LoSavio, ABPP (she/her/hers) – University of Texas Health Science Center at San Antonio

    Co-author: Bailee Schuhmann, PhD (she/her/hers) – University of Texas Health Sciences Center for San Antonio

    Co-author: Shashanka Subrahmanya, M.S. (he/him/his) – Stanford University

    Co-author: Johannes Eichstaedt, PhD (he/him/his) – Stanford University

    Co-author: Katherine Dondanville, ABPP, Psy.D. (she/her/hers) – The University of Texas Health Science Center at San Antonio

  • 8:30 AM – 10:00 AM EST
    (SYM 134) Enhancing the Quality of Cognitive Behavioral Therapy in Community Mental Health Through Artificial Intelligence Generated Fidelity Feedback (Project AFFECT)

    Speaker: Torrey Creed, Ph.D. (she/her/hers) – Perelman School of Medicine at the University of Pennsylvania

  • 8:30 AM – 10:00 AM EST
    (SYM 134) Correlation of Machine Learning Derived Estimates of Treatment Mental Health Counseling Content with Patient Outcomes

    Speaker: Zac Imel, Ph.D. (he/him/his) – Lyssn.io

    Co-author: Michael Tanana, Ph.D. (he/him/his) – Lyssn.io, Inc.

    Co-author: Christina Soma, PhD – Lyssn.io

    Co-author: Thomas Hull, PhD – Talkspace

    Co-author: Torrey Creed, Ph.D. (she/her/hers) – Perelman School of Medicine at the University of Pennsylvania

    Co-author: Sarah Stanco, M.A. – Lyssn.io

    Co-author: Theresa Moyers, PhD – University of New Mexico

  • 8:30 AM – 10:00 AM EST
    (SYM 134) Development of Machine Learning Models to Identify and Match Treatment Recommendations

    Speaker: Keke Schuler, Ph.D. – Reliant Medical Group

    Co-author: Keke Schuler, Ph.D. – Reliant Medical Group

    Co-author: Pratha Sah, PhD – Reliant Medical Group

    Co-author: Brittany Jaso, PhD – Reliant Medical Group

    Co-author: Mariesa Pennine, BA – Reliant Medical Group

    Co-author: Mara Eyllon, PhD (she/her/hers) – Reliant Medical Group

    Co-author: Kankana Sengupta, PhD – Reliant Medical Group

    Co-author: J. Ben Barnes, PhD – Reliant Medical Group

    Co-author: Georgia Hoyler, BS – United Health Group

    Co-author: Samuel Nordberg, PhD (she/her/hers) – Reliant Medical Group

    Co-author: Soo Jeong Youn, PhD – Reliant Medical Group