Using Responsible Artificial Intelligence (AI) to Predict Online Therapy Outcome and Engagement

NCT05758285 | Completed

• 1 other identifier: 2022-02263; th23Meinlschmidt
• Study Type: observational
• Target: 6,671
• Locations: 1 country
• Sites: 1

Brief Summary

This study is to develop AI-based models for the personalised prediction of treatment engagement and treatment outcomes in patients engaging in digital psychotherapy. A large, real-world dataset of patients in a digital psychotherapy program will be used to train AI algorithms. Responsible AI algorithms will be developed by describing, accounting for, and mitigating bias due to severity of mental disturbances in AI-based models, in addition to considering bias due to other sensitive attributes, such as gender, ethnicity, and socio-demographic status.

Conditions

Mental Health Care; Mental Disorders

Keywords

Artificial Intelligence (AI); Digital Therapeutics (DTx); Internet-delivered, Cognitive Behaviour Therapy (iCBT); Information and Communication Technology (ICT); Explainable Artificial Intelligence (XAI); Digital psychotherapy; Personalised prediction models; Bias; AI-based prediction models; Online Therapy Unit; Anxiety symptoms; Depressive symptoms; Wellbeing Course

Outcome Measures

Primary Outcomes (2)

• Change in Patient Health Questionnaire 9-item (PHQ9) (percent change)

  Change in PHQ9 (percent change) to evaluate symptom improvement vs. no symptom improvement pre- to post-digital psychotherapy intervention. Patient Health Questionnaire (PHQ-9): Total = /27 ; Depression Severity: 0-4 none, 5-9 mild, 10-14 moderate, 15-19 moderately severe, 20-27 severe.

  week 1 until week 8

• Change in General Anxiety Disorder-7 Questionnaire (GAD7) (percent change)

  Change in General Anxiety Disorder-7 Questionnaire (GAD7) to evaluate symptom improvement vs. no symptom improvement pre- to post-digital psychotherapy intervention. Score 0-4: Minimal Anxiety · Score 5-9: Mild Anxiety · Score 10-14: Moderate Anxiety · Score greater than 15: Severe Anxiety.

  week 1 until week 8

Other Outcomes (4)

• Number of messages sent by client

  week 1 until week 8

• Number of messages received by client

  week 1 until week 8

• Number of phone calls to physician notes

  week 1 until week 8

Interventions

AI-Based Prediction of Treatment Engagement and Outcomes OTHER

AI-based algorithms and prediction models of treatment engagement and outcomes based on data from the Online Therapy Unit by Prof. Heather Hadjistavropoulos will be trained to predict symptom improvement of patients from pre- to post-digital psychotherapy intervention and to predict patients' engagement with the digital psychotherapy intervention and to predict patient drop out probability. For prediction model estimation, state of the art AI-based algorithms, such as XGBoost, is used . XGBoost is a machine learning method developed by refining previously established decision-tree-based methodologies. Data is split into training and testing sets (e.g., 80/20 split).

Eligibility Criteria

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

Study Population

Participants at the publicly funded, internet-delivered, cognitive behaviour therapy (iCBT) program in Saskatchewan, Canada. The program provides symptom screenings and an eight-week transdiagnostic iCBT program called the Wellbeing Course. In Saskatchewan, this transdiagnostic iCBT program has been integrated into the public mental health care, for example by assigning clinicians in community mental health clinics to the Online Therapy Unit and by encouraging therapists to direct patients to this service. Data was collected as part of research trials in the Online Therapy Unit from 2013 to 2021.

You may qualify if:

• Participants that were screened as eligible to take part in a Wellbeing Course trial offered at the Online Therapy Unit between Nov 4 2013 and Dec 21 2021.
• Participants that consented to the use of their data to evaluate and improve iCBT services.
• Accessed Lesson 1 of the course content and completed baseline questionnaires.

You may not qualify if:

• Data will only be excluded in case of errors in data collection

Sponsors & Collaborators

• University Hospital, Basel, Switzerland: lead

Study Sites (1)

University Hospital Basel, Department of Psychosomatic Medicine

Basel, 4031, Switzerland

Location

Related Publications (1)

• Roemmel N, Bahmane S, Hadjistavropoulos HD, Nugent M, Lieb R, Meinlschmidt G. Prediction of treatment outcome in patients receiving internet-delivered cognitive behavioural therapy for depressive and anxiety symptoms: a machine learning analysis of data from a healthcare-embedded longitudinal study. BMJ Open. 2025 Sep 3;15(9):e097651. doi: 10.1136/bmjopen-2024-097651.

  PMID: 40903086 RESULT

MeSH Terms

Conditions

Mental Disorders; Anxiety Disorders; Depression

Interventions

Treatment Outcome

Condition Hierarchy (Ancestors)

Behavioral Symptoms; Behavior

Intervention Hierarchy (Ancestors)

Prognosis; Diagnosis; Outcome Assessment, Health Care; Outcome and Process Assessment, Health Care; Quality of Health Care; Health Services Administration; Health Care Evaluation Mechanisms; Health Care Quality, Access, and Evaluation

Study Officials

• Gunther Meinlschmidt, Prof.

  University Hospital Basel, Department of Psychosomatic Medicine

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: February 24, 2023
• First Posted: March 7, 2023
• Study Start: March 1, 2023
• Primary Completion: December 6, 2024
• Study Completion: September 3, 2025
• Last Updated: November 18, 2025

Record last verified: 2025-11

Locations

CH (1)